WO2022156352A1 - 地图更新方法、装置和计算机可读存储介质 - Google Patents

地图更新方法、装置和计算机可读存储介质 Download PDF

Info

Publication number
WO2022156352A1
WO2022156352A1 PCT/CN2021/132759 CN2021132759W WO2022156352A1 WO 2022156352 A1 WO2022156352 A1 WO 2022156352A1 CN 2021132759 W CN2021132759 W CN 2021132759W WO 2022156352 A1 WO2022156352 A1 WO 2022156352A1
Authority
WO
WIPO (PCT)
Prior art keywords
data
information
map
map element
type
Prior art date
Application number
PCT/CN2021/132759
Other languages
English (en)
French (fr)
Inventor
刘建琴
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP21920728.9A priority Critical patent/EP4283484A1/en
Publication of WO2022156352A1 publication Critical patent/WO2022156352A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23—Updating
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3807—Creation or updating of map data characterised by the type of data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3833—Creation or updating of map data characterised by the source of data
    • G01C21/3841—Data obtained from two or more sources, e.g. probe vehicles
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3833—Creation or updating of map data characterised by the source of data
    • G01C21/3848—Data obtained from both position sensors and additional sensors
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38—Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804—Creation or updating of map data
    • G01C21/3859—Differential updating map data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
    • G—PHYSICS
    • G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
    • G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
    • G09B29/00—Maps; Plans; Charts; Diagrams, e.g. route diagram
    • G09B29/003—Maps
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02—Services making use of location information

Definitions

  • the present application relates to the technical field of intelligent transportation, and in particular, to a map updating method, device and computer-readable storage medium.
  • High Definition Map is a map with high positioning accuracy and real-time data update.
  • High-precision electronic maps mainly serve self-driving vehicles, providing lane-level planning and self-vehicle positioning assistance in road sections for self-driving vehicles.
  • data is collected by a professional map collecting vehicle, and the map is updated according to the data collected by the professional map collecting vehicle.
  • the cost of professional map collection vehicles is relatively high, and the number of them is small, and the amount of data collected cannot meet the needs of autonomous vehicles for the hourly or even minute-level data update of the map.
  • the cloud server can create and update high-precision maps according to the data collected by multiple data collection devices (such as multiple vehicles), and at the same time publish the updated high-precision maps to vehicles.
  • this high-precision map production and update method will become the mainstream method, and how to improve the accuracy of the produced or updated high-precision map has become an urgent problem to be solved.
  • the present application provides a map updating method, device and storage medium, which are used to determine the information of map elements in combination with data of multiple data types, so that the accuracy of the map can be improved.
  • the present application provides a map updating method, the method comprising: a map updating apparatus can receive data of a first data type and data of a second data type from a plurality of data collection devices; Obtain the first information of the map element; obtain the second information of the map element from the data of the second data type; according to the first information and the second information, determine the target information of the map element on the map, wherein the target information includes the map element at least one of the location information, content information or attribute information of .
  • the first data type and the second data type are: two data types among original data, feature-level data or target-level data.
  • the original data is the data collected by the sensor.
  • Feature-level data is the data extracted from the raw data collected by the sensor that can characterize the features of the detected object.
  • the target-level data is the data extracted from the raw data or feature-level data that can characterize the properties of the detected object.
  • the accuracy of the target information can be improved.
  • feature-level data may filter out some key information due to the filtering of the original data. If the target information of the map element is determined in combination with the original data and the feature-level data, the accuracy of the target information of the map element can be further improved.
  • target-level data may filter out some key information compared to original data and feature-level data due to more information filtering on original data. Therefore, target-level data and feature-level data, or Taking the target-level data and the original-level data into consideration comprehensively to determine the target information of the map element, the accuracy of the target information of the map element can be further improved.
  • the plurality of data collection devices include a first data collection device and a second data collection device
  • the map updating apparatus may obtain the first information of the map elements from the data of the first data type, including: The third information of the map element is obtained from the first data acquired by the first data collection device; the first data is data of the first data type.
  • the fourth information of the map element is obtained from the second data acquired by the second data acquisition device; the second data is data of the first data type. According to the third information and the fourth information, the first information of the map element is obtained. In this way, the first information can be obtained according to a plurality of data of the first data type, so that the accuracy of the first information can be improved.
  • the map updating apparatus may obtain the first information of the map element according to the third information and the fourth information, including: according to the reliability of the first data or the reliability of the second data At least one item, along with the third information and the fourth information, determines the first information. In this way, the reliability of the first information can be further improved.
  • the map updating apparatus may be based on at least one of the reliability of the first data or the reliability of the second data, as well as the third information and the fourth information, including: according to the first data At least one of the reliability of the second data or the reliability of the second data, determine the first weight, and the first weight is used to indicate the degree of influence of the third information on the first information.
  • the second weight is determined according to at least one of the reliability of the first data or the reliability of the second data, and the second weight is used to represent the degree of influence of the fourth information on the first information.
  • the first information is determined according to the first weight, the second weight, the third information, and the fourth information. Since the information of the map elements is weighted and fused according to the reliability of the data, the reliability of the first information can be further improved.
  • the credibility of the first data is related to at least one of the following: the historical map element recognition accuracy of the first data collection device; or, the confidence of the first data.
  • the accuracy of the credibility can be further improved.
  • the reliability of the second data is related to at least one of the following contents: the recognition accuracy rate of historical map elements of the second data collection device; or, the confidence of the second data.
  • the reliability of the first data can be further improved.
  • the accuracy rate of the historical map elements of the second data acquisition device it is possible to take into account the hardware accuracy of the second data acquisition device itself, that is, it is possible to infer the accuracy of the second data based on historical performance. credibility, so the accuracy of the credibility can be further improved.
  • the confidence of the data is combined to determine the credibility of the data, the accuracy of the credibility can be further improved.
  • the confidence of the first data is related to at least one of a parameter of a sensor device that collects the first data, or a relative positional relationship between the sensor device that collects the first data and a map element. In this way, the confidence level of the first data can more accurately reflect the reliability of the first data.
  • the confidence of the second data is related to at least one of a parameter of a sensor device that collects the second data, or a relative positional relationship between the sensor device that collects the second data and a map element. In this way, the confidence level of the second data can more accurately reflect the reliability of the second data.
  • the historical map element recognition accuracy rate of the first data collection device includes at least one of the following: within a preset time period, in the data reported by the first data collection device: map elements The proportion of correctly identified data by information; within a preset time period, among the data of the first data type reported by the first data collection device: the proportion of correctly identified data by map element information; or, within a preset time period , among the data reported by the first data collection device that includes map elements of the same type as the map elements: the proportion of data whose map element information is correctly identified. It can be seen that the identification accuracy rate of historical map elements of the data collection device can be maintained at different granularities, so that the capability of the data collection device can be more accurately evaluated.
  • the historical map element recognition accuracy rate of the second data collection device is used to indicate at least one of the following: within a preset time period, in the data reported by the second data collection device: a map The proportion of the data identified by the element information correctly; within the preset time period, among the data of the first data type reported by the second data collection device: the proportion of the data identified by the map element information correctly; or, within the preset time period In the data reported by the second data collection device that includes map elements of the same type as the map elements: the proportion of data whose map element information is correctly identified. It can be seen that the identification accuracy rate of historical map elements of the data collection device can be maintained at different granularities, so that the capability of the data collection device can be more accurately evaluated.
  • obtaining the second information of the map element from the data of the second data type includes: obtaining the sixth information of the map element from the third data obtained by the third data collection device; the third data data of the second data type.
  • the seventh information of the map element is obtained from the fourth data acquired by the fourth data acquisition device; the fourth data is data of the second data type. According to the sixth information and the seventh information, the second information of the map element is obtained. In this way, the second information can be obtained according to a plurality of data of the second data type, so that the accuracy of the second information can be improved.
  • obtaining the second information of the map element according to the sixth information and the seventh information includes: according to at least one of the reliability of the third data or the reliability of the fourth data, Together with the sixth information and the seventh information, the second information is determined. In this way, the reliability of the second information can be further improved.
  • the map updating apparatus may be based on at least one of the reliability of the third data or the reliability of the fourth data, as well as the sixth information and the seventh information, including: according to the third data At least one of the reliability of the fourth data or the reliability of the fourth data, determine the fifth weight, and the fifth weight is used to indicate the degree of influence of the sixth information on the second information.
  • a sixth weight is determined according to at least one of the reliability of the third data or the reliability of the fourth data, and the sixth weight is used to indicate the degree of influence of the seventh information on the second information.
  • the second information is determined according to the fifth weight, the sixth weight, the sixth information, and the seventh information. Since the information of the map elements is weighted and fused according to the reliability of the data, the reliability of the second information can be further improved.
  • the reliability of the third data is related to at least one of the following contents: the recognition accuracy rate of historical map elements of the third data collection device; or, the confidence of the third data.
  • the recognition accuracy rate of historical map elements of the third data collection device it may be possible to take into account the hardware accuracy of the third data collection device itself, that is, it is possible to infer the accuracy of the third data based on historical performance. credibility, so the accuracy of the credibility can be further improved.
  • the confidence of the data is combined to determine the credibility of the data, the accuracy of the credibility can be further improved.
  • the reliability of the fourth data is related to at least one of the following: the recognition accuracy rate of historical map elements of the fourth data collection device; or, the confidence of the fourth data.
  • the recognition accuracy rate of historical map elements of the fourth data collection device or, the confidence of the fourth data.
  • the confidence of the third data is related to at least one of a parameter of a sensor device that collects the third data, or a relative positional relationship between the sensor device that collects the third data and a map element. In this way, the confidence level of the third data can more accurately reflect the reliability of the third data.
  • the confidence of the fourth data is related to at least one of a parameter of a sensor device that collects the fourth data, or a relative positional relationship between the sensor device that collects the fourth data and a map element. In this way, the confidence level of the fourth data can more accurately reflect the reliability of the fourth data.
  • the map updating apparatus may send target information to the third data collection device, where the target information is used to enable the third data collection device to determine, in combination with the sixth information, that the historical map element identification of the third data collection device is accurate Rate.
  • the target information is used to enable the third data collection device to determine, in combination with the sixth information, that the historical map element identification of the third data collection device is accurate Rate.
  • the map updating apparatus may send target information to the fourth data collection device, where the target information is used to enable the fourth data collection device to determine, in combination with the seventh information, that the historical map element identification of the fourth data collection device is accurate Rate.
  • the target information is used to enable the fourth data collection device to determine, in combination with the seventh information, that the historical map element identification of the fourth data collection device is accurate Rate.
  • the map updating apparatus may update the historical map element recognition accuracy rate of at least one data acquisition device in the plurality of data acquisition devices according to the data received from the plurality of data acquisition devices and the target information
  • at least A data collection device may be a device that provides data of a first data type.
  • the at least one data acquisition device may also be a device providing data of the first data type.
  • the map updating apparatus may determine the historical map element recognition accuracy rate of the third data collection device according to the target information and the sixth information; Historical map element recognition accuracy. In this way, vertical fusion can be further performed according to the historical map element recognition accuracy rate of the data acquisition device, which can further improve the accuracy of vertical fusion.
  • the map updating apparatus may determine the recognition accuracy rate of historical map elements of the fourth data acquisition device according to the target information and the seventh information; and send the historical map of the fourth data acquisition device to the fourth data acquisition device Element recognition accuracy.
  • vertical fusion can be further performed according to the historical map element recognition accuracy rate of the data acquisition device, which can further improve the accuracy of vertical fusion.
  • the historical map element recognition accuracy rate of the at least one data acquisition device includes at least one of the following:
  • the detection success rate of at least one data acquisition device within a preset time period for example, the higher the detection success rate, the higher the historical map element recognition accuracy;
  • the number of times that at least one data collection device has effectively contributed to cloud fusion within a preset time period for example, the more times it has effectively contributed to cloud fusion, the higher the recognition accuracy of historical map elements;
  • the reliability star of at least one data collection device for example, the highest 5 stars, the star rating of the first data collection device is 3 (for example, the higher the reliability star, the The higher the recognition accuracy of historical map elements);
  • the number of times of detection errors in at least one data acquisition device within a preset time period for example, the fewer the times of detection errors, the higher the recognition accuracy of historical map elements;
  • the detection error of at least one data acquisition device within a preset time period for example, the smaller the detection error, the higher the recognition accuracy of historical map elements;
  • At least one data collection device has a star rating of the detection result accuracy; for example, the higher the star rating of the detection result accuracy, the higher the recognition accuracy of historical map elements.
  • the historical map element recognition accuracy rate of the at least one data collection device is: the historical map element recognition accuracy rate for a specific data type.
  • the calculation method of the historical map element recognition accuracy of the third data collection device may be: within a preset time period, in the data of a specific data type reported by the third data collection device: the map element information identifies the correct data. proportion.
  • the data type can also be written as level, and in this case, it can also be written as the recognition accuracy rate of historical map elements for a certain level. In this way, the data accuracy advantage of each data acquisition device under a specific data type can be utilized, and finally the accuracy of map information after fusion of multiple data acquisition devices can be improved.
  • the historical map element recognition accuracy rate of the at least one data collection device is: the historical map element recognition accuracy rate for a specific map element type.
  • the method for calculating the accuracy rate of historical map element recognition of the third data collection device may be: within a preset time period, in the data reported by the third data collection device that includes specific map element types: map element information identification The percentage of correct data. In this way, the data accuracy advantage of each data collection device under a specific map element type can be utilized, and finally the accuracy of map information after fusion of multiple data collection devices can be improved.
  • the historical map element recognition accuracy rate of the at least one data collection device is: the historical map element recognition accuracy rate for a specific data collection environment.
  • the method for calculating the accuracy rate of historical map element recognition of the third data collection device may be: within a preset time period, in the data including the specific data collection environment reported by the third data collection device: the map element information is correctly identified. proportion of the data. In this way, the data accuracy advantage of each data collection device in a specific data collection environment can be utilized, and finally the accuracy of map information after fusion of multiple data collection devices can be improved.
  • the map updating apparatus may indicate a data reporting strategy to at least one data acquisition device, and the data reporting strategy is determined according to the identification accuracy rate of historical map elements.
  • the data reporting policy indicated to the at least one data collection device includes at least one of the following: a reporting period of the at least one data collection device; or, a map element type reported by the at least one data collection device information.
  • the map updating apparatus may indicate to the at least one data acquisition device: the reporting period of the data of the specific data type according to the historical map element recognition accuracy rate of the at least one data acquisition device for the specific data type. In this way, an information reporting strategy can be formulated more reasonably according to the performance of the data collection device.
  • the map updating apparatus may indicate to the at least one data acquisition device: data of map elements of a specific map element type according to the historical map element recognition accuracy rate of the at least one data acquisition device for a specific map element type reporting cycle.
  • an information reporting strategy can be formulated more reasonably according to the performance of the data collection device.
  • the map update apparatus may indicate to the at least one data collection device: reporting of data in a specific data collection environment according to the historical map element recognition accuracy rate of the at least one data collection device for a specific data collection environment cycle. In this way, an information reporting strategy can be formulated more reasonably according to the performance of the data collection device.
  • the map updating apparatus may determine the target information of the map element on the map according to the first information and the second information of the map element, including: according to at least one of the first parameter information or the second parameter information One item, along with the first information and the second information, determines the target information.
  • the first parameter information is used to represent the reliability of the data in the data of the first data type
  • the second parameter information is used to represent the reliability of the data in the data of the second data type. In this way, the accuracy of the target information can be further improved.
  • the map updating apparatus may determine the target information according to at least one of the first parameter information or the second parameter information, as well as the first information and the second information, including: according to the first parameter information or At least one item of the second parameter information is used to determine the third weight, and the third weight is used to indicate the degree of influence of the first information on the target information; according to at least one item of the first parameter information or the second parameter information, the fourth weight is determined. weight, the fourth weight is used to indicate the degree of influence of the second information on the target information; the target information is determined according to the third weight, the fourth weight, the first information and the second information. Since the weighted fusion of the first information and the second information is performed according to the parameter information used to characterize the reliability of the data, the accuracy of the target information can be further improved.
  • the map updating apparatus may determine, according to the first parameter information and the second parameter information, information with a higher degree of reliability among the first information and the second information as the target information. Since the most credible item is eager to determine the target information, the accuracy of the target information can be improved, thereby improving the accuracy of the updated map.
  • the first parameter information includes at least one of the following contents: a preset priority level of the first data type; quantity; the amount of data in the data of the first data type; the confidence level of the data in the data of the first data type; or, the historical map element recognition accuracy rate of the data collection device corresponding to the data in the data of the first data type.
  • the second parameter information includes at least one of the following contents: the preset priority level of the second data type; the information matching the second information in the first information and the second information quantity; the amount of data in the data of the second data type; the confidence level of the data in the data of the second data type;
  • the content included in the first parameter information is sequentially determined according to the priority of the following parameter items: the parameter item with the highest priority is: the preset priority level of the first data type; The next highest parameter item is: the number of information matching the first information in the information of the map element used to determine the target information; the next highest priority parameter item is: the data amount in the data of the first data type.
  • priority is set for each parameter item, so that the accuracy of horizontal fusion can be further improved.
  • the content included in the second parameter information is sequentially determined according to the priority of the following parameter items: the parameter item with the highest priority is: the preset priority level of the second data type; The next highest parameter item is: the number of information matching the second information in the information of the map element used to determine the target information; the next highest priority parameter item is: the data amount in the data of the second data type.
  • priority is set for each parameter item, so that the accuracy of horizontal fusion can be further improved.
  • the confidence level of the data in the data of the first data type is related to at least one of the following: a sensor device parameter of the data acquisition device corresponding to the data in the data of the first data type; or, The relative positional relationship between the data acquisition device and the map element corresponding to the data in the data of the first data type. In this way, the confidence level can more accurately reflect the reliability of the data.
  • the confidence level of the data in the data of the second data type is related to at least one of the following: a sensor device parameter of the data acquisition device corresponding to the data in the data of the second data type; or, The relative positional relationship between the data acquisition device and the map element corresponding to the data in the data of the second data type. In this way, the confidence level can more accurately reflect the reliability of the data.
  • the present application also provides an apparatus.
  • the device may be a map update device, a server-side device, or a chip.
  • the map update device can be used as the map update device on the server side or a communication chip that can be used for the map update device on the server side.
  • an apparatus for updating a map including a communication unit and a processing unit, so as to execute any one of the implementations of the first aspect above.
  • the communication unit is used to perform functions related to transmission and reception.
  • the communication unit includes a receiving unit and a sending unit.
  • the map update device is a communication chip, and the communication unit may be an input and output circuit or port of the communication chip.
  • the communication unit may be a transmitter and receiver, or the communication unit may be a transmitter and receiver.
  • the map updating apparatus further includes various modules that can be used to execute any one of the implementation manners of the first aspect above.
  • a map updating device is provided, and the map updating device is the above-mentioned server-side map updating device. Includes processor and memory. Optionally, it also includes a transceiver, the memory is used to store a computer program or instruction, the processor is used to call and run the computer program or instruction from the memory, and when the processor executes the computer program or instruction in the memory, make the computer program or instruction in the memory.
  • the map updating apparatus executes any one of the implementations of the above-mentioned first aspect.
  • processors there are one or more processors and one or more memories.
  • the memory may be integrated with the processor, or the memory may be provided separately from the processor.
  • the transceiver may include a transmitter (transmitter) and a receiver (receiver).
  • a map updating apparatus including a processor.
  • the processor coupled to the memory, is operable to perform the method of any of the possible implementations of the first aspect.
  • the map updating apparatus further includes a memory.
  • the map updating apparatus further includes a communication interface, and the processor is coupled to the communication interface.
  • the map update device is a map update device on the server side.
  • the communication interface may be a transceiver, or an input/output interface.
  • the transceiver may be a transceiver circuit.
  • the input/output interface may be an input/output circuit.
  • the map updating apparatus is a chip or a chip system.
  • the communication interface may be an input/output interface, an interface circuit, an output circuit, an input circuit, a pin or a related circuit on the chip or a chip system.
  • a processor may also be embodied as a processing circuit or a logic circuit.
  • a system which includes the above-mentioned data acquisition device and a server-side map updating apparatus.
  • a vehicle including the above data collection device.
  • a computer program product comprising: a computer program (also referred to as code, or an instruction), when the computer program is executed, the map updating apparatus executes any one of the above-mentioned first aspects methods in possible implementations.
  • a computer-readable storage medium stores a computer program (also referred to as code, or instruction), when it runs on a processor, to cause the map updating apparatus to execute the above-mentioned first aspect method in any of the possible implementations.
  • a computer program also referred to as code, or instruction
  • a system-on-chip may include a processor.
  • the processor coupled to the memory, is operable to perform the method of any of the possible implementations of the first aspect.
  • the chip system further includes a memory.
  • Memory used to store computer programs (also called code, or instructions).
  • the processor is used to call and run the computer program from the memory, so that the device installed with the chip system executes the method in any possible implementation manner of the first aspect.
  • the above-mentioned map updating device can be a chip
  • the input circuit can be an input pin
  • the output circuit can be an output pin
  • the processing circuit can be a transistor, a gate circuit, a flip-flop, and various logic circuits.
  • the input signal received by the input circuit may be received and input by, for example, but not limited to, a receiver
  • the signal output by the output circuit may be, for example, but not limited to, output to and transmitted by a transmitter
  • the circuit can be the same circuit that acts as an input circuit and an output circuit at different times.
  • the embodiments of the present application do not limit the specific implementation manners of the processor and various circuits.
  • FIG. 1 is a schematic diagram of a scenario to which an embodiment of the present application is applicable
  • FIG. 2 is a schematic flowchart of a method for updating a map according to an embodiment of the present application
  • FIG. 3 is a schematic flowchart of a method for updating a map according to an embodiment of the present application
  • FIG. 4 is a schematic structural diagram of a communication device according to an embodiment of the present application.
  • FIG. 5 is a schematic structural diagram of another communication device provided by an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of another communication apparatus provided by an embodiment of the present application.
  • FIG. 1 exemplarily shows a schematic diagram of a scenario to which this embodiment of the present application is applicable.
  • the data acquisition device can be a terminal device.
  • the terminal device is a vehicle as an example for illustration.
  • three vehicles are schematically shown in FIG. 1 , namely, a vehicle 201 , a vehicle 202 , and a vehicle 203 .
  • the data collection device may also be the roadside unit 206 .
  • the application scenarios of the embodiments of the present application may further include a server 204, a storage device 205, and the like.
  • the server may be configured to determine the information of the map elements according to the data collected by each data collection device, and then update the map according to the information of the map elements.
  • Storage device 205 may be used to store maps.
  • the terminal device in this embodiment of the present application may be a vehicle or non-motor vehicle, a portable device, a wearable device, or a mobile phone (or a "cellular" phone) with a communication function, and may also be a component or chip in these devices Wait.
  • the terminal device in this application may refer to the terminal device applied to the Internet of Vehicles, and the terminal device in this application may also be referred to as the Internet of Vehicles terminal device, the Internet of Vehicles terminal, the Internet of Vehicles communication device or the in-vehicle terminal device and so on.
  • a vehicle (such as any one of the vehicle 201 , the vehicle 202 or the vehicle 203 ) is a typical terminal device in the Internet of Vehicles.
  • a vehicle is used as an example for description. Any vehicle may be a smart car or a non-smart car, and the comparison of the embodiments of the present application is not limited. It should be understood by those skilled in the art that the embodiments in the present application taking the vehicle as an example can also be applied to other types of terminal devices.
  • the terminal device can execute the related business processes of the Internet of Vehicles through its internal functional units or devices.
  • the terminal device when the terminal device is a vehicle, one or more of the following devices in the vehicle may be used to execute the method process related to the terminal device in the embodiments of the present application, such as a telematics box (T-Box), a domain controller (domain controller) , DC), multi-domain controller (MDC), on board unit (OBU) or car networking chip, etc.
  • T-Box telematics box
  • domain controller domain controller
  • DC domain controller
  • MDC multi-domain controller
  • OBU on board unit
  • car networking chip etc.
  • the vehicle may communicate with other objects based on a wireless communication technology between the vehicle and the outside world (for example, vehicle to everything (V2X)).
  • V2X vehicle to everything
  • the communication between the vehicle and the cloud server can be realized based on V2X.
  • Communication between vehicles and other objects may be based on wireless high-fidelity (eg, wireless fidelity (Wi-Fi)), fifth-generation (5th generation, 5G) mobile communication technologies, and the like.
  • Wi-Fi wireless fidelity
  • 5G fifth-generation
  • communication between the vehicle and other devices, such as the roadside unit 206 or the server 204 may be enabled based on 5G.
  • the terminal device may be used to collect surrounding environment information, for example, the surrounding environment information may be collected through a sensor set on the terminal device.
  • a data collection device may be included in the vehicle.
  • the data collection device can collect data through the sensor, and transmit the raw data collected through the sensor to the server or roadside unit, so that it can update the map.
  • the data acquisition device can also process the original data to obtain processed data (such as feature-level data, target-level data, etc.), and transmit the processed data to the server or roadside unit, so that it can update the map.
  • the data collection device in the vehicle in the embodiment of the present application may be a component in the vehicle, the vehicle itself, or a mobile phone.
  • the data acquisition device may include the data acquisition device of the positioning system in the vehicle, the data acquisition device of intelligent driving, or any other device with computing capability.
  • a terminal device such as a vehicle
  • the sensor is used to collect images near the vehicle
  • the sensor may include a camera, a lidar, a millimeter-wave radar, an ultrasonic wave, and the like.
  • each vehicle may be provided with one or more sensors, and the number of each sensor may be one or more.
  • the sensors may be installed on the roof of the vehicle (for example, may be arranged in the middle of the roof of the vehicle), the front end of the vehicle, etc. The embodiments of the present application do not limit the installation position and number of sensors in each vehicle.
  • this application scenario can include RSU206, which can be used to send vehicle to everything (vehicle to everything) to terminal equipment through communication methods such as direct communication (such as PC5) or dedicated short range communications (DSRC). everything, V2X) message.
  • the V2X message can carry dynamic information or other information that needs to be notified to the terminal device.
  • the communication method between the roadside unit and the terminal equipment may also be called vehicle to roadside infrastructure (V2I) communication.
  • FIG. 1 only shows that the roadside unit 206 has a communication path with the vehicle 201 and the server 204. In practical applications, the roadside unit 206 may also communicate with other vehicles, such as the vehicle 202, the vehicle 203, etc. Communication paths, not shown in the figure.
  • the roadside unit can also be used to report dynamic information occurring within the jurisdiction to the Internet of Vehicles server, for example, reporting dynamic information through roadside information (RSI) messages.
  • RSSI roadside information
  • the system architecture to which the embodiments of the present application are applicable may include roadside units, or may not include roadside units, which are not limited in the embodiments of the present application.
  • the roadside unit may perform key perception on some specified elements according to the instructions issued by the server, and report the perception results.
  • the roadside unit may also send an instruction to the terminal device or deliver an updated map.
  • the roadside unit in the embodiment of the present application may also be provided with a data collection device.
  • the data collection device can collect data through the sensor, and transmit the raw data collected through the sensor to the server or roadside unit, so that it can update the map.
  • the data acquisition device can also process the original data to obtain processed data (such as feature-level data, target-level data, etc.), and transmit the processed data to the server or roadside unit, so that it can update the map.
  • processed data such as feature-level data, target-level data, etc.
  • this application scenario may include a server 204, and the server 204 may be a vehicle networking platform or server that manages and provides services for terminal devices and/or roadside units, including providing services for high-precision maps and navigation maps application server or map cloud server.
  • the server 204 may be used for functions such as updating the map according to the data reported by the data collection device, and updating and delivering the high-precision map.
  • the specific deployment form of the server is not limited in this application, for example, it may be deployed in the cloud, or it may be an independent computer device or chip.
  • the server can send the V2X message to the roadside unit, and the roadside unit broadcasts it to the terminal equipment in its coverage area.
  • the server can also directly send the V2X message to the terminal device.
  • a storage device 205 may be used, and the storage device 205 may be used to store data, such as a map.
  • Data types include: original data, feature-level data and target-level data.
  • a data acquisition device such as a vehicle
  • a sensor is used to collect images near the vehicle
  • the sensor may include a camera, a lidar, a millimeter-wave radar, an ultrasonic wave, and the like.
  • each vehicle may be provided with one or more sensors, and the number of each sensor may be one or more.
  • the sensors may be installed on the roof of the vehicle (for example, may be arranged in the middle of the roof of the vehicle), the front end of the vehicle, etc. The embodiments of the present application do not limit the installation position and number of sensors in each vehicle.
  • three types of data are defined: original data, feature level (Feature Level) data, and target level data.
  • the raw data collected by the sensor in the embodiment of the present application can be processed to obtain at least one of feature-level data or target-level data.
  • the three data types are described below.
  • Raw data is the data collected by the sensor.
  • the raw data is lidar point cloud data; when the sensor is a camera, the raw data is pixel-level data.
  • Pi is the information of a certain point in the environment detected by the sensor
  • N represents the number of environmental points detected by the sensor.
  • Pi represents the three-dimensional coordinate information of a point in the environment
  • Pi represents the pixel information of a point in the environment mapped to a two-dimensional image.
  • Feature level (Detection Level or Feature Level) data is the data extracted from the raw data collected by the sensor that can characterize the characteristics of the detected object.
  • Features for example, can be the key points of the shape and outline of a detected object, or can be local gradient features obtained through 3D laser point clouds or images in the environment.
  • the object level data is the data extracted from the original data or feature level data that can characterize the properties of the detected object.
  • Object-level data has significant semantic features, such as lane lines, traffic lights, or traffic signs.
  • feature extraction and target extraction can be used to achieve conversion between data types.
  • feature extraction can be performed on raw data to obtain feature-level data
  • target extraction can be performed on original data to obtain target-level data
  • feature-level data can be obtained by performing target extraction on raw data.
  • Target-level data can be obtained by performing target extraction on the data, and this embodiment is not limited to the methods of feature extraction and target extraction.
  • the map elements in the embodiments of the present application refer to some elements in the map, including but not limited to: roads, lane lines, signs, ground signs, signal lights, drivable area identification lines, and the like.
  • the road can include guardrails, road edges, etc.; signs include: road signs, indicative signs, height limit signs and other types, and ground signs include: diversion signs, entrance and exit signs, speed limit signs, time limit signs, etc.
  • the embodiments of the present application may be applied to high-precision maps.
  • high-precision maps are electronic maps with higher precision, more data dimensions, and more map elements. Higher accuracy is reflected in the fact that the feature information contained in the map is accurate to the centimeter level.
  • FIG. 2 exemplarily shows a schematic flowchart of a map updating method provided by an embodiment of the present application, and the method may be executed by a map updating apparatus and a data collection device.
  • the map updating apparatus may be located on the server side, for example, may be a device on the server side, or a module on the server, or a chip on the server.
  • the data collection device mentioned in the embodiments of the present application may be located at the vehicle end, for example, may be a vehicle, or a module of the vehicle, or may be a chip on the vehicle.
  • the data acquisition device may also be located at the RSU end, such as the RSU, a module on the RSU, or a chip on the RSU.
  • the method includes:
  • Step 201 one or more data collection devices report data.
  • the map updating apparatus receives data of N data types from a plurality of data collection devices, where N is an integer greater than 1.
  • the N data types are multiple data types among original data, feature-level data, or target-level data. It should be noted that the three data types mentioned in the embodiments of the present application are only examples, and the data types applicable to the embodiments of the present application are not limited to these three types. For the introduction of these three data types, please refer to the foregoing content, which will not be repeated here.
  • Step 202 the map updating apparatus obtains N pieces of information of map elements from data of N data types. Among them, N pieces of information are in one-to-one correspondence with N kinds of data types.
  • Step 203 the map updating apparatus determines target information of the map element on the map according to the N pieces of information.
  • the target information includes at least one item of location information, content information or attribute information of the map element.
  • the target information may be at least one of the position information of the lane line, the color of the lane line, or the specific shape (solid line or dotted line, etc.) of the lane line.
  • the target information may be at least one of the location information of the sign, the content of the sign, the shape of the sign, or the color of the sign.
  • the target information may be the location information of the ground mark, the specific shape of the ground mark, or at least one of the colors of the ground mark. one.
  • the target information may be at least one of the position information of the signal light or the specific shape of the signal light.
  • the target information may be the location information of the drivable area identification line, or at least one of the specific content of the drivable area identification line.
  • the target information may be at least one of the position information of the obstacle or the shape information of the obstacle.
  • a possible implementation manner of FIG. 2 includes: obtaining the first information of the map element from data of the first data type.
  • the second information of the map element is obtained from the data of the second data type. According to the first information and the second information, target information of the map element on the map is determined.
  • a possible implementation manner of FIG. 2 includes: obtaining the first information of the map element from data of the first data type.
  • the second information of the map element is obtained from the data of the second data type.
  • the fifth information of the map element is obtained from at least one data of the third data type. According to the first information, the second information and the fifth information, target information of the map element on the map is determined. Subsequent content
  • the first data type is target-level data
  • the second data type is feature-level data
  • the third data type is raw data as an example for introduction.
  • FIG. 3 exemplarily shows a schematic diagram of another possible scenario to which the embodiments of the present application are applicable.
  • the map updating method provided by the embodiment of the present application will be introduced below with reference to FIG. 3 .
  • the data collection device is a vehicle as an example for illustration, such as vehicle V 11 , vehicle V 12 , vehicle V 21 , vehicle V 22 , vehicle V 31 , and vehicle V 32 as shown in FIG. 3 .
  • the following content takes the map element as an obstacle (the obstacle can be, for example, a traffic cone) as an example, and the information of the map element can be the position information of the obstacle or the shape of the obstacle.
  • the information of the map element is taken as an example of the position information of the obstacle for introduction.
  • the data types reported by any vehicle in this embodiment of the application may be one or more types, for example, one or more types of raw data, feature-level data, or target-level data.
  • the types of reported data types are not limited.
  • FIG. 3 is just an example.
  • the data types of the data reported by the vehicle V 11 (the first data collection device) and the vehicle V 12 (the second data collection device) are target-level data (the first data type).
  • the data reported by at least one of the vehicle V 11 or the vehicle V 12 may include that the obstacle is a traffic cone, and the location information of the traffic cone.
  • the data type of the data reported by the vehicle V 21 (the third data collection device) or the vehicle V 22 (the fourth data collection device) is feature-level data (the second data type).
  • the data reported by at least one of the vehicle V 21 or the vehicle V 22 may include: shape outline key point information of the obstacle.
  • the data types of the data reported by the vehicle V 31 (the fifth data acquisition device) and the vehicle V 32 (the sixth data acquisition device) are raw data (third data type).
  • the data reported by at least one of the vehicle V 31 or the vehicle V 32 may include: lidar point cloud data of obstacles.
  • the server 204 in the cloud may first perform vertical integration of the data of each data type.
  • the vertical fusion mentioned in the embodiments of this application refers to the fusion of data of the same data type.
  • the map updating device fuses the target-level data (first data) reported by the vehicle V 11 and the target-level data (second data) reported by the vehicle V 12 to obtain the position information (map) of the corresponding obstacles in the fused target-level data. element's first information).
  • one position information (third information) of the obstacle can be obtained from the target-level data reported by the vehicle V11
  • another position of the obstacle can be obtained from the target-level data reported by the vehicle V12.
  • the information (fourth information) is fused according to the position information of the obstacle to obtain the position information of the obstacle corresponding to the fused target-level data (the first information of the map element).
  • the map update device fuses the feature-level data (third data) reported by the vehicle V 21 and the feature-level data (fourth data) reported by the vehicle V 22 , and obtains the position information (map) of the corresponding obstacle in the fused feature-level data. element's second information).
  • one position information (sixth information) of the obstacle can be obtained from the feature-level data reported by the vehicle V 21
  • another position of the obstacle can be obtained from the feature-level data reported by the vehicle V 22 .
  • the information (seventh information) is fused according to the two position information of the obstacle to obtain the position information of the obstacle (second information of the map element) corresponding to the fused feature-level data.
  • the map update device fuses the original data (the fifth data) reported by the vehicle V 31 and the original data (the sixth data) reported by the vehicle V 32 to obtain the position information of the corresponding obstacle (the first data of the map element) after the fusion of the original data. 5 information).
  • the position information of the obstacle can be obtained from the original data reported by the vehicle V 31
  • another position information of the obstacle can be obtained from the original data reported by the vehicle V 32 .
  • Nine information) fuse the two position information of the obstacle to obtain the position information of the obstacle corresponding to the fused original data (the fifth information of the map element).
  • the target information of the map element is the information of the map element on the updated map.
  • the position information of the obstacle corresponding to the fused target-level data (the first information of the map element)
  • the position information of the obstacle corresponding to the fused feature-level data (the second information of the map element)
  • the fused position information of the obstacle corresponding to the original data (the fifth information of the map element) is fused, and finally the position information of the obstacle is obtained, which is the target information of the map element.
  • the position information of the obstacle corresponding to the fused target-level data is position information 1
  • the position information of the obstacle corresponding to the fused feature-level data is position information 2
  • the obstacle corresponding to the fused original data is The location information is location information 3.
  • the feature-level data may filter the original data
  • some key information may be filtered out
  • the target-level data may filter out more information, so a possible sorting method of data type priority is:
  • the raw data has the highest priority
  • the feature-level data has the next priority
  • the target-level data has the lowest priority.
  • the position information of the obstacle can be determined as: position information 3 after horizontal fusion.
  • the map update device on the server side in the embodiment of the present application may also update the historical map element identification of at least one data acquisition device among the multiple data acquisition devices according to the data received from the multiple data acquisition devices and the target information. Rate.
  • the at least one data acquisition device may be a device that provides data of a first data type.
  • the at least one data acquisition device may also be a device providing data of the second data type.
  • the map update device on the server side can calculate the accuracy rate of historical map element recognition of the data acquisition device on or the terminal based on the target information, and then send the historical map element recognition readiness rate of the data acquisition device to the data acquisition device.
  • the map update device on the server side may also send target information to the data acquisition devices at each vehicle end, so that each of them maintains the identification accuracy rate of historical map elements.
  • the recognition accuracy of historical map elements the subsequent content will be introduced in detail, and will not be elaborated here.
  • horizontal and vertical closed-loop fusion can be implemented in the embodiment of the present application, that is, according to the data reported by each data acquisition device, vertical fusion is performed for the same type of data, and then the fusion corresponding to each data type is obtained. The data. Further horizontal fusion is performed again for the fused data corresponding to each data type, and the final result is used as the target information of the map element to update the map. Further, the obtained target information of map elements is used to feed back to each data acquisition device, so that each data acquisition device maintains its own historical map element recognition accuracy.
  • the accuracy of the target information can be improved.
  • feature-level data may filter out some key information due to the filtering of the original data. If the target information of the map element is determined in combination with the original data and the feature-level data, the accuracy of the target information of the map element can be further improved.
  • target-level data may filter out some key information compared to original data and feature-level data due to more information filtering on original data. Therefore, target-level data and feature-level data, or Taking the target-level data and the original-level data into consideration comprehensively to determine the target information of the map element, the accuracy of the target information of the map element can be further improved.
  • the data may be fused according to the reliability corresponding to the data in the multiple pieces of data.
  • the first information may be determined according to at least one of the reliability of the first data or the reliability of the second data, as well as the third information and the fourth information. The higher the reliability of the data, the greater the influence of the information of the map elements in the data on the first information.
  • the information of the map element corresponding to the data with the highest reliability may be used as the first information.
  • the target level data (first data) reported by the vehicle V 11 has a higher reliability
  • the position information of the obstacle determined according to the first data is the position information 4
  • the target level data reported by the vehicle V 12 is higher.
  • the position information of the obstacle identified by the data (second data) is position information 5 .
  • the position information 4 can be determined as the first information of the obstacle.
  • the information of the map element in the vertical fusion result corresponding to the data type there are three vehicles, the data types reported by the three vehicles are all target-level data, and the location information of the obstacles determined according to the data reported by the three vehicles are location information 6, location information 7 and location information respectively.
  • Information 7. since the position information 7 accounts for a large proportion of the total amount, it can be determined that in the result of vertical fusion of the target-level data: the position information of the obstacle is the position information 7 .
  • the first weight is determined according to at least one of the reliability of the first data or the reliability of the second data, and the first weight is used to represent the third information to the first information. influence level.
  • the second weight is determined according to at least one of the reliability of the first data or the reliability of the second data, and the second weight is used to represent the degree of influence of the fourth information on the first information.
  • the first information is determined according to the first weight, the second weight, the third information, and the fourth information.
  • target-level data (such as the first data and the second data in FIG. 3 ) is taken as an example for illustrative introduction.
  • data fusion can be performed on the first data and the second data by formula (1):
  • y is the data fusion result
  • the above result 1 can be understood as the third information of the map element determined from the first data
  • result 2 is the fourth information of the map element determined from the first data
  • y is the pair of After the first data and the second data are fused, the first information is obtained from the fused data.
  • the credibility of a piece of data can be divided into finer details, so that different map elements in the data correspond to different credibility respectively. It is not difficult to understand that if the proportion of the credibility of the first data in the sum of the credibility of the first data and the second data is larger, the proportion of the first data in the fusion result is larger. It can also be understood that, which sensor device has a relatively large value of reliability, the sensing data detected by which sensor device accounts for a relatively large proportion in the fusion result.
  • the fusion of target-level data is taken as an example for an exemplary introduction, and the fusion scheme for raw data and feature-level data is similar.
  • a fifth weight is determined according to at least one of the reliability of the third data or the reliability of the fourth data, and the fifth weight is used to indicate the degree of influence of the sixth information on the second information.
  • a sixth weight is determined according to at least one of the reliability of the third data or the reliability of the fourth data, and the sixth weight is used to indicate the degree of influence of the seventh information on the second information.
  • the second information is determined according to the fifth weight, the sixth weight, the sixth information, and the seventh information. The manner of determining the second information is similar to that of the first information, and details are not repeated here.
  • the reliability of the data collected by a data collection device may include at least one of the confidence of the data, or the recognition accuracy rate of historical map elements of the data collection device.
  • Parameter item a1 the confidence level corresponding to the first data.
  • the confidence of the first data is related to at least one of a parameter of a sensor device that collects the first data, or a relative positional relationship between the sensor device that collects the first data and a map element.
  • the confidence level may be determined according to one or more of the parameters of the sensing device that collected the first data, the perceived distance of the map element, and the perceived angle of the map element.
  • the parameters of the sensing device are related to the initial accuracy of the sensing device itself, the installation space angle and the installation coordinates.
  • the perceived distance of the map element is the distance between the map element and the sensing device in the perceived coordinate system.
  • the perception angle of the map element is the angle formed by the map element and the sensing device in the perception coordinate system.
  • the confidence level of the sensor device can be obtained by weighting or averaging the confidence levels of the multiple sensors included in the sensor device.
  • the value of the confidence level will be larger, and if the accuracy of the parameters of the sensor device is lower, the value of the confidence level will be smaller. If the perceived distance is smaller, the value of the confidence is larger, and if the perceived distance is larger, the value of the confidence is smaller. If the perception angle is smaller, the confidence value is larger, and if the perception angle is larger, the confidence value is smaller.
  • Confidence can be used to measure the credibility of the recognition results.
  • there are currently many methods for calculating confidence in the industry including at least the following:
  • the calculation method of the confidence level in the embodiment of the present application is not limited to the above-mentioned ones, and any calculation method that can be used to determine the confidence level can be applied to the embodiment of the present application, and all belong to the protection scope of the embodiment of the present application .
  • Parameter item a2 the recognition accuracy rate of historical map elements of the first data collection device.
  • the historical map element recognition accuracy rate of the first data acquisition device may be maintained according to historical data.
  • one or more of the following parameter item a2-1, parameter item a2-2 and parameter item a2-3 may be included.
  • Parameter item a2-1 in the preset time period, among the data reported by the first data collection device: the proportion of the data whose map element information is correctly identified.
  • the proportion of the data for which the map element information is correctly identified can also be understood as: the accuracy rate of the map element information identification.
  • the first data collection device reports information of K0 map elements, wherein the information of K1 map elements satisfies the first preset condition. Wherein, if the first preset condition is satisfied, it can be said that the information of the map element belongs to the correctly detected data.
  • the ratio of K1 to K0 may be used as the identification accuracy rate of historical map elements of the first data acquisition device.
  • K0 is a positive integer
  • K1 is an integer not greater than K0.
  • the information of a map element that satisfies the first preset condition may include the following:
  • the information of the map element is location information
  • the distance between the location indicated by the location information of the map element included in the data and the location indicated by the location information of the finally determined map element is less than the preset distance threshold, it can be said that the data satisfies the first preset condition
  • the data can be said to satisfy the first preset condition.
  • the recognition accuracy rate of historical map elements of the first data collection device may also be used to indicate one or more of the following:
  • the detection success rate of the first data collection device within a preset time period (for example, the higher the detection success rate, the higher the historical map element recognition accuracy);
  • the number of times the first data collection device has effectively contributed to the cloud fusion within a preset time period for example, the more times the first data collection device has effectively contributed to the cloud fusion, the higher the recognition accuracy of historical map elements
  • the star rating of the reliability of the first data collection device for example, the highest 5 stars, the star rating of the first data collection device is 3 (for example, the higher the star rating of the reliability, the higher the star rating of the first data collection device. The higher the recognition accuracy of historical map elements);
  • the number of times that the first data collection device has detection errors within the preset time period (for example, the fewer the times of detection errors, the higher the recognition accuracy of historical map elements);
  • the first data acquisition device detects the size of the error (for example, the smaller the detection error, the higher the recognition accuracy of historical map elements);
  • the first data collection device detects the star rating of the result accuracy (for example, the higher the star rating of the detection result accuracy, the higher the historical map element recognition accuracy).
  • Parameter item a2-2 in the preset time period, among the data of the first data type reported by the first data collection device: the proportion of the data correctly identified by the map element information.
  • the proportion of the data for which the map element information is correctly identified can also be understood as: the accuracy rate of the map element information identification.
  • the first data collection device reports the information of K0 map elements, the information of K2 map elements exists in the information of the K0 map elements, and the information of the K2 map elements is the first
  • the data collection device is carried by reporting data of the first data type.
  • the information of K3 map elements in the information of K2 map elements satisfies the first preset condition.
  • the ratio of K3 to K2 is the historical map element recognition accuracy rate in the data of the first data type reported by the first data collection device.
  • the ratio of K3 to K2 can be used as the historical map element recognition accuracy rate of the first data acquisition device.
  • K2 is an integer not greater than K0
  • K3 is an integer not greater than K2. In this way, the information identification accuracy of the map elements of the data collection device can be maintained based on the granularity of the data type.
  • the recognition accuracy rate of historical map elements of the first data collection device may also be used to indicate one or more of the following:
  • the reliability of the first data collection device on the data of the first data type has a star rating, for example, a maximum of 5 stars, and the first data collection device has a star rating of 3;
  • the first data acquisition device detects the size of the error on the data of the first data type
  • the first data collection device detects the star level of the result accuracy on the data of the first data type.
  • Parameter item a2-3 in the preset time period, among the data reported by the first data collection device including the map element of the same type as the map element: the proportion of the data whose map element information is correctly identified.
  • the proportion of the data for which the map element information is correctly identified can also be understood as: the accuracy rate of the map element information identification.
  • the embodiment of the present application involves type information of map elements, map elements can be classified, each type of map element can be identified by a type, and the type information mentioned herein can be a type identifier.
  • the classification rules are not limited, for example, the signs can be divided into one category, or the ground signs can be divided into one category and so on.
  • the first data collection device reports information of K0 map elements, information of K4 map elements exists in the information of K0 map elements, and each of the information of the K4 map elements contains information of K4 map elements.
  • the type of each map element is the same type as the type of the map element mentioned in the above step 227, for example, it can be the content recognition of the sign, and the like.
  • the type of the map element mentioned in the above step 227 is referred to as the first type.
  • the type of each map element in the information of the K4 map elements is the first type.
  • the ratio of K5 to K4 is the identification accuracy rate of map element information in the data including the map element of the same type as the map element reported by the first data collection device.
  • the ratio of K5 to K4 may be used as the identification accuracy rate of map element information of the first data acquisition device.
  • K4 is an integer not greater than K0
  • K5 is an integer not greater than K4. In this way, the information identification accuracy of the map elements of the data collection device can be maintained based on the granularity of the map elements.
  • the map element recognition accuracy rate of the first data collection device may also be used to indicate one or more of the following:
  • the first data collection device has a reliability star rating of the first type of map element, for example, the highest 5 stars, and the first data collection device has a star rating of 3;
  • the first data acquisition device detects the error size on the map element of the first type
  • the first data collection device detects the star level of the result accuracy on the map element of the first type.
  • the above-mentioned parameter item a2-1, parameter item a2-2 and parameter item a2-3 can also be combined, for example, within a preset time period, the first data collection device reports K0 information of K0 map elements, information of K4 map elements exists in the information of K0 map elements, and the type of each map element in the information of the K4 map elements is the same as the type of the map element mentioned in the above step 227.
  • the same type such as content recognition that can be both signs, etc.
  • the information of the K5 map elements exists in the information of the K4 map elements, and the information of the K5 map elements all satisfy the first preset condition.
  • the K6 map elements in the K5 map elements are carried by the first data acquisition device by reporting the data of the first data type.
  • the ratio of K6 to K4 may be used as the historical map element recognition accuracy rate of the first data acquisition device.
  • K6 is an integer not greater than K5. In this way, the information identification accuracy of the map elements of the data collection device can be maintained based on the granularity of the map elements and data types.
  • the information of a plurality of map elements in the information of the K0 map elements may be sent to the map update device through one data reporting process, or may be sent to the map update device through multiple data reporting processes. That is to say, when the data collection device reports data once, the number of map elements included in the data is not limited, and it can be one or more.
  • the server in this embodiment of the present application may also send target information to each data collection device, so that each of them maintains the historical map element identification accuracy.
  • the server may calculate or update the historical map element recognition accuracy rate of the data collection device based on the target information, and then send it to the data collection device.
  • the map updating apparatus sends target information to the first data collection device, where the target information is used to enable the first data collection device to determine the historical map element recognition accuracy of the first data collection device in combination with the third information.
  • the map update device sends target information to the second data collection device, and the target information is used to enable the second data collection device to determine the historical map element recognition accuracy of the second data collection device in combination with the fourth information.
  • the map update device determines the recognition accuracy rate of historical map elements of the first data acquisition device according to the target information and the third information; and sends the historical map elements of the first data acquisition device to the first data acquisition device. recognition accuracy.
  • the map update device determines the accuracy rate of identifying historical map elements of the second data acquisition device according to the target information and the fourth information; and sends the historical map elements of the second data acquisition device to the second data acquisition device. recognition accuracy.
  • the reliability of the second data is related to one or more items of the historical map element recognition accuracy of the second data collection device and the confidence of the second data.
  • the confidence of the second data is related to at least one of a parameter of the sensor device that collects the second data, or a relative positional relationship between the sensor device that collects the second data and a map element.
  • the reliability of the third data is related to at least one of the following: the recognition accuracy rate of historical map elements of the third data collection device, or the confidence of the third data.
  • the reliability of the fourth data is related to at least one of the following: the recognition accuracy rate of historical map elements of the fourth data collection device, or the confidence of the fourth data.
  • the confidence of the third data is related to at least one of the parameters of the sensor device collecting the third data, or the relative positional relationship between the sensor device collecting the third data and the map element.
  • the confidence of the fourth data is related to at least one of a parameter of the sensor device that collects the fourth data, or a relative positional relationship between the sensor device that collects the fourth data and a map element.
  • the map update device in the embodiment of the present application can combine the map element identification readiness rate and/or the confidence level of the data with the data collection device to perform a more accurate update on the data.
  • Information fusion and the elimination of defective data can improve the accuracy of the fused data on the one hand, thereby improving the accuracy of map update, and on the other hand, it can remove redundant interference data and reduce the complexity of processing.
  • there may be a variety of different implementation algorithms for how to perform fusion and data culling based on the reliability of the data which is not specifically limited here.
  • the fused data can also have corresponding credibility.
  • the calculation method of the credibility may include a Bayesian estimation method, a fuzzy mathematics method, a K-means method, a random vector machine method, or other classical neural network calculation methods, etc., which are not specifically limited here.
  • the credibility of the fused data can be obtained according to the credibility of the fused data.
  • the reliability of each data can be averaged, and the obtained value can be used as the reliability of the fused data.
  • the obtained value can be used as the reliability of the fused data.
  • W V11 and W V12 may be weighted and added together, and the obtained value may be used as the reliability corresponding to the first type of data.
  • the vertical fusion in this embodiment of the present application may be performed on the side of the data collection device, or may be performed on a server in the cloud.
  • the data acquisition device can perform vertical fusion of multiple data of the same data type acquired by itself.
  • the process is performed on the cloud server, the data of the same data type reported by multiple vehicles may also be vertically fused in the embodiment of the present application.
  • the data of the same type of sensors may be fused, or the data of different types of sensors may be fused.
  • the advantages of multiple sensors can be taken into account.
  • the target-level data of cameras and millimeter-wave radars can be fused:
  • the first target point represents the target detected by the millimeter wave radar sensor
  • the second target point represents the target detected by the camera.
  • the size of the first preset threshold can be set according to the size of the target object, for example, it is set to 1/1 of the size of the target object 5-1/2.
  • the distance and speed of the target detected by the millimeter-wave radar, and the category and lateral position of the target detected by the camera can be combined as target-level data information of the target.
  • the target-level data of the camera and the target-level data of the millimeter-wave accumulators are fused, so that the target resolution and angle resolution capabilities of the camera can be exerted, and the ranging and speed measurement capabilities of the millimeter-wave radar can be exerted.
  • horizontal fusion may be performed according to the parameter information of each of the N data types.
  • the target information may be determined according to at least one of the first parameter information or the second parameter information, and the first information and the second information.
  • the first parameter information is used to indicate the reliability of the data in the data of the first data type
  • the second parameter information is used to indicate the reliability of the data in the data of the second data type.
  • the information of the map element corresponding to the data type with the highest reliability may be used as the target information.
  • the information of a map element with the largest proportion among the N pieces of information may be used as the target information.
  • a third weight is determined according to at least one item of the first parameter information or the second parameter information, and the third weight is used to indicate the degree of influence of the first information on the target information.
  • a fourth weight is determined according to at least one item of the first parameter information or the second parameter information, and the fourth weight is used to indicate the degree of influence of the second information on the target information.
  • Target information is determined according to the third weight, the fourth weight, the first information, and the second information.
  • the parameter information of a data type may include at least one of the following: the preset priority level of the data type, the information of the map element used to determine the target information that matches the information of the map element corresponding to the data type.
  • the first data type is taken as an example for introduction, and the following information b1, information b2, information b3 and information b4 are used to introduce the parameter information (first parameter information) of the first data type:
  • Information b1 the preset priority level of the first data type.
  • data types can be prioritized. For example, considering that the feature-level data may filter the original data, some key information may be filtered out, and the target-level data may filter out more information, so a possible sorting method of data type priority is: The raw data has the highest priority, the feature-level data has the next priority, and the target-level data has the lowest priority. The higher the priority of the data type, the higher the weight of the information of the map element corresponding to the data of the data type.
  • the map element is the content on the sign (for example, the sign of the above-mentioned maximum speed limit)
  • the information of the map element corresponding to the data of multiple data types is different, the original data can be selected to be used.
  • the information of the map element in is the target information.
  • Information b2 the data amount of the data of the first data type.
  • the map update apparatus will receive data belonging to the first data type from multiple data collection devices, and may further fuse multiple data belonging to the first data type to obtain fused data , and further obtain the first information of the map element from the fused data of the first data type.
  • the information b2 refers to the sample data amount of the fused first data type data.
  • the larger the amount of sample data the more accurate the data of the first data type after fusion, the more accurate the first information of the map element, and the greater the weight of the first information of the map element.
  • the data of the first data type in the information b2 are D V11 and D V12 . It can be seen that the data amount of the data of the first data type in this example is 2. Similarly, for another example, the data amount of the data of the second data type may be 3.
  • the reliability of the data of the first data type may be the reliability corresponding to the first information. It can be obtained according to the reliability W V11 and the reliability W V12 .
  • the confidence level W V11 may include the confidence level of D V11 , and/or the recognition accuracy rate of historical map elements of the vehicle V 11 .
  • the confidence level W V12 may include the confidence level of D V12 , and/or the historical map element recognition accuracy of the vehicle V 12 .
  • the reliability W V11 is the reliability of the map element i in the data D V11
  • the reliability W V12 is the reliability of the map element i in the data D V12 .
  • the data D V11 is the data including the map element i reported by the vehicle V 11 .
  • the data D V12 is the data reported by the vehicle V 12 including the map element i.
  • Information b4 the number of information matching the first information among the N pieces of information.
  • the information of the map element is the position information of the map element
  • the distance between the position indicated by the second information and the position indicated by the first information can be within the preset Within the distance threshold, it can be said that the first information matches the second information.
  • the position indicated by the second information may be the same as or different from the position indicated by the first information.
  • the information of the map element is the content of the sign
  • the first information and the second information are said to match.
  • the first information and the second information are different, it is said that the first information and the second information do not match.
  • the parameter information of the second data type may include at least one of the following: the preset priority level of the second data type, the The data volume of the data, the reliability of the data of the second data type, or the number of information matching the second information among the N pieces of information.
  • the content included in the first parameter information may be sequentially determined according to the priorities of the following parameter items: the parameter item with the highest priority is: the preset priority level of the first data type.
  • the parameter item with the second highest priority is: the number of information matching the first information in the information of the map element used to determine the target information.
  • the parameter item with the second highest priority is: the amount of data in the data of the first data type.
  • the content included in the second parameter information is sequentially determined according to the priority of the following parameter items: the parameter item with the highest priority is: the preset priority level of the second data type.
  • the parameter item with the second highest priority is: the number of information matching the second information in the information of the map element used to determine the target information.
  • the parameter item with the second highest priority is: the amount of data in the data of the second data type.
  • the N pieces of information in the above step 203 include the first information, the second information and the fifth information
  • the first information is the information obtained according to the target-level data
  • the second information is the information obtained according to the feature-level data
  • the fifth information is the information obtained according to the original data.
  • the target information of map elements can be determined according to the priority level of the preset data type. For example, the priority of the original data is set to the highest, and the priority of the feature-level data and the target-level data
  • the fifth information may be determined as target information.
  • the information can be obtained according to the N information.
  • the target information is determined by the number of the information with the same result among the pieces of information, that is, the information with the largest number of the information with the same result among the N pieces of information is used as the target information. If there are M1 information 1 with consistent results, and M1 information 2 with consistent results, and the number of other information with consistent results is less than M1, in this case, choose information 1 or information 2? There are three possible implementations, and one piece of information with the largest number of sample points among the N pieces of information can be used as the target information. In another possible implementation, the number of all sample points corresponding to information 1 may be determined, the number of all sample points corresponding to information 2 may be determined, and then information with a larger number of sample points may be used as target information.
  • the third weight of the first information may be determined according to one of the above information b1 to b4. In another possible implementation manner, the third weight of the first information may be determined according to multiple items of the foregoing information b1 to b4. For example, a weight can be assigned to each of the above information b1 to b4, and the scores are scored according to the above information b1 to b4 to obtain a score corresponding to each of the information b1 to b4, and then the The four scores are weighted and added to obtain the total score of the first information.
  • the total score of each of the N pieces of information can also be obtained, and then the weight corresponding to each of the N pieces of information is determined according to the proportional relationship between the total scores of each of the N pieces of information. For example, when the N pieces of information only include the first information and the second information, the proportional relationship between the total score of the first information and the total score of the second information may be used as the ratio between the third weight and the fourth weight.
  • the setting of the weight corresponding to the data of one data type in the embodiment of the present application may be set according to the specific situation, specifically, may be set according to the information of the map element.
  • the value of the weight corresponding to one of the N pieces of information mentioned in the foregoing content may be 0 or 1, or a value other than 0 and 1.
  • the first information includes the first position information of the map element, for example, may include the coordinate value of the map element in the earth coordinate system.
  • the second information includes second location information of the map element.
  • the third weight and the fourth weight can be set to 0 and 1, so that the second information can be selected from the first information and the second information as the target information.
  • the third weight and the fourth weight can also be set to other parameters, such as 20% and 80%, etc.
  • the coordinate values in the first information and the second information can be set. After the weighted addition is performed, the average value is obtained to obtain the target information.
  • the value of the weight corresponding to one of the N pieces of information mentioned in the foregoing content can only be 0 or 1, and cannot be a value other than 0 and 1.
  • the map element is an identification of the maximum speed limit
  • the first information includes the first identification content of the map element (the first identification content shows that the identified identification of the maximum speed limit is 80 kilometers per hour (km/h)).
  • the second information includes the second identification content of the map element (in the second identification content, the identification of the identified maximum speed limit is displayed as 60 km/h).
  • the values of the third weight and the fourth weight can only be set to 0 and 1.
  • the third weight is 0 and the fourth weight is 1, which means that the second information (60km/h) is selected as the target information. That is, only one of the first information and the second information can be selected as the target information.
  • the map update device needs to select from a plurality of specific values One as target information.
  • information of multiple map elements can be obtained according to data of multiple data types, which can also be understood as performing horizontal mutual verification on the information of multiple map elements.
  • the cloud can calibrate the feature data and target-level data according to the original data.
  • the map update apparatus can correct other data with relatively low reliability according to the detection data results with higher reliability (for example, it may be higher reliability).
  • Type of detection data results For example, when the map element is location information, for example, the first information, the second information and the third information all include the location information of the map element.
  • the information that is inconsistent with the content of the target information in the first information, the second information and the third information can be corrected according to the position information in the finally determined target information.
  • a correction coefficient can be determined, so as to correct the position information of the map element subsequently collected by the data collection device.
  • the map update device placed in the cloud may indicate the reporting strategy of the data collection device placed on the vehicle end according to the target information and the data collected by the data collection device.
  • the map update device may generate a first message according to at least one of target information or data collected by the first data collection device, and send the first message to the first data collection device, where the first message is used to instruct the first data collection device
  • the map update device may generate a second message according to at least one item of target information or data collected by the second data collection device, and send the second message to the second data collection device, where the second message is used to instruct the second data collection device.
  • the map update device can instruct the data acquisition device to report some information, for example, it can instruct the data acquisition device to report its identification information (when the data acquisition device is a vehicle, it can be the vehicle's license plate number, identification number or vehicle type information, etc. ).
  • the map updating apparatus may determine a data reporting policy of a data collection device based on the maintained historical map element recognition accuracy of the data collection device.
  • the data reporting period of the data collection equipment may be indicated based on the identification accuracy rate of historical map elements of the maintained data collection equipment. For example, when the historical map element recognition accuracy of the data acquisition device is relatively high, the data reporting period of the data acquisition device can be shortened. When the historical map element recognition accuracy of the data acquisition device is low, the data reporting period of the data acquisition device can be made longer, or the data acquisition device can no longer report data.
  • the type information of the map elements reported by the data collection equipment can be indicated. If the value is high, the data collection device can be instructed to report only the information of these types of map elements, or the reporting period of the information of these types of map elements can be shortened.
  • the recognition accuracy of historical map elements can be different according to the data collection environment (for example: day or night, sunny or rainy, whether it is snowing, suburban or urban, expressway or urban road, rugged or flat, congested, etc.)
  • the data collection equipment is instructed to the data collection equipment with the data reporting strategy related to the data collection environment in which the data collection equipment is located, so as to comprehensively utilize each data collection equipment in a specific
  • the advantage of data accuracy in the data collection environment will ultimately improve the accuracy of map information after fusion of multiple data collection devices.
  • “at least one” refers to one or more, and “multiple” refers to two or more.
  • “And/or”, which describes the association relationship of the associated objects, indicates that there can be three kinds of relationships, for example, A and/or B, which can indicate: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the associated objects are an “or” relationship.
  • “At least one item(s) below” or similar expressions thereof refer to any combination of these items, including any combination of single item(s) or plural items(s).
  • At least one item (a) of a, b, or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, c may be single or multiple .
  • ordinal numbers such as “first” and “second” mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, sequence, priority or importance of multiple objects degree.
  • first data type and the second data type are only used to distinguish different data types, but do not indicate the difference in priority or importance of the two data types.
  • each network element in the above-mentioned implementation includes corresponding hardware structures and/or software modules for executing each function.
  • the present invention can be implemented in hardware or a combination of hardware and computer software in conjunction with the units and algorithm steps of each example described in the embodiments disclosed herein. Whether a function is performed by hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.
  • FIG. 4 provides a schematic structural diagram of a map update device capable of executing the map update method shown in FIG. 2 according to an embodiment of the present application.
  • the map update device may be a server-side map update device. It can also be a chip or circuit, such as a chip or circuit that can be provided in a map updating device on the server side.
  • the map updating apparatus 1301 may further include a bus system, wherein the processor 1302, the memory 1304, and the transceiver 1303 may be connected through the bus system.
  • the above-mentioned processor 1302 may be a chip.
  • the processor 1302 may be a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on chip (SoC), or a system on chip (SoC). It can be a central processing unit (CPU), a network processor (NP), a digital signal processing circuit (DSP), or a microcontroller (microcontroller). unit, MCU), it can also be a programmable logic device (PLD) or other integrated chips.
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • SoC system on chip
  • SoC system on chip
  • SoC system on chip
  • MCU microcontroller
  • MCU programmable logic device
  • PLD programmable logic device
  • each step of the above-mentioned method can be completed by an integrated logic circuit of hardware in the processor 1302 or an instruction in the form of software.
  • the steps of the methods disclosed in conjunction with the embodiments of the present application may be directly embodied as being executed by a hardware processor, or executed by a combination of hardware and software modules in the processor 1302 .
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory 1304, and the processor 1302 reads the information in the memory 1304, and completes the steps of the above method in combination with its hardware.
  • processor 1302 in this embodiment of the present application may be an integrated circuit chip, which has a signal processing capability.
  • each step of the above method embodiments may be completed by a hardware integrated logic circuit in a processor or an instruction in the form of software.
  • the aforementioned processors may be general purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components .
  • DSPs digital signal processors
  • ASICs application specific integrated circuits
  • FPGAs field programmable gate arrays
  • the methods, steps, and logic block diagrams disclosed in the embodiments of this application can be implemented or executed.
  • a general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
  • the steps of the method disclosed in conjunction with the embodiments of the present application may be directly embodied as executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.
  • the software modules may be located in random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, registers and other storage media mature in the art.
  • the storage medium is located in the memory, and the processor reads the information in the memory, and completes the steps of the above method in combination with its hardware.
  • the memory 1304 in this embodiment of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory.
  • the non-volatile memory may be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically programmable Erase programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory may be random access memory (RAM), which acts as an external cache.
  • RAM random access memory
  • DRAM dynamic random access memory
  • SDRAM synchronous DRAM
  • SDRAM double data rate synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • SLDRAM synchronous link dynamic random access memory
  • direct rambus RAM direct rambus RAM
  • the map updating apparatus may include a processor 1302 , a transceiver 1303 and a memory 1304 .
  • the memory 1304 is used for storing instructions
  • the processor 1302 is used for executing the instructions stored in the memory 1304, so as to realize the correlation of the map updating device in the method corresponding to any one or any of the items shown in FIG. 1 to FIG. 3 above. Program.
  • the transceiver 1303 is configured to receive data of the first data type and data of the second data type from multiple data acquisition devices.
  • the processor 1302 is configured to obtain the first information of the map element from the data of the first data type; obtain the second information of the map element from the data of the second data type; determine the map element according to the first information and the second information Target information on the map, wherein the target information includes at least one of location information, content information or attribute information of map elements.
  • the first data type and the second data type are: raw data, feature-level data or target-level data; the original data is the data collected by the sensor; the feature-level data is the original data collected from the sensor.
  • the target-level data is the data extracted from the original data or the feature-level data that can characterize the properties of the detected object.
  • the accuracy of the target information can be improved.
  • feature-level data may filter out some key information due to the filtering of the original data. If the target information of the map element is determined in combination with the original data and the feature-level data, the accuracy of the target information of the map element can be further improved.
  • target-level data may filter out some key information compared to original data and feature-level data due to more information filtering on original data. Therefore, target-level data and feature-level data, or Taking the target-level data and the original-level data into consideration comprehensively to determine the target information of the map element, the accuracy of the target information of the map element can be further improved.
  • the plurality of data acquisition devices include a first data acquisition device and a second data acquisition device.
  • the processor 1302 is specifically configured to: obtain the third information of the map element from the first data obtained by the first data collection device; the first data is data of the first data type; the second data obtained from the second data collection device The fourth information of the map element is obtained in ; the second data is data of the first data type; and the first information of the map element is obtained according to the third information and the fourth information.
  • the processor 1302 is specifically configured to: determine the first data according to at least one of the reliability of the first data or the reliability of the second data, and the third information and the fourth information a message.
  • the processor 1302 is specifically configured to: determine a first weight according to at least one of the reliability of the first data or the reliability of the second data, and the first weight is used to represent The degree of influence of the third information on the first information; the second weight is determined according to at least one of the reliability of the first data or the reliability of the second data, and the second weight is used to represent the influence of the fourth information on the first information.
  • the degree of influence of the information; the first information is determined according to the first weight, the second weight, the third information and the fourth information.
  • the credibility of the first data is related to at least one of the following: the historical map element recognition accuracy of the first data collection device; or, the confidence of the first data.
  • the accuracy of the credibility can be further improved.
  • the reliability of the second data is related to at least one of the following contents: the recognition accuracy rate of historical map elements of the second data collection device; or, the confidence of the second data.
  • the reliability of the first data can be further improved.
  • the accuracy rate of the historical map elements of the second data acquisition device it is possible to take into account the hardware accuracy of the second data acquisition device itself, that is, it is possible to infer the accuracy of the second data based on historical performance. credibility, so the accuracy of the credibility can be further improved.
  • the confidence of the data is combined to determine the credibility of the data, the accuracy of the credibility can be further improved.
  • the confidence of the first data is related to at least one of a parameter of a sensor device that collects the first data, or a relative positional relationship between the sensor device that collects the first data and a map element. In this way, the confidence level of the first data can more accurately reflect the reliability of the first data.
  • the confidence of the second data is related to at least one of a parameter of a sensor device that collects the second data, or a relative positional relationship between the sensor device that collects the second data and a map element. In this way, the confidence level of the second data can more accurately reflect the reliability of the second data.
  • the processor 1302 is specifically configured to: determine target information according to at least one of the first parameter information or the second parameter information, and the first information and the second information; wherein the first parameter The parameter information is used to indicate the reliability of the data in the data of the first data type, and the second parameter information is used to indicate the reliability of the data in the data of the second data type.
  • the processor 1302 is specifically configured to: determine a third weight according to at least one item of the first parameter information or the second parameter information, where the third weight is used to indicate that the first information is to the target information The degree of influence of The first information and the second information determine target information.
  • the processor 1302 is specifically configured to: determine, according to the first parameter information and the second parameter information, information with a higher degree of credibility among the first information and the second information as the target information.
  • the processor 1302 is further configured to: send target information to the first data collection device through the transceiver 1303, where the target information is used to enable the first data collection device to determine the first data in combination with the third information Accuracy rate of historical map element recognition of the acquisition device.
  • the processor 1302 is further configured to: send target information to the second data collection device through the transceiver 1303, where the target information is used to enable the second data collection device to determine the second data in combination with the fourth information Accuracy rate of historical map element recognition of the acquisition device.
  • the processor 1302 is further configured to: determine the historical map element recognition accuracy rate of the first data collection device according to the target information and the third information; send the data to the first data collection device through the transceiver 1303 The recognition accuracy rate of historical map elements of the first data collection device.
  • the processor 1302 is further configured to: determine the historical map element recognition accuracy rate of the second data collection device according to the target information and the fourth information; send the data to the second data collection device through the transceiver 1303 The historical map element recognition accuracy rate of the second data acquisition device.
  • the processor 1302 is further configured to: update the historical map element identification of at least one data acquisition device in the plurality of data acquisition devices according to the data received from the plurality of data acquisition devices and the target information Accuracy, the at least one data acquisition device is a device that provides data of the first data type.
  • the transceiver 1303 is further configured to: indicate a data reporting strategy to at least one data collection device, where the data reporting strategy is determined according to the identification accuracy rate of historical map elements.
  • the transceiver 1303 is specifically configured to: indicate to the at least one data acquisition device: according to the historical map element recognition accuracy rate of the at least one data acquisition device for a specific data type: reporting cycle.
  • the transceiver 1303 is specifically configured to: indicate to the at least one data acquisition device: according to the historical map element recognition accuracy rate of the at least one data acquisition device for a specific map element type: The reporting period of map element data.
  • the transceiver 1303 is specifically configured to: indicate to the at least one data collection device: in the specific data collection environment, according to the historical map element recognition accuracy rate of the at least one data collection device for a specific data collection environment The reporting period of the data.
  • FIG. 5 is a schematic structural diagram of a map updating apparatus provided by an embodiment of the present application.
  • the map updating apparatus 1401 may include a communication interface 1403 , a processor 1402 and a memory 1404 .
  • the communication interface 1403 is used for inputting and/or outputting information; the processor 1402 is used for executing a computer program or instruction, so that the map updating device 1401 realizes the map updating device 1401 in the related scheme of the above-mentioned FIGS.
  • the method on the map update device side in the related scheme of FIG. 3 the communication interface 1403 can implement the solution implemented by the transceiver 1303 in FIG. 4, the processor 1402 can implement the solution implemented by the processor 1302 in FIG. 4, and the memory 1404 can implement the memory 1304 in FIG. 4.
  • the implemented solution will not be repeated here.
  • FIG. 6 is a schematic diagram of a map updating apparatus that can implement the map updating method shown in FIG. 2 according to an embodiment of the present application.
  • the map updating apparatus 1501 may be a server side
  • the map update device can also be a chip or a circuit, such as a chip or circuit of the map update device that can be set on the server side.
  • the communication unit 1503 is configured to receive data of the first data type and data of the second data type from a plurality of data collection devices.
  • the processing unit 1502 is configured to obtain the first information of the map element from the data of the first data type, obtain the second information of the map element from the data of the second data type, and determine the map element according to the first information and the second information Target information on the map, wherein the target information includes at least one item of location information or content of road signs.
  • the first data type and the second data type are: raw data, feature-level data or target-level data;
  • the original data is the data collected by the sensor;
  • the feature-level data is from The data extracted from the raw data collected by the sensor that can characterize the characteristics of the detected object;
  • the target-level data is the data extracted from the raw data or feature-level data that can represent the properties of the detected object.
  • the accuracy of the target information can be improved.
  • feature-level data may filter out some key information due to the filtering of the original data. If the target information of the map element is determined in combination with the original data and the feature-level data, the accuracy of the target information of the map element can be further improved.
  • target-level data may filter out some key information compared to original data and feature-level data due to more information filtering on original data. Therefore, target-level data and feature-level data, or Taking the target-level data and the original-level data into consideration comprehensively to determine the target information of the map element, the accuracy of the target information of the map element can be further improved.
  • the communication unit 1503 is configured to receive the first message.
  • the processing unit 1502 is configured to parse the first message, obtain first data, and update the map according to the first data.
  • the first data is obtained according to data collected by at least one sensor of the vehicle, and the first message includes the first data.
  • the first message includes at least one of first indication information, second indication information and third indication information.
  • each unit in the above-mentioned map updating apparatus 1501 may refer to the implementation of the corresponding method embodiments, which will not be repeated here.
  • the above division of the units of the map updating apparatus is only a division of logical functions, and may be fully or partially integrated into a physical entity in actual implementation, or may be physically separated.
  • the communication unit 1503 may be implemented by the transceiver 1303 shown in FIG. 4 above, and the processing unit 1502 may be implemented by the processor 1302 shown in FIG. 4 above.
  • the present application also provides a computer program product, the computer program product includes: computer program code or instructions, when the computer program code or instructions are run on a computer, the computer is made to execute FIG. 1 To the method of any one of the embodiments shown in FIG. 3 .
  • the present application further provides a computer-readable storage medium, where the computer-readable medium stores program codes, and when the program codes are executed on a computer, the computer is made to execute FIG. 1 to FIG. 3 The method of any one of the illustrated embodiments.
  • the present application further provides a chip system, where the chip system may include a processor.
  • the processor is coupled to the memory and can be used to perform the method of any one of the embodiments shown in FIGS. 1 to 3 .
  • the chip system further includes a memory. Memory, used to store computer programs (also called code, or instructions).
  • the processor is used to call and run the computer program from the memory, so that the device in which the chip system is installed executes the method of any one of the embodiments shown in FIG. 1 to FIG. 3 .
  • the present application further provides a system, which includes the aforementioned one or more vehicles and a server-side map update device, and the vehicle is provided with the aforementioned data collection device.
  • a computer program product includes one or more computer instructions.
  • the computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
  • Computer instructions may be stored in or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server, or data center over a wire (e.g.
  • coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless means to transmit to another website site, computer, server or data center.
  • a computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, a data center, or the like that includes an integration of one or more available media.
  • Useful media may be magnetic media (eg, floppy disk, hard disk, magnetic tape), optical media (eg, high-density digital video disc (DVD)), or semiconductor media (eg, solid state disc (SSD)) )Wait.
  • the map updating device in each of the above device embodiments corresponds to the map updating device in the method embodiments, and corresponding steps are performed by corresponding modules or units, for example, the communication unit (transceiver) performs the receiving or sending steps in the method embodiments, except Steps other than sending and receiving can be performed by a processing unit (processor).
  • the communication unit transmits the receiving or sending steps in the method embodiments, except Steps other than sending and receiving can be performed by a processing unit (processor).
  • processor For functions of specific units, reference may be made to corresponding method embodiments.
  • the number of processors may be one or more.
  • the disclosed system, apparatus and method may be implemented in other manners.
  • the apparatus embodiments described above are only illustrative.
  • the division of units is only a logical function division.
  • there may be other division methods for example, multiple units or components may be combined or integrated. to another system, or some features can be ignored, or not implemented.
  • the shown or discussed mutual coupling or direct coupling or communication connection may be through some interfaces, indirect coupling or communication connection of devices or units, and may be in electrical, mechanical or other forms.
  • Units described as separate components may or may not be physically separated, and components shown as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one unit, or each unit may exist physically alone, or two or more units may be integrated into one unit.

Abstract

一种地图更新方法、装置和计算机可读存储介质，用于提高更新后地图的准确度。该地图更新装置从多个数据采集设备接收第一数据类型的数据和第二数据类型的数据，从第一数据类型的数据中得到地图元素的第一信息，从第二数据类型的数据中得到所述地图元素的第二信息；根据所述地图元素的第一信息和所述第二信息，确定所述地图元素在地图上的目标信息。由于相比一种数据类型的数据，两种不同的数据类型的数据可以包括更多的信息，因此结合两种数据类型的数据可以得到更准确的地图元素的信息，进而可以提高更新后地图的准确度。

Description

地图更新方法、装置和计算机可读存储介质
相关申请的交叉引用
本申请要求在2021年01月25日提交中国专利局、申请号为202110097462.X、申请名称为“地图更新方法、装置和计算机可读存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及智能交通技术领域，尤其涉及一种地图更新方法、装置和计算机可读存储介质。
背景技术
高精度电子地图(High Definition Map，HD Map)，是一种具备高定位精度、能实时更新数据的地图。高精度电子地图主要服务于自动驾驶车辆，为自动驾驶车辆提供路段内车道级别规划和自车定位辅助。
一种解决方案中由专业地图采集车采集数据，依据专业地图采集车采集的数据进行地图更新。但是专业地图采集车成本较高，而且数量较少，采集到的数据量难以满足自动驾驶车辆对地图小时级乃至分钟级数据更新度的需求。
随着整个车辆行业智能化的不断发展，安装各类传感器的车辆越来越多，车辆端可以将传感器采集的数据通过网络传给云端服务器。除了车辆以外，还有越来越多的设备具有数据采集功能，例如路侧单元(road side unit，RSU)。云端服务器可以根据多个数据采集设备(例如多辆车)采集到的数据进行高精度地图的制作与更新，同时将更新后的高精度地图发布给车辆。未来这种高精度地图制作与更新方式将成为主流方式，而如何提高所制作或所更新的高精度地图的准确度成为亟需解决的问题。
发明内容
本申请提供一种地图更新方法、装置和存储介质，用于结合多种数据类型的数据确定地图元素的信息，从而可以提高地图的准确度。
第一方面，本申请提供一种地图更新方法，该方法包括：地图更新装置可以从多个数据采集设备接收第一数据类型的数据和第二数据类型的数据；从第一数据类型的数据中得到地图元素的第一信息；从第二数据类型的数据中得到地图元素的第二信息；根据第一信息和第二信息，确定地图元素在地图上的目标信息，其中，目标信息包括地图元素的位置信息、内容信息或属性信息中的至少一项。在一种可能地实施方式中，第一数据类型和第二数据类型为：原始数据、特征级数据或目标级数据中的两种数据类型。其中，原始数据为传感器采集到的数据。特征级数据为从传感器采集到的原始数据中提取的能够表征被探测物特征的数据。目标级数据为从原始数据或者特征级数据中提取的能够表征被探测物属性的数据。
可以看出，本申请实施例中由于可以综合考虑多种数据类型的数据来确定目标信息， 因此，可以提高目标信息的准确性。举个例子，比如，特征级数据由于对原始数据进行了过滤，因此可能会可能滤掉一些关键信息。若结合原始数据和特征级数据确定地图元素的目标信息，则可以进一步提高地图元素的目标信息的准确度。再举个例子，比如目标级数据由于对原始数据进行了较多的信息过滤，因此相比原始数据和特征级数据，可能会滤掉一些关键信息，因此将目标级数据和特征级数据，或者将目标级数据和原始级数据综合考虑，以确定地图元素的目标信息，则可以进一步提高地图元素的目标信息的准确度。
在一种可能地实施方式中，多个数据采集设备包括第一数据采集设备和第二数据采集设备，地图更新装置可以从第一数据类型的数据中得到地图元素的第一信息，包括：从第一数据采集设备获取的第一数据中得到地图元素的第三信息；第一数据为第一数据类型的数据。从第二数据采集设备获取的第二数据中得到地图元素的第四信息；第二数据为第一数据类型的数据。根据第三信息和第四信息，得到地图元素的第一信息。如此，可以根据多个第一数据类型的数据得到第一信息，从而可以提高第一信息的准确性。
在一种可能地实施方式中，地图更新装置可以根据第三信息和第四信息，得到地图元素的第一信息，包括：根据第一数据的可信度或第二数据的可信度中的至少一项，以及第三信息和第四信息，确定第一信息。如此，可以进一步提高第一信息的可靠性。
在一种可能地实施方式中，地图更新装置可以根据第一数据的可信度或第二数据的可信度中的至少一项，以及第三信息和第四信息，包括：根据第一数据的可信度或第二数据的可信度中的至少一项，确定第一权重，第一权重用于表示第三信息对第一信息的影响程度。根据第一数据的可信度或第二数据的可信度中的至少一项，确定第二权重，第二权重用于表示第四信息对第一信息的影响程度。根据第一权重、第二权重、第三信息和第四信息，确定第一信息。由于根据数据的可信度对地图元素的信息进行了加权融合，如此，可以进一步提高第一信息的可靠性。
在一种可能地实施方式中，第一数据的可信度与以下内容中的至少一项相关：述第一数据采集设备的历史地图元素识别准确率；或者，第一数据的置信度。如此，当结合第一数据采集设备的历史地图元素识别准确率时，可能可以将第一数据采集设备本身的硬件准确度问题都考虑在内，即可以依据历史上的表现来推测第一数据的可信度，因此可以进一步提高可信度的准确性。另一方面，当结合数据的置信度来确定数据的可信度时，可以进一步提高可信度的准确性。
在一种可能地实施方式中，第二数据的可信度与以下内容中的至少一项相关：第二数据采集设备的历史地图元素识别准确率；或者，第二数据的置信度。如此，可以进一步提高第一数据的可信度。如此，当结合第二数据采集设备的历史地图元素识别准确率时，可能可以将第二数据采集设备本身的硬件准确度问题都考虑在内，即可以依据历史上的表现来推测第二数据的可信度，因此可以进一步提高可信度的准确性。另一方面，当结合数据的置信度来确定数据的可信度时，可以进一步提高可信度的准确性。
在一种可能地实施方式中，第一数据的置信度与采集第一数据的传感器装置参数，或采集第一数据的传感器装置与地图元素的相对位置关系中的至少一项相关。如此，第一数据的置信度可以更加准确的反映出第一数据的可靠性。
在一种可能地实施方式中，第二数据的置信度与采集第二数据的传感器装置参数，或采集第二数据的传感器装置与地图元素的相对位置关系中的至少一项相关。如此，第二数据的置信度可以更加准确的反映出第二数据的可靠性。
在一种可能地实施方式中，第一数据采集设备的历史地图元素识别准确率，包括以下内容中的至少一项：在预设时间段内，第一数据采集设备上报的数据中：地图元素信息识别正确的数据的占比；在预设时间段内，第一数据采集设备上报的第一数据类型的数据中：地图元素信息识别正确的数据的占比；或者，在预设时间段内，第一数据采集设备上报的包括有与地图元素相同类型的地图元素的数据中：地图元素信息识别正确的数据的占比。可以看出，可以在不同的粒度上维护数据采集设备的历史地图元素识别准确率，从而可以更加精准的评估数据采集设备的能力。
在一种可能地实施方式中，第二数据采集设备的历史地图元素识别准确率用于指示以下内容中的至少一项：在预设时间段内，第二数据采集设备上报的数据中：地图元素信息识别正确的数据的占比；在预设时间段内，第二数据采集设备上报的第一数据类型的数据中：地图元素信息识别正确的数据的占比；或者，在预设时间段内，第二数据采集设备上报的包括有与地图元素相同类型的地图元素的数据中：地图元素信息识别正确的数据的占比。可以看出，可以在不同的粒度上维护数据采集设备的历史地图元素识别准确率，从而可以更加精准的评估数据采集设备的能力。
在一种可能地实施方式中，从第二数据类型的数据中得到地图元素的第二信息，包括：从第三数据采集设备获取的第三数据中得到地图元素的第六信息；第三数据为第二数据类型的数据。从第四数据采集设备获取的第四数据中得到地图元素的第七信息；第四数据为第二数据类型的数据。根据第六信息和第七信息，得到地图元素的第二信息。如此，可以根据多个第二数据类型的数据得到第二信息，从而可以提高第二信息的准确性。
在一种可能地实施方式中，根据第六信息和第七信息，得到地图元素的第二信息，包括：根据第三数据的可信度或第四数据的可信度中的至少一项，以及第六信息和第七信息，确定第二信息。如此，可以进一步提高第二信息的可靠性。
在一种可能地实施方式中，地图更新装置可以根据第三数据的可信度或第四数据的可信度中的至少一项，以及第六信息和第七信息，包括：根据第三数据的可信度或第四数据的可信度中的至少一项，确定第五权重，第五权重用于表示第六信息对第二信息的影响程度。根据第三数据的可信度或第四数据的可信度中的至少一项，确定第六权重，第六权重用于表示第七信息对第二信息的影响程度。根据第五权重、第六权重、第六信息和第七信息，确定第二信息。由于根据数据的可信度对地图元素的信息进行了加权融合，如此，可以进一步提高第二信息的可靠性。
在一种可能地实施方式中，第三数据的可信度与以下内容中的至少一项相关：第三数据采集设备的历史地图元素识别准确率；或者，第三数据的置信度。如此，当结合第三数据采集设备的历史地图元素识别准确率时，可能可以将第三数据采集设备本身的硬件准确度问题都考虑在内，即可以依据历史上的表现来推测第三数据的可信度，因此可以进一步提高可信度的准确性。另一方面，当结合数据的置信度来确定数据的可信度时，可以进一步提高可信度的准确性。
在一种可能地实施方式中，第四数据的可信度与以下内容中的至少一项相关：第四数据采集设备的历史地图元素识别准确率；或者，第四数据的置信度。如此，当结合第四数据采集设备的历史地图元素识别准确率时，可能可以将第四数据采集设备本身的硬件准确度问题都考虑在内，即可以依据历史上的表现来推测第四数据的可信度，因此可以进一步提高可信度的准确性。另一方面，当结合数据的置信度来确定数据的可信度时，可以进一 步提高可信度的准确性。
在一种可能地实施方式中，第三数据的置信度与采集第三数据的传感器装置参数，或采集第三数据的传感器装置与地图元素的相对位置关系中的至少一项相关。如此，第三数据的置信度可以更加准确的反映出第三数据的可靠性。
在一种可能地实施方式中，第四数据的置信度与采集第四数据的传感器装置参数，或采集第四数据的传感器装置与地图元素的相对位置关系中的至少一项相关。如此，第四数据的置信度可以更加准确的反映出第四数据的可靠性。
在一种可能地实施方式中，地图更新装置可以将目标信息发送给第三数据采集设备，目标信息用于使第三数据采集设备结合第六信息确定第三数据采集设备的历史地图元素识别准确率。如此，可以进一步依据数据采集设备的历史地图元素识别准确率进行纵向融合，可以进一步提高纵向融合的准确性。
在一种可能地实施方式中，地图更新装置可以将目标信息发送给第四数据采集设备，目标信息用于使第四数据采集设备结合第七信息确定第四数据采集设备的历史地图元素识别准确率。如此，可以进一步依据数据采集设备的历史地图元素识别准确率进行纵向融合，可以进一步提高纵向融合的准确性。
在一种可能地实施方式中，地图更新装置可以根据从多个数据采集设备接收的数据，以及目标信息，更新多个数据采集设备中的至少一个数据采集设备的历史地图元素识别准确率，至少一个数据采集设备可以为提供第一数据类型的数据的设备。至少一个数据采集设备也可以为提供第一数据类型的数据的设备。比如，在一种可能地实施方式中，地图更新装置可以根据目标信息和第六信息，确定第三数据采集设备的历史地图元素识别准确率；向第三数据采集设备发送第三数据采集设备的历史地图元素识别准确率。如此，可以进一步依据数据采集设备的历史地图元素识别准确率进行纵向融合，可以进一步提高纵向融合的准确性。
在一种可能地实施方式中，地图更新装置可以根据目标信息和第七信息，确定第四数据采集设备的历史地图元素识别准确率；向第四数据采集设备发送第四数据采集设备的历史地图元素识别准确率。如此，可以进一步依据数据采集设备的历史地图元素识别准确率进行纵向融合，可以进一步提高纵向融合的准确性。
在一种可能地实施方式中，针对多个数据采集设备中的至少一个数据采集设备，该至少一个数据采集设备的历史地图元素识别准确率包括以下内容中的至少一项：
在预设时间段内，至少一个数据采集设备的检测成功率；比如，检测成功率越高，则历史地图元素识别准确率越高；
在预设时间段内，至少一个数据采集设备对云端融合的有效贡献次数；比如，对云端融合有效贡献的次数越多，则历史地图元素识别准确率越高；
在预设时间段内，至少一个数据采集设备的可信度的星级；如，最高5颗星，第一数据采集设备的星级为3颗(比如，可信度的星级越高，则历史地图元素识别准确率越高)；
在预设时间段内，至少一个数据采集设备发生检测错误的次数；比如，发生检测错误的次数越少，则历史地图元素识别准确率越高；
在预设时间段内，至少一个数据采集设备的检测误差；比如，检测误差越小，则历史地图元素识别准确率越高；
在预设时间段内，至少一个数据采集设备检测结果精度的星级；比如，检测结果精度 的星级越高，则历史地图元素识别准确率越高。
通过上述方案可以看出，数据采集设备的历史地图元素识别准确率的具体表现形式可以多种多样，从而可以提高方案的灵活性。
在一种可能地实施方式中，至少一个数据采集设备的历史地图元素识别准确率为：针对特定数据类型的历史地图元素识别准确率。举个例子，第三数据采集设备的历史地图元素识别准确率的计算方法可以为：在预设时间段内，第三数据采集设备上报的特定数据类型的数据中：地图元素信息识别正确的数据的占比。本申请中，数据类型也可以写为level，这种情况下，也可以写为针对某一个level的历史地图元素识别准确率。如此，可以利用每个数据采集设备在特定数据类型下的数据精确度优势，最终提高多个数据采集设备融合后的地图信息准确度。
在一种可能地实施方式中，至少一个数据采集设备的历史地图元素识别准确率为：针对特定地图元素类型的历史地图元素识别准确率。举个例子，第三数据采集设备的历史地图元素识别准确率的计算方法可以为：在预设时间段内，第三数据采集设备上报的包括有特定地图元素类型的数据中：地图元素信息识别正确的数据的占比。如此，可以利用每个数据采集设备在特定地图元素类型下的数据精确度优势，最终提高多个数据采集设备融合后的地图信息准确度。
在一种可能地实施方式中，至少一个数据采集设备的历史地图元素识别准确率为：针对特定数据采集环境的历史地图元素识别准确率。举个例子，第三数据采集设备的历史地图元素识别准确率的计算方法可以为：在预设时间段内，第三数据采集设备上报的包括特定数据采集环境的数据中：地图元素信息识别正确的数据的占比。如此，可以利用每个数据采集设备在特定数据采集环境下的数据精确度优势，最终提高多个数据采集设备融合后的地图信息准确度。
在一种可能地实施方式中，地图更新装置可以向至少一个数据采集设备指示数据上报策略，数据上报策略是根据历史地图元素识别准确率确定的。在一种可能地实施方式中，向至少一个数据采集设备指示的数据上报策略包括以下内容中的至少一项：至少一个数据采集设备的上报周期；或者，至少一个数据采集设备上报的地图元素类型信息。
在一种可能地实施方式中，地图更新装置可以根据至少一个数据采集设备的针对特定数据类型的历史地图元素识别准确率，向至少一个数据采集设备指示：特定数据类型的数据的上报周期。如此，可以更加合理的依据数据采集设备的自身性能制定信息上报策略。
在一种可能地实施方式中，地图更新装置可以根据至少一个数据采集设备的针对特定地图元素类型的历史地图元素识别准确率，向至少一个数据采集设备指示：特定地图元素类型的地图元素的数据的上报周期。如此，可以更加合理的依据数据采集设备的自身性能制定信息上报策略。
在一种可能地实施方式中，地图更新装置可以根据至少一个数据采集设备的针对特定数据采集环境的历史地图元素识别准确率，向至少一个数据采集设备指示：特定数据采集环境下的数据的上报周期。如此，可以更加合理的依据数据采集设备的自身性能制定信息上报策略。
在一种可能地实施方式中，地图更新装置可以根据地图元素的第一信息和第二信息，确定地图元素在地图上的目标信息，包括：根据第一参数信息或第二参数信息中的至少一项，以及第一信息和第二信息，确定目标信息。其中，第一参数信息用于表示第一数据类 型的数据中数据的可信程度，第二参数信息用于表示第二数据类型的数据中数据的可信程度。如此，可以进一步提高目标信息的准确度。
在一种可能地实施方式中，地图更新装置可以根据第一参数信息或第二参数信息中的至少一项，以及第一信息和第二信息，确定目标信息，包括：根据第一参数信息或第二参数信息中的至少一项，确定第三权重，第三权重用于表示第一信息对目标信息的影响程度；根据第一参数信息或第二参数信息中的至少一项，确定第四权重，第四权重用于表示第二信息对目标信息的影响程度；根据第三权重、第四权重、第一信息和第二信息，确定目标信息。由于对第一信息和第二信息进行了加权融合，且是根据用于表征数据可信程度的参数信息，因此可以进一步提高目标信息的准确性。
在一种可能地实施方式中，地图更新装置可以根据第一参数信息和第二参数信息，将第一信息和第二信息中可信程度较大的信息确定为目标信息。由于急于可信程度最大的一项确定目标信息，因此可以提高目标信息的准确性，继而提高更新后地图的准确性。
在一种可能地实施方式中，第一参数信息包括以下内容中的至少一项：预设的第一数据类型的优先级等级；第一信息和第二信息中与第一信息匹配的信息的数量；第一数据类型的数据中的数据量；第一数据类型的数据中数据的置信度；或者，第一数据类型的数据中数据对应的数据采集设备的历史地图元素识别准确率。
在一种可能地实施方式中，第二参数信息包括以下内容中的至少一项：预设的第二数据类型的优先级等级；第一信息和第二信息中与第二信息匹配的信息的数量；第二数据类型的数据中的数据量；第二数据类型的数据中数据的置信度；或者，第二数据类型的数据中数据对应的数据采集设备的历史地图元素识别准确率。
在一种可能地实施方式中，依据如下参数项的优先级，依次确定第一参数信息中包括的内容：优先级最高的参数项为：预设的第一数据类型的优先级等级；优先级次高的参数项为：用于确定目标信息的地图元素的信息中与第一信息匹配的信息的数量；优先级次次高的参数项为：第一数据类型的数据中的数据量。如此，为各个参数项设置优先级，从而可以进一步提高横向融合的准确性。
在一种可能地实施方式中，依据如下参数项的优先级，依次确定第二参数信息中包括的内容：优先级最高的参数项为：预设的第二数据类型的优先级等级；优先级次高的参数项为：用于确定目标信息的地图元素的信息中与第二信息匹配的信息的数量；优先级次次高的参数项为：第二数据类型的数据中的数据量。如此，为各个参数项设置优先级，从而可以进一步提高横向融合的准确性。
在一种可能地实施方式中，第一数据类型的数据中数据的置信度与以下内容中的至少一项相关：第一数据类型的数据中数据对应的数据采集设备的传感器装置参数；或者，第一数据类型的数据中数据对应的数据采集设备与地图元素的相对位置关系。如此，置信度可以更加准确的反映出数据的可靠性。
在一种可能地实施方式中，第二数据类型的数据中数据的置信度与以下内容中的至少一项相关：第二数据类型的数据中数据对应的数据采集设备的传感器装置参数；或者，第二数据类型的数据中数据对应的数据采集设备与地图元素的相对位置关系。如此，置信度可以更加准确的反映出数据的可靠性。
相应于第一方面中所提供的方法，本申请还提供了一种装置。该装置可以是地图更新装置，可以为服务器侧的设备，还可以为芯片。比如，地图更新装置可以作为上述服务器 侧的地图更新装置或可用于服务器侧的地图更新装置的通信芯片。
第二方面，提供了一种地图更新装置，包括通信单元和处理单元，以执行上述第一方面中的任一种实施方式。通信单元用于执行与发送和接收相关的功能。可选地，通信单元包括接收单元和发送单元。在一种设计中，地图更新装置为通信芯片，通信单元可以为通信芯片的输入输出电路或者端口。
在另一种设计中，通信单元可以为发射器和接收器，或者通信单元为发射机和接收机。
可选的，地图更新装置还包括可用于执行上述第一方面中的任一种实施方式的各个模块。
第三方面，提供了一种地图更新装置，该地图更新装置为上述服务器侧的地图更新装置。包括处理器和存储器。可选的，还包括收发器，该存储器用于存储计算机程序或指令，该处理器用于从存储器中调用并运行该计算机程序或指令，当处理器执行存储器中的计算机程序或指令时，使得该地图更新装置执行上述第一方面中的任一种实施方式。
可选的，处理器为一个或多个，存储器为一个或多个。
可选的，存储器可以与处理器集成在一起，或者存储器与处理器分离设置。
可选的，收发器中可以包括，发射机(发射器)和接收机(接收器)。
第四方面，提供了一种地图更新装置，包括处理器。该处理器与存储器耦合，可用于执行第一方面中任一种可能实现方式中的方法。可选地，该地图更新装置还包括存储器。可选地，该地图更新装置还包括通信接口，处理器与通信接口耦合。
在另一种实现方式中，该地图更新装置为服务器侧的地图更新装置。当该地图更新装置为服务器侧的地图更新装置时，通信接口可以是收发器，或，输入/输出接口。可选地，收发器可以为收发电路。可选地，输入/输出接口可以为输入/输出电路。
在又一种实现方式中，该地图更新装置为芯片或芯片系统。当该地图更新装置为芯片或芯片系统时，通信接口可以是该芯片或芯片系统上的输入/输出接口、接口电路、输出电路、输入电路、管脚或相关电路等。处理器也可以体现为处理电路或逻辑电路。
第五方面，提供了一种系统，该系统包括上述数据采集设备和服务器侧的地图更新装置。
第六方面，提供一种车辆，包括上述数据采集设备。
第七方面，提供了一种计算机程序产品，计算机程序产品包括：计算机程序(也可以称为代码，或指令)，当计算机程序被运行时，使得地图更新装置执行上述第一方面中任一种可能实现方式中的方法。
第八方面，提供了一种计算机可读存储介质，计算机可读介质存储有计算机程序(也可以称为代码，或指令)当其在处理器上运行时，使得地图更新装置执行上述第一方面中任一种可能实现方式中的方法。
第九方面，提供了一种芯片系统，该芯片系统可以包括处理器。该处理器与存储器耦合，可用于执行第一方面中任一种可能实现方式中的方法。可选地，该芯片系统还包括存储器。存储器，用于存储计算机程序(也可以称为代码，或指令)。处理器，用于从存储器调用并运行计算机程序，使得安装有芯片系统的设备执行第一方面中任一种可能实现方式中的方法。
在具体实现过程中，上述地图更新装置可以为芯片，输入电路可以为输入管脚，输出电路可以为输出管脚，处理电路可以为晶体管、门电路、触发器和各种逻辑电路等。输入 电路所接收的输入的信号可以是由例如但不限于接收器接收并输入的，输出电路所输出的信号可以是例如但不限于输出给发射器并由发射器发射的，且输入电路和输出电路可以是同一电路，该电路在不同的时刻分别用作输入电路和输出电路。本申请实施例对处理器及各种电路的具体实现方式不做限定。
附图说明
图1为本申请实施例适用的一种场景的示意图；
图2为本申请实施例提供的一种地图更新方法的流程示意图；
图3为本申请实施例提供的一种地图更新方法的流程示意图；
图4为本申请实施例提供的一种通信装置的结构示意图；
图5为本申请实施例提供的另一种通信装置的结构示意图；
图6为本申请实施例提供的另一种通信装置的结构示意图。
具体实施方式
下面结合附图进一步介绍本申请实施例。
图1示例性示出了本申请实施例适用的一种场景的示意图，如图1所示，该场景中可以有一个或多个数据采集设备，数据采集设备可以用于通过传感器采集数据。数据采集设备可以为终端设备。在图1中是以终端设备为车辆为例进行示意，如图1所示，图1中示意性示出了三辆车辆，分别为车辆201、车辆202和车辆203。数据采集设备还可以为路侧单元206。本申请实施例的应用场景中还可以包括有服务器204以及存储设备205等。其中，服务器可以用于根据各个数据采集设备采集的数据确定出地图元素的信息，继而根据地图元素的信息更新地图。存储设备205可以用于存储地图。下面分别介绍图1中涉及到的部件以及本申请实施例中涉及到的部分术语进行介绍。
(1)终端设备。
本申请实施例中的终端设备可以是具备通信功能的车辆或非机动车、便携设备、可穿戴设备或移动电话(或称为“蜂窝”电话)等，也可以是这些设备中的部件或者芯片等。本申请中的终端设备可以是指应用于车联网的终端设备，本申请中的终端设备也可以称为车联网终端设备、车联网终端、车联网通信装置或车载终端设备等等。
车辆(如车辆201、车辆202或车辆203中的任一项)是一种典型的车联网中的终端设备，在本申请以下实施例中，以车辆为例进行描述，本申请实施例中的任意一个车辆可以是智能车或非智能车，本申请实施例对比不做限定。本领域技术人员应该理解的是，本申请中以车辆为例的实施例还可以应用于其它类型的终端设备。终端设备具体可以通过其内部的功能单元或装置执行车联网相关业务流程。例如，当终端设备为车辆时，车辆中一个或多个如下装置可用于执行本申请实施例中终端设备相关的方法流程，如车载盒子(telematics box，T-Box)、域控制器(domian controller，DC)、多域控制器(multi-domian controller，MDC)、车载单元(on board unit，OBU)或车联网芯片等。
本申请实施例中车辆可以基于车辆与外界无线通信技术(例如，vehicle to everything(V2X))与其它物体进行通信。例如，可以基于V2X实现车辆与云端服务器之间的通信。车辆与其它物体之间进行通信可以基于无线高保真(例如，wireless fidelity(Wi-Fi))、第 五代(5th generation，5G)移动通信技术等进行通信。例如，可以基于5G实现车辆与其他装置(比如路侧单元206或服务器204)之间的通信。
本申请实施例中终端设备可以用于采集周边环境信息，比如可以通过终端设备上设置的传感器采集周边环境信息。本申请实施例中车辆中可以包括数据采集设备。数据采集设备可以通过传感器采集数据，并将通过传感器采集的原始数据传输给服务器或路侧单元，以使其进行地图的更新操作。数据采集设备也可以对原始数据进行处理，得到处理后数据(比如特征级数据、目标级数据等)，并将处理后数据传输给服务器或路侧单元，以使其进行地图的更新操作。当终端设备为车辆时，本申请实施例中车辆中的数据采集设备可以为车辆内的部件、车辆本身或者手机等。该数据采集设备可以包括该车辆中定位系统的数据采集设备、智能驾驶的数据采集设备或其他任何具有计算能力的设备实施。
本申请实施例中终端设备(比如车辆)上设置有传感器，该传感器用于采集车辆附近的图像，其中，传感器可以包括摄像头、激光雷达、毫米波雷达、超声波等。另外，每辆车可以设置一种或多种传感器，每种传感器的数量可以为一个或多个。传感器可以安装在车辆的顶部(例如可以设置在车辆顶部的中间位置)、车辆前端等等位置，本申请实施例对每个车辆中传感器安装位置和数量并不做限定。
(2)路侧单元(road side unit，RSU)206。
如图1所示，该应用场景中可以包括RSU206，RSU206可用于通过直接通信(如PC5)或专用短程通信技术(dedicated short range communications，DSRC)等通信方式向终端设备发送车辆到一切(vehicle to everything，V2X)消息。V2X消息可承载动态信息或者其他需要通知终端设备的信息。其中，路侧单元与终端设备之间的通信方式也可被称为车辆与路边基础设施(vehicle to infrastructure，V2I)通信。需要说明的是图1中仅仅示意出了路侧单元206与车辆201以及服务器204之间具有通信途径，在实际应用中，路侧单元206也可以与其他车辆，比如车辆202、车辆203等具有通信途径，在图中未示出。
本申请对于路侧单元的具体部署形态不作具体限定，其可以是一个终端设备、移动或非移动的终端设备、服务器或芯片等等。路侧单元还可用于将管辖范围内发生的动态信息上报至车联网服务器，如，通过路侧信息(roadside information，RSI)消息上报动态信息。
本申请实施例所适用的系统架构中可以包括有路侧单元，也可以不包括路侧单元，本申请实施例不做限制。在一种可能的实施方式中，路侧单元可以根据服务器下发的指令对一些指定的元素进行重点感知，并将感知结果进行上报。或者，在另一种可能的实施方式中，路侧单元也可以向终端设备发送指令或者下发更新后地图。
本申请实施例中的路侧单元中也可以设置有数据采集设备。数据采集设备可以通过传感器采集数据，并将通过传感器采集的原始数据传输给服务器或路侧单元，以使其进行地图的更新操作。数据采集设备也可以对原始数据进行处理，得到处理后数据(比如特征级数据、目标级数据等)，并将处理后数据传输给服务器或路侧单元，以使其进行地图的更新操作。
(3)服务器204。
如图1所示，该应用场景中可以包括服务器204，服务器204可以是对终端设备和/或路侧单元进行管理、提供服务的车联网平台或服务器，包括为高精地图和导航地图提供服务的应用服务器或地图云服务器。在一种可能的实施方式中，服务器204可以用于根据数据采集设备上报的数据更新地图，以及高精地图的更新下发等功能。服务器的具体部署形 态本申请不做限定，比如可以是云端部署，还可以是独立的计算机设备或芯片等。当需要向终端设备发送V2X消息时，可由服务器将V2X消息发送至路侧单元，并由路侧单元向其覆盖区域内的终端设备进行广播。当然，也可由服务器直接将V2X消息发送至终端设备。
(4)存储设备205。
如图1所示，该应用场景中可以存储设备205，存储设备205可以用于存储数据，比如可以存储地图。
(5)数据类型包括：原始数据、特征级数据和目标级数据。
本申请实施例中数据采集设备(比如车辆)上设置有传感器，该传感器用于采集车辆附近的图像，其中，传感器可以包括摄像头、激光雷达、毫米波雷达、超声波等。另外，每辆车可以设置一种或多种传感器，每种传感器的数量可以为一个或多个。传感器可以安装在车辆的顶部(例如可以设置在车辆顶部的中间位置)、车辆前端等等位置，本申请实施例对每个车辆中传感器安装位置和数量并不做限定。
本申请实施例中对数据类型定义为三种：原始数据、特征级(Feature Level)数据以及目标级数据。其中，本申请实施例中传感器采集到的原始数据经过处理，可以得到特征级数据或目标级数据中的至少一种。下面对这三种数据类型分别进行介绍。
需要说明的是，本申请实施例中提到的这三种数据类型仅仅是示例，本申请实施例适用的数据类型不限于此三种。
原始数据(Raw Data)为传感器采集到的数据。例如，当传感器为激光雷达时，原始数据为激光雷达点云数据；当传感器为摄像头时，原始数据为像素级(Pixel Level)数据。原始数据可以表示为Pi(i＝0,1,2…N)，Pi为传感器探测的环境中某一点的信息，N表示传感器探测的环境点数量。如对于三维激光雷达点云而言，Pi表示环境中某点的三维坐标信息，对于摄像头而言，Pi表示环境中某点映射到二维图像中的像素信息。
特征级(Detection Level或者Feature Level)数据为从传感器采集到的原始数据中提取的能够表征被探测物特征的数据。特征，例如可以为某个被探测物形状轮廓的关键点，还可以为环境中通过三维激光点云或图像获得的局部梯度特征等。特征级数据可以表示为Fi(i＝0,1,2…N)，Fi可以为传感器探测的环境中被探测物的某个特征的信息，N表示被探测物的特征的数量。
目标级(Object Level)数据为从原始数据或者特征级数据中提取的能够表征被探测物属性的数据。目标级数据具有显著的语义特征，例如可以为车道线、红绿灯或交通标志牌等。目标级数据可以表示为Oi(i＝0,1,2…N)，Oi为环境中传感器探测的环境中某一目标的信息，N表示传感器探测的目标的数量。
本申请实施例中可以通过特征提取和目标提取实现各数据类型之间的转换，比如，对原始数据进行特征提取可以得到特征级数据，对原始数据进行目标提取可以得到目标级数据，对特征级数据进行目标提取可以得到目标级数据，本实施例不限于特征提取和目标提取的方法。
(6)地图元素。
本申请实施例中的地图元素是指地图中的一些元素，包括不限于：道路、车道线、标牌、地面标识、信号灯、可行驶区域标识线等。其中，道路可以包括护栏、路沿等；标牌包括：路标牌、指示性牌、限高牌等各种类型，地面标识包括：分流标识、出入口标识、限速标识、限时标识等。在一种可能的实施方式中，本申请实施例可以适用于高精地图， 高精地图通俗来讲就是精度更高、数据维度更多的电子地图，地图元素更多。精度更高例如体现在地图中包含的要素信息精确到厘米级别。
基于上述内容，图2示例性示出了本申请实施例提供的一种地图更新方法的流程示意图，该方法可以由地图更新装置和数据采集设备来执行。其中，地图更新装置可以位于服务器侧，比如可以为服务器侧的一个设备，或者为服务器上的一个模块，或者为服务器上的芯片。本申请实施例中提到的数据采集设备可以位于车辆端，比如可以为车辆，或者为车辆的一个模块，还可以为车辆上的芯片。数据采集设备还可以位于RSU端，比如可以为RSU，还可以为RSU上的一个模块，还可以为RSU上的芯片。如图2所示，该方法包括：
步骤201，一个或多个数据采集设备上报数据。地图更新装置从多个数据采集设备接收N种数据类型的数据，N为大于1的整数。
一种可能地实施方式中，N种数据类型为原始数据、特征级数据或目标级数据中的多种数据类型。需要说明的是，本申请实施例中提到的这三种数据类型仅仅是示例，本申请实施例适用的数据类型不限于此三种。关于这三种数据类型的介绍可以参见前述内容，在此不再赘述。
步骤202，地图更新装置从N种数据类型的数据中得到地图元素的N个信息。其中，N个信息与N种数据类型一一对应。
步骤203，地图更新装置根据N个信息，确定地图元素在地图上的目标信息。其中，目标信息包括地图元素的位置信息、内容信息或者属性信息中的至少一项。
例如，当地图元素为车道线时，目标信息可以为车道线的位置信息、车道线的颜色，或者车道线的具体形状(实线或虚线等)中的至少一项。
再例如，当地图元素为标牌时，比如路标牌、指示性牌或者限高牌等，目标信息可以为标牌的位置信息、标牌的内容、标牌的形状，或者标牌的颜色中的至少一项。
再例如，当地图元素为地面标识时，比如分流标识、出入口标识、限速标识或者限时标识等，目标信息可以为地面标识的位置信息、地面标识的具体形状，或者地面标识的颜色中的至少一项。
再例如，当地图元素为信号灯时，目标信息可以为信号灯的位置信息，或者信号灯的具体形状中的至少一项。
再例如，当地图元素为可行驶区域标识线时，目标信息可以为可行驶区域标识线的位置信息，或者可行驶区域标识线的具体内容中的至少一项。
再例如，当地图元素为障碍物(比如该障碍物为交通路锥)，目标信息可以为障碍物的位置信息，或者障碍物的形状信息中的至少一项。
当N为2时，图2的一种可能地实施方式包括：从第一数据类型的数据中得到地图元素的第一信息。从第二数据类型的数据中得到地图元素的第二信息。根据第一信息和第二信息，确定地图元素在地图上的目标信息。当N为3时，图2的一种可能地实施方式包括：从第一数据类型的数据中得到地图元素的第一信息。从第二数据类型的数据中得到地图元素的第二信息。从第三数据类型的至少一个数据中得到地图元素的第五信息。根据第一信息、第二信息和第五信息，确定地图元素在地图上的目标信息。后续内容为了更清楚的介绍本申请实施例，以第一数据类型为目标级数据，第二数据类型为特征级数据，第三数据类型为原始数据为例进行介绍。
为了更清楚的介绍图2所示的方案，图3示例性示出了本申请实施例适用的又一种可能地场景示意图。下面结合图3对本申请实施例提供的地图更新方法进行介绍。
如图3所示，以数据采集设备为车辆为例进行示意，如图3中所示的车辆V 11、车辆V 12、车辆V 21、车辆V 22、车辆V 31和车辆V 32。为了介绍清楚本申请实施例，下面内容中以地图元素为障碍物(障碍物比如可以为交通路锥)为例进行介绍，地图元素的信息可以为障碍物的位置信息或障碍物的形状中的至少一项，下述内容中以地图元素的信息为障碍物的位置信息为例进行介绍。
本申请实施例中任何一个车辆上报的数据类型可以是一种或多种，比如可以为原始数据、特征级数据或目标级数据中的一种或多种，本申请实施例中对于一个车辆可以上报的数据类型的种类不做限制。图3中仅仅是一种示例，如图3所示，车辆V 11(第一数据采集设备)和车辆V 12(第二数据采集设备)上报的数据的数据类型为目标级数据(第一数据类型)。例如，车辆V 11或车辆V 12中的至少一项上报的数据可以包括：障碍物为交通路锥，以及交通路锥的位置信息。
如图3所示，车辆V 21(第三数据采集设备)或车辆V 22(第四数据采集设备)上报的数据的数据类型为特征级数据(第二数据类型)。例如，车辆V 21或车辆V 22中的至少一项上报的数据可以包括：障碍物的形状轮廓关键点信息。
如图3所示，车辆V 31(第五数据采集设备)和车辆V 32(第六数据采集设备)上报的数据的数据类型为原始数据(第三数据类型)。例如，车辆V 31或车辆V 32中的至少一项上报的数据可以包括：障碍物的激光雷达点云数据。
本申请实施例中，云端的服务器204收到这些数据之后，可以先对各个数据类型的数据进行纵向融合。本申请实施例中提到的纵向融合是指对同一种数据类型的数据进行的融合。比如，地图更新装置对车辆V 11上报的目标级数据(第一数据)和车辆V 12上报的目标级数据(第二数据)融合，得到融合后的目标级数据对应障碍物的位置信息(地图元素的第一信息)。一种可能地实施方式中，可以从车辆V 11上报的目标级数据中得到障碍物的一个位置信息(第三信息)，从车辆V 12上报的目标级数据中得到该障碍物的另一个位置信息(第四信息)，根据该障碍物的连个位置信息进行融合，得到融合后的目标级数据对应的障碍物的位置信息(地图元素的第一信息)。
比如，地图更新装置对车辆V 21上报的特征级数据(第三数据)和车辆V 22上报的特征级数据(第四数据)融合，得到融合后的特征级数据对应障碍物的位置信息(地图元素的第二信息)。一种可能地实施方式中，可以从车辆V 21上报的特征级数据中得到障碍物的一个位置信息(第六信息)，从车辆V 22上报的特征级数据中得到该障碍物的另一个位置信息(第七信息)，根据该障碍物的两个位置信息进行融合，得到融合后的特征级数据对应的障碍物的位置信息(地图元素的第二信息)。
比如，地图更新装置对车辆V 31上报的原始数据(第五数据)和车辆V 32上报的原始数据(第六数据)融合，得到融合后的原始数据对应障碍物的位置信息(地图元素的第五信息)。一种可能地实施方式中，可以从车辆V 31上报的原始数据中得到障碍物的位置信息(第八信息)，从车辆V 32上报的原始数据中得到该障碍物的另一个位置信息(第九信息)，对障碍物的两个位置信息进行融合，得到融合后的原始数据对应的障碍物的位置信息(地图元素的第五信息)。
进一步，对得到的各个数据类型对应的地图元素的信息再进行融合，该融合可以理解为横向融合，进而得到地图元素的目标信息。地图元素的目标信息即为更新后地图上地图元素的信息。比如，将融合后的目标级数据对应的障碍物的位置信息(地图元素的第一信息)、融合后的特征级数据对应的障碍物的位置信息(地图元素的第二信息)和融合后的原始数据对应的障碍物的位置信息(地图元素的第五信息)进行融合，最终得到障碍物的位置信息即为地图元素的目标信息。
举个例子，比如融合后的目标级数据对应的障碍物的位置信息为位置信息1，融合后的特征级数据对应的障碍物的位置信息为位置信息2，融合后的原始数据对应的障碍物的位置信息为位置信息3。比如，考虑到特征级数据可能对原始数据进行了过滤，可能会过滤掉一些关键信息，而目标级数据可能过滤掉的信息更多，因此一种可能地数据类型的优先级的排序方式为：原始数据的优先级最高，特征级数据的优先级次之，目标级数据的优先级最低。基于此，进行横向融合后可以确定障碍物的位置信息(地图元素的目标信息)为：位置信息3。
进一步的，本申请实施例中服务器侧的地图更新装置还可以根据从多个数据采集设备接收的数据，以及目标信息，更新多个数据采集设备中的至少一个数据采集设备的历史地图元素识别准确率。至少一个数据采集设备可以为提供第一数据类型的数据的设备。至少一个数据采集设备也可以为提供第二数据类型的数据的设备。比如，服务器侧的地图更新装置可以基于目标信息计算或更新车端的数据采集设备的历史地图元素识别准确率，进而将数据采集设备的历史地图元素识别准备率发送给数据采集设备。又一种可能地实施方式中，服务器侧的地图更新装置还可以将目标信息发送给各个车端的数据采集设备，以使其各自维护历史地图元素识别准确率。关于历史地图元素识别准确率，后续内容将进行详细介绍，在此先不做阐述。
从上述内容可以看出，本申请实施例中可以实现横向加纵向的闭环融合，即根据各个数据采集设备上报的数据，针对同一种类型的数据进行纵向融合，继而得到各个数据类型对应的融合后的数据。进一步针对各个数据类型对应的融合后的数据再次进行横向融合，将最终结果作为地图元素的目标信息，用以更新地图。进一步，所得到的地图元素的目标信息用于反馈给各个数据采集设备，用于使各个数据采集设备维护各自的历史地图元素识别准确率。
通过上述内容可以看出，本申请实施例中由于可以综合考虑多种数据类型的数据来确定目标信息，因此，可以提高目标信息的准确性。举个例子，比如，特征级数据由于对原始数据进行了过滤，因此可能会可能滤掉一些关键信息。若结合原始数据和特征级数据确定地图元素的目标信息，则可以进一步提高地图元素的目标信息的准确度。再举个例子，比如目标级数据由于对原始数据进行了较多的信息过滤，因此相比原始数据和特征级数据，可能会滤掉一些关键信息，因此将目标级数据和特征级数据，或者将目标级数据和原始级数据综合考虑，以确定地图元素的目标信息，则可以进一步提高地图元素的目标信息的准确度。
针对纵向融合，一种可能地实施方式中，可以根据多个数据中数据对应的可信度对数据进行融合。比如可以根据第一数据的可信度或第二数据的可信度中的至少一项，以及第三信息和第四信息，确定第一信息。可信度越高的数据，该数据中的地图元素的信息对第 一信息的影响越大。
一种可能地实施方式中，可以采用可信度最高的数据对应的地图元素的信息作为第一信息。举个例子，车辆V 11上报的目标级数据(第一数据)的可信度更高，根据第一数据确定出的障碍物的位置信息为位置信息4，而根据车辆V 12上报的目标级数据(第二数据)确定出的障碍物的位置信息为位置信息5。这种情况下，可以确定将位置信息4作为障碍物的第一信息。
又一种可能地实施方式中，当数据采集装置较多时，可以针对相同地图元素得到多于两个的同一种数据类型的数据，可以将较多数量的数据采集装置所支持的地图元素的信息作为：该数据类型对应的纵向融合结果中该地图元素的信息。举个例子，存在三辆车，该三辆车上报的数据类型均为目标级数据，根据该三辆车上报的数据确定出的障碍物的位置信息分别为位置信息6、位置信息7和位置信息7。这种情况下，由于位置信息7在总量中的占比较大，因此可以确定针对目标级数据进行纵向融合的结果中：障碍物的位置信息为位置信息7。
又一种可能地实施方式中，根据第一数据的可信度或第二数据的可信度中的至少一项，确定第一权重，第一权重用于表示第三信息对第一信息的影响程度。根据第一数据的可信度或第二数据的可信度中的至少一项，确定第二权重，第二权重用于表示第四信息对第一信息的影响程度。根据第一权重、第二权重、第三信息和第四信息，确定第一信息。
本申请实施例中以目标级数据(比如图3中的第一数据和第二数据)进行融合为例进行示例性介绍。
在一种可能地实施方式中，可以通过公式(1)对第一数据和第二数据进行数据融合：
Figure PCTCN2021132759-appb-000001
在公式(1)中：
y为数据融合结果；
result 1为第一数据；
result 2为第二数据；
w1为第一数据对应的可信度，具体可以根据获取到第一数据的第一传感器装置的参数确定；其中，w1可以为一维数据，也可以为多维数据，例如w1＝(w1 1，w1 2，…w1 i…，w1 M1)，M1为第一数据中包括的目标的数量，w1 i为第一数据中目标i对应的可信度，i为小于M1的自然数；
w2为第二数据对应的可信度，具体可以根据获取到第二数据的第二传感器装置的参数确定；其中，w2可以为一维数据，也可以为多维数据，例如w2＝(w2 1，w2 2，…w2 j…，w2 M2)，M2为第二数据中包括的目标的数量，w2 j为第二数据中目标j对应的可信度，j为小于M2的自然数；
Figure PCTCN2021132759-appb-000002
可以理解为第一权重；
Figure PCTCN2021132759-appb-000003
可以理解为第二权重。
又一种可能地实施方式中，上述result 1可以理解为从第一数据中确定的地图元素的第三信息，result 2为从第一数据中确定的该地图元素的第四信息，y为对第一数据和第二数据融合后，从融合后的数据中得到的第一信息。
可以理解，一个数据的可信度可以划分得更细，以使数据中的不同的地图元素分别对应不同的可信度。不难理解，若第一数据的可信度在第一数据和第二数据的可信度总和中 的占比越大，则第一数据在融合结果中所占的比重越大。也可以理解为，哪个传感装置的可信度的值比较大，则哪个传感装置侦测得到的感知数据在融合结果中所占的比重比较大。
上述内容中，以目标级数据进行融合为例进行示例性介绍，针对原始数据和特征级数据的融合方案与之类似，比如，也可以根据第三数据的可信度或第四数据的可信度中的至少一项，以及第六信息和第七信息，确定第二信息。根据第三数据的可信度或第四数据的可信度中的至少一项，确定第五权重，第五权重用于表示第六信息对第二信息的影响程度。根据第三数据的可信度或第四数据的可信度中的至少一项，确定第六权重，第六权重用于表示第七信息对第二信息的影响程度。根据第五权重、第六权重、第六信息和第七信息，确定第二信息。第二信息的确定方式与第一信息类似，不再赘述。
基于上述内容可以看出，在纵向融合过程中可以基于数据采集设备所采集的数据对应的可信度进行纵向融合。一种可能地实施方式中，一个数据采集设备采集的数据的可信度可以包括该数据的置信度，或该数据采集设备的历史地图元素识别准确率中的至少一项。下面通过以下参数项a1和参数项a2对这些参数项进行介绍。
参数项a1：第一数据对应的置信度。
一种可能地实施方式中，第一数据的置信度与采集第一数据的传感器装置参数，或采集第一数据的传感器装置与地图元素的相对位置关系中的至少一项相关。
置信度可以根据采集到该第一数据的传感装置参数、地图元素的感知距离以及地图元素的感知角度中的一项或多项来确定。
其中，传感装置参数与传感装置本身的初始精度、安装空间角度以及安装坐标有关。
地图元素的感知距离为地图元素与传感装置在感知坐标系中的距离。
地图元素的感知角度为地图元素与传感装置在感知坐标系中构成的角度。
需要说明的是，当传感器装置包括多个传感器时，该传感器装置的置信度可以通过对该传感器装置包括的多个传感器的置信度加权或求平均等方式得到。
不难理解，若传感装置参数的精度越高，则置信度的值越大，若传感装置参数的精度越低，则置信度的值越小。若感知距离越小，则置信度的值越大，若感知距离越大，则置信度的值越小。若感知角度越小，则置信度的值越大，若感知角度越大，则置信度的值越小。
置信度(confidence)可用于度量识别结果的可信程度。其中，目前业界计算置信度的方法有多种，至少包括以下几种：
基于贝叶斯分类方法直接得到的后验概率，基于神经网络或其他方法得到的对后验概率的估计，基于算法随机性理论得到的随机性度量值，基于模糊数学得到的隶属度值，通过多次测试实验统计得到的准确率等。
需要说明的是，本申请实施例中置信度的计算方法并不限于上述几种，任何可以用于确定置信度的计算方法都可以应用到本申请实施例中，都属于本申请实施例保护范围。
参数项a2：第一数据采集设备的历史地图元素识别准确率。
本申请实施例中可以根据历史数据维护第一数据采集设备的历史地图元素识别准确率。具体来说可以包括以下参数项a2-1、参数项a2-2和参数项a2-3中的一项或多项。
参数项a2-1：在预设时间段内，第一数据采集设备上报的数据中：地图元素信息识别正确的数据的占比。
本申请实施例中，地图元素信息识别正确的数据的占比也可以理解为：地图元素信息识别准确率。
举个例子，在预设时间段内，第一数据采集设备上报了K0个地图元素的信息，其中K1个地图元素的信息满足第一预设条件。其中，满足第一预设条件则可以称该地图元素的信息属于检测正确的数据。这种情况下，可以将K1与K0的比值作为第一数据采集设备的历史地图元素识别准确率。K0为正整数，K1为不大于K0的整数。
一种可能地实施方式中，一个地图元素的信息满足第一预设条件可以包括以下内容：
当该地图元素的信息为位置信息，则：若该数据中包括的地图元素的位置信息所指示的位置，与最终确定的地图元素的位置信息所指示的位置之间的距离小于预设的距离阈值，则可以称该数据满足第一预设条件；
当该地图元素的信息为障碍物的位置信息，则：若该数据中包括的地图元素的信息，与最终确定的地图元素的信息相同，则可以称该数据满足第一预设条件。
一种可能地实施方式中，第一数据采集设备的历史地图元素识别准确率还可以用于指示以下内容中的一项或多项：
在预设时间段内，第一数据采集设备的检测成功率(比如，检测成功率越高，则历史地图元素识别准确率越高)；
在预设时间段内，第一数据采集设备对云端融合有效贡献的次数(比如，对云端融合有效贡献的次数越多，则历史地图元素识别准确率越高)；
在预设时间段内，第一数据采集设备的可信度的星级，如，最高5颗星，第一数据采集设备的星级为3颗(比如，可信度的星级越高，则历史地图元素识别准确率越高)；
在预设时间段内，第一数据采集设备发生检测错误的次数(比如，发生检测错误的次数越少，则历史地图元素识别准确率越高)；
在预设时间段内，第一数据采集设备检测误差大小(比如，检测误差越小，则历史地图元素识别准确率越高)；
在预设时间段内，第一数据采集设备检测结果精度的星级(比如，检测结果精度的星级越高，则历史地图元素识别准确率越高)。
参数项a2-2：在预设时间段内，第一数据采集设备上报的第一数据类型的数据中：地图元素信息识别正确的数据的占比。
本申请实施例中，地图元素信息识别正确的数据的占比也可以理解为：地图元素信息识别准确率。
举个例子，在预设时间段内，第一数据采集设备上报了K0个地图元素的信息，K0个地图元素的信息中存在K2个地图元素的信息，该K2个地图元素的信息是第一数据采集设备通过上报第一数据类型的数据承载的。且K2个地图元素的信息中存在K3个地图元素的信息满足第一预设条件。这种情况下，K3与K2的比值为第一数据采集设备上报的第一数据类型的数据中的历史地图元素识别准确率。可以将K3与K2的比值作为第一数据采集设备的历史地图元素识别准确率。K2为不大于K0的整数，K3为不大于K2的整数。如此，可以基于数据类型的粒度维护数据采集设备的地图元素的信息识别准确率。
一种可能地实施方式中，第一数据采集设备的历史地图元素识别准确率还可以用于指示以下内容中的一项或多项：
在预设时间段内，第一数据采集设备在第一数据类型的数据上的检测成功率；
在预设时间段内，第一数据采集设备在第一数据类型的数据上对云端融合有效贡献的次数；
在预设时间段内，第一数据采集设备在第一数据类型的数据上的可信度的星级，如，最高5颗星，第一数据采集设备的星级为3颗；
在预设时间段内，第一数据采集设备在第一数据类型的数据上发生检测错误的次数；
在预设时间段内，第一数据采集设备在第一数据类型的数据上检测误差大小；
在预设时间段内，第一数据采集设备在第一数据类型的数据上检测结果精度的星级。
参数项a2-3：在预设时间段内，第一数据采集设备上报的包括有与该地图元素相同类型的地图元素的数据中：地图元素信息识别正确的数据的占比。
本申请实施例中，地图元素信息识别正确的数据的占比也可以理解为：地图元素信息识别准确率。
本申请实施例中涉及到地图元素的类型信息，地图元素可以分类，每类地图元素可以由一个类型标识，本文提到的类型信息可以为类型标识。分类规则不限，比如可以将标牌分为一类，或者将地面标识分为一类等等。
举个例子，在预设时间段内，第一数据采集设备上报了K0个地图元素的信息，K0个地图元素的信息中存在K4个地图元素的信息，该K4个地图元素的信息中的每个地图元素的类型均与上述步骤227中提到的地图元素的类型为同一个类型，比如可以均为标牌的内容识别等。为了引用方便，将上述步骤227中提到的地图元素的类型称为第一类型，如此，则该K4个地图元素的信息中的每个地图元素的类型均为第一类型。进一步，该K4个地图元素的信息中存在K5个地图元素的信息，该K5个地图元素的信息均满足第一预设条件。这种情况下，K5与K4的比值为第一数据采集设备上报的包括有与该地图元素相同类型的地图元素的数据中的地图元素信息识别准确率。可以将K5与K4的比值作为第一数据采集设备的地图元素信息识别准确率。K4为不大于K0的整数，K5为不大于K4的整数。如此，可以基于地图元素的粒度维护数据采集设备的地图元素的信息识别准确率。
一种可能地实施方式中，第一数据采集设备的地图元素识别准确率还可以用于指示以下内容中的一项或多项：
在预设时间段内，第一数据采集设备在第一类型的地图元素上的检测成功率；
在预设时间段内，第一数据采集设备在第一类型的地图元素上对云端融合有效贡献的次数；
在预设时间段内，第一数据采集设备在第一类型的地图元素上的可信度的星级，如，最高5颗星，第一数据采集设备的星级为3颗；
在预设时间段内，第一数据采集设备在第一类型的地图元素上发生检测错误的次数；
在预设时间段内，第一数据采集设备在第一类型的地图元素上检测误差大小；
在预设时间段内，第一数据采集设备在第一类型的地图元素上检测结果精度的星级。
又一种可能地实施方式中，还可以将上述参数项a2-1、参数项a2-2和参数项a2-3进行结合，比如，在预设时间段内，第一数据采集设备上报了K0个地图元素的信息，K0个地图元素的信息中存在K4个地图元素的信息，该K4个地图元素的信息中的每个地图元素的类型均与上述步骤227中提到的地图元素的类型为同一个类型，比如可以均为标牌的内容识别等。且K4个地图元素的信息中存在K5个地图元素的信息，该K5个地图元素的信息均满足第一预设条件。且K5个地图元素中的K6个地图元素是第一数据采集设备通过上 报第一数据类型的数据承载的。这种情况下，可以将K6与K4的比值作为第一数据采集设备的历史地图元素识别准确率。K6为不大于K5的整数。如此，可以基于地图元素和数据类型的粒度维护数据采集设备的地图元素的信息识别准确率。
需要说明的是，上述K0个地图元素的信息中的多个地图元素的信息可以通过一次数据上报发送给地图更新装置，也可以通过多次数据上报过程发送给地图更新装置。也就是说，数据采集设备上报一次数据，该数据中包括的地图元素的数量不做限制，可以是一个，也可以是多个。
上述内容通过参数项a2介绍了历史地图元素识别准确率。在一种可能地实施方式中，在上述步骤203之后，本申请实施例中服务器还可以将目标信息发送给各个数据采集设备，以使其各自维护历史地图元素识别准确率。或者，服务器可以基于目标信息计算或更新数据采集设备的历史地图元素识别准确率，进而将其发送给数据采集设备。
一种可能地实施方式中，地图更新装置将目标信息发送给第一数据采集设备，目标信息用于使第一数据采集设备结合第三信息确定第一数据采集设备的历史地图元素识别准确率。又一种可能地实施方式中，地图更新装置将目标信息发送给第二数据采集设备，目标信息用于使第二数据采集设备结合第四信息确定第二数据采集设备的历史地图元素识别准确率。又一种可能地实施方式中，地图更新装置根据目标信息和第三信息，确定第一数据采集设备的历史地图元素识别准确率；向第一数据采集设备发送第一数据采集设备的历史地图元素识别准确率。又一种可能地实施方式中，地图更新装置根据目标信息和第四信息，确定第二数据采集设备的历史地图元素识别准确率；向第二数据采集设备发送第二数据采集设备的历史地图元素识别准确率。
类似地，第二数据的可信度与：第二数据采集设备的历史地图元素识别准确率，以及第二数据的置信度的一项或多项相关。其中，第二数据的置信度与采集第二数据的传感器装置参数，或采集第二数据的传感器装置与地图元素的相对位置关系中的至少一项相关。第三数据的可信度与以下内容中的至少一项相关：第三数据采集设备的历史地图元素识别准确率，或者，第三数据的置信度。第四数据的可信度与以下内容中的至少一项相关：第四数据采集设备的历史地图元素识别准确率，或者，第四数据的置信度。第三数据的置信度与采集第三数据的传感器装置参数，或采集第三数据的传感器装置与地图元素的相对位置关系中的至少一项相关。第四数据的置信度与采集第四数据的传感器装置参数，或采集第四数据的传感器装置与地图元素的相对位置关系中的至少一项相关。相关介绍可参见前述第一数据的可信度的介绍，在此不再赘述。
通过上述内容可以看出，本申请实施例中地图更新装置针对收到的同一个类型的数据，可以结合数据采集设备的地图元素识别准备率和/或数据的置信度，对数据进行更准确的信息融合和残次数据的剔除，从而一方面可以提高融合后的数据的准确性，进而可以提高地图更新的准确度，另一方面可以去除掉冗余的干扰数据进而可以降低处理的复杂度。应理解，如何基于数据的可信度进行融合和数据剔除可以有多种不同的实现算法，这里不做具体限定。
进一步，当对同一种数据类型的数据进行融合(也可以称为纵向融合)时，融合后的数据也可以对应有可信度。可信度的计算方法可以包括贝叶斯估计方法、模糊数学方法、K-均值方法、随机向量机方法或其他经典的神经网络计算方法等，这里也不做具体限定。
比如，融合后的数据的可信度可以根据进行融合的数据的可信度得到。比如可以对各 个数据的可信度进行求取平均值的操作，将得到的值作为融合后的数据的可信度。举个例子，比如将地图元素i在数据D V11的可信度W V11，以及地图元素i在数据D V12的可信度W V12求取平均值，将得到的值作为第一类型的数据对应的可信度。又一种可能地实施方式中，可以将W V11和W V12加权相加，将得到的值作为第一类型的数据对应的可信度。
本申请实施例中的纵向融合可以在数据采集设备侧执行，也可以在云端的服务器进行。当在数据采集设备侧执行时，该数据采集设备可以对自身获取的多个同一数据类型的数据进行纵向融合。当在云端服务器进行时，本申请实施例中还可以对多个车辆上报的同一种数据类型的数据进行纵向融合。
另一方面，本申请实施例中针对同一个类型的数据进行融合时，可以对同一种类型的传感器的数据进行融合，也可以对不同类型的传感器的数据进行融合。其中，当对不同传感器的数据进行融合时，可以兼顾多种传感器的优势，举个例子，对摄像头和毫米波雷达的目标级数据进行融合：
获取第一目标点的位置信息和第二目标点的位置信息，第一目标点代表毫米波雷达传感器探测到的目标物，第二目标点代表摄像头探测到的目标物。当确定第一目标点和第二目标点之间的距离小于第一预设阈值(第一预设阈值的大小可以根据目标物的尺寸大小进行设定，例如设定为目标物尺寸的1/5-1/2)。此时认为第一目标点和第二目标点是同一个目标。进而，可以将毫米波雷达探测到的该目标的距离和速度、摄像头探测到的该目标的类别和横向位置组合作为该目标的目标级数据信息。通过该方式对摄像头的目标级数据和毫米波累的目标级数据进行了融合，从而可以既发挥摄像头的目标分辨和角度分辨能力，又发挥毫米波雷达的测距和测速能力。
针对上述步骤203中的横向融合，一种可能地实施方式中，当N个信息中存在至少两个信息不一致时，可以根据N个数据类型中每个数据类型的参数信息进行横向融合。比如当N个信息中有第一信息和第二信息时，可以根据第一参数信息或第二参数信息中的至少一项，以及第一信息和第二信息，确定目标信息。其中，第一参数信息用于表示第一数据类型的数据中数据的可信程度，第二参数信息用于表示第二数据类型的数据中数据的可信程度。一种可能地实施方式中，可以采用可信程度最高的数据类型对应的地图元素的信息作为目标信息。又一种可能地实施方式中，可以将N个信息中占比最大的一个地图元素的信息作为目标信息。可能地实施方式又多种，不再穷举。
又一种可能地实施方式中，根据第一参数信息或第二参数信息中的至少一项，确定第三权重，第三权重用于表示第一信息对目标信息的影响程度。根据第一参数信息或第二参数信息中的至少一项，确定第四权重，第四权重用于表示第二信息对目标信息的影响程度。根据第三权重、第四权重、第一信息和第二信息，确定目标信息。
一个数据类型的参数信息可以包括以下内容中的至少一项：预设的该数据类型的优先级等级、用于确定目标信息的地图元素的信息中与该数据类型对应的地图元素的信息匹配的信息的数量、该数据类型的数据量、该数据类型的数据的置信度，或者，该数据类型的数据对应的数据采集设备的历史地图元素识别准确率。
为了介绍的更清楚，以第一数据类型为例进行介绍，以以下信息b1、信息b2、信息b3和信息b4对第一数据类型的参数信息(第一参数信息)进行介绍：
信息b1：预设的第一数据类型的优先级等级。
一种可能地实施方式中，可以对数据类型设置优先级。比如，考虑到特征级数据可能对原始数据进行了过滤，可能会过滤掉一些关键信息，而目标级数据可能过滤掉的信息更多，因此一种可能地数据类型的优先级的排序方式为：原始数据的优先级最高，特征级数据的优先级次之，目标级数据的优先级最低。数据类型的优先级越高，该数据类型的数据对应的地图元素的信息的权重可以越大。
在一种可能地实施方式中，若地图元素为标识牌上的内容(比如为上述最高限速的标识)，若多种数据类型的数据对应的地图元素的信息不同，则可以选择使用原始数据中的地图元素的信息作为目标信息。
信息b2：第一数据类型的数据的数据量。
在一种可能地实施方式中，地图更新装置会收到来自多个数据采集设备的属于第一数据类型的数据，进一步可以对多个属于第一数据类型的数据进行融合，得到融合后的数据，进一步从融合后的第一数据类型的数据中得到地图元素的第一信息。信息b2是指得到融合后的第一数据类型的数据的样本数据量。一种可能地实施方式中，样本数据量越多，则融合后的第一数据类型的数据越准确，地图元素的第一信息也越准确，地图元素的第一信息的权重可以越大。
举个例子，信息b2中第一数据类型的数据为D V11和D V12，可以看出，该示例中第一数据类型的数据的数据量为2。类似的，再比如，第二数据类型的数据的数据量可以为3。
信息b3：第一数据类型的数据的可信度。
第一数据类型的数据的可信度可以为第一信息对应的可信度。可以根据可信度W V11和可信度W V12得到。其中，可信度W V11可以包括D V11的置信度，和/或，车辆V 11的历史地图元素识别准确率。可信度W V12可以包括D V12的置信度，和/或，车辆V 12的历史地图元素识别准确率。其中，可信度W V11为地图元素i在数据D V11的可信度，可信度W V12为地图元素i在数据D V12的可信度。数据D V11为车辆V 11上报的包括有地图元素i的数据。数据D V12为车辆V 12上报的包括有地图元素i的数据。
信息b4：N个信息中与第一信息匹配的信息的数量。
当地图元素的信息为地图元素的位置信息，若N个信息中的一个信息，比如第二信息，当第二信息所指示的位置与第一信息所指示的位置可以之间的距离在预设的距离阈值内，则可以说第一信息与第二信息匹配。第二信息所指示的位置与第一信息所指示的位置可以相同也可以不同。
当地图元素的信息为标牌的内容，这种情况下，当第一信息和第二信息相同时，称第一信息和第二信息匹配。而当第一信息和第二信息不同时，则称第一信息和第二信息不匹配。
上述内容以第一数据类型为例进行了示例，类似地，第二数据类型的参数信息可以包括如下内容中的至少一项：预设的第二数据类型的优先级等级、第二数据类型的数据的数据量、第二数据类型的数据的可信度，或N个信息中与第二信息匹配的信息的数量。相关内容的介绍可以参见上述信息b1至信息b4，在此不再赘述。
又一种可能地实施方式中，可以依据如下参数项的优先级，依次确定第一参数信息中包括的内容：优先级最高的参数项为：预设的第一数据类型的优先级等级。优先级次高的参数项为：用于确定目标信息的地图元素的信息中与第一信息匹配的信息的数量。优先级次次高的参数项为：第一数据类型的数据中的数据量。又一种可能地实施方式中，依据如 下参数项的优先级，依次确定第二参数信息中包括的内容：优先级最高的参数项为：预设的第二数据类型的优先级等级。优先级次高的参数项为：用于确定目标信息的地图元素的信息中与第二信息匹配的信息的数量。优先级次次高的参数项为：第二数据类型的数据中的数据量。
举个例子，当上述步骤203中N个信息包括第一信息、第二信息和第五信息，其中，第一信息为根据目标级数据得到的信息，第二信息为根据特征级数据得到的信息，第五信息为根据原始数据得到的信息。一种可能地实施方式中，可以根据预设的数据类型的优先级等级确定地图元素的目标信息，比如将原始数据的优先级设置为最高，特征级数据和目标级数据的优先级相同，则可将第五信息确定为目标信息。又一种可能地实施方式中，若N个信息中不包括根据原始数据得到的信息，比如仅包括根据特征级数据得到的信息和根据目标级数据得到的信息，这种情况下，可以根据N个信息中结果一致的信息的数量确定目标信息，即将N个信息中结果一致的信息的数量最多的一个信息作为目标信息。若在N个信息中存在M1个结果一致的信息1，且存在M1个结果一致的信息2，而其他结果一致的信息的数量均小于M1，这种情况下，选择信息1还是信息2？一种可能地实施方三种，可以根据N个信息中样本点数量最多的一个信息作为目标信息。又一种可能地实施方式中，可以确定信息1对应的所有样本点的数量，确定信息2对应的所有样本点的数量，继而将样本点数量较多的信息作为目标信息。
又一种可能地实施方式中，可以根据上述信息b1至信息b4中的一项确定第一信息的第三权重。另一种可能地实施方式中，可以根据上述信息b1至信息b4中的多项确定第一信息的第三权重。举个例子，可以为上述信息b1至信息b4中的每一项分配一个权重，根据上述信息b1至信息b4，分别进行打分，得到信息b1至信息b4中的每个信息对应的分数，之后对该四个分数进行加权相加，得到第一信息的总分数。
类似地，也可以得到N个信息中每个信息的总分数，之后根据N个信息中每个信息的总分数之间的比例关系，确定N个信息中每个信息对应的权重。比如，当N个信息仅包括第一信息和第二信息，则可以将第一信息的总分数和第二信息的总分数之间的比例关系作为第三权重和第四权重之间的比值。
一种可能地实施方式中，本申请实施例中的一个数据类型的数据对应的权重的设置可以根据具体情况进行设置，具体来说，可以根据地图元素的信息进行设置。
举个例子，当地图元素的信息为位置信息，则前述内容提到的N个信息中的一个信息对应的权重的值可以为0或1，也可以为除0和1之外的值。比如，第一信息包括地图元素的第一位置信息，比如可以包括地图元素在地球坐标系下的坐标值。第二信息包括地图元素的第二位置信息。这种情况下，第三权重和第四权重可以设置为0和1，如此可以从第一信息和第二信息中选择第二信息作为目标信息。又一种可能地实施方式中，也可以将第三权重和第四权重设置为其他参数，比如20％和80％等，这种情况下，可以将第一信息和第二信息中的坐标值进行加权相加后，求取平均值，从而得到目标信息。
再举个例子，当地图元素的信息为标牌的内容，则前述内容提到的N个信息中的一个信息对应的权重的值仅可以为0或1，不可以为除0和1之外的值。比如，地图元素为最高限速的标识，第一信息包括地图元素的第一识别内容(第一识别内容中显示识别出的最高限速的标识为80千米每小时(km/h))。第二信息包括地图元素的第二识别内容(第二识别内容中显示识别出的最高限速的标识为60km/h)。这种情况下，第三权重和第四权重 的值仅可以设置为0和1。比如第三权重为0，第四权重为1，则表示选择第二信息(60km/h)为目标信息。即仅能从第一信息和第二信息中选择一个作为目标信息。当N个信息中包括超过两个信息时，当地图元素为最高限速的标识，且N个信息中包括该最高限速的标识的具体值时，地图更新装置需要从多个具体值中选择一个作为目标信息。
本申请实施例中可以根据多种数据类型的数据，得到多个地图元素的信息，也可以理解为对多个地图元素的信息进行横向的相互验证。举个例子，针对同一地图元素，当地图更新装置同时有原始数据、特征级数据和目标级数据时，云端可以根据原始数据去校准特征数据和目标级数据。可选地，当三种类型数据的结果存在不一致或冲突时，地图更新装置可以根据可信度更高(比如可以是置信度更高)的检测数据结果去修正可信度相对低的其他数据类型的检测数据的结果。举个例子，当地图元素为位置信息，比如，第一信息、第二信息和第三信息均包括地图元素的位置信息。可以根据最终确定出的目标信息中的位置信息去修正第一信息、第二信息和第三信息中与目标信息内容不一致的信息，进一步，可以根据目标信息去修正数据采集设备采集到的与目标信息不一致的该地图元素的信息，比如可以确定出修正系数，以便对该数据采集设备后续采集到的地图元素的位置信息进行修正。
在上述步骤203之后，一种可能地实施方式中，置于云端的地图更新装置可以根据目标信息以及数据采集设备采集的数据，指示置于车端的数据采集设备的上报策略。
比如，地图更新装置可以根据目标信息或第一数据采集设备采集的数据中的至少一项，生成第一消息，向第一数据采集设备发送第一消息，第一消息用于指示第一数据采集设备的数据上报周期，或者第一数据采集设备上报的地图元素类型信息中的至少一项。再比如，地图更新装置可以根据目标信息或第二数据采集设备采集的数据的至少一项，生成第二消息，向第二数据采集设备发送第二消息，第二消息用于指示第二数据采集设备的数据上报周期，或者第二数据采集设备上报的地图元素类型信息中的至少一项。
在实际应用中，地图更新装置可以指示数据采集设备上报一些信息，比如可以指示数据采集设备上报其标识信息(当数据采集设备为车辆时，可以为车辆的车牌号、标识号或车辆类型信息等)。一种可能地实施方式中，地图更新装置可以基于维护的某个数据采集设备的历史地图元素识别准确率，确定该数据采集设备的数据上报策略。
比如，可以基于维护的数据采集设备的历史地图元素识别准确率，指示数据采集设备的数据上报周期。比如当该数据采集设备的历史地图元素识别准确率较高，则可以使该数据采集设备的数据上报周期较短。当该数据采集设备的历史地图元素识别准确率较低，则可以使该数据采集设备的数据上报周期较长，或者令该数据采集设备不再上报数据。
再比如，可以基于维护的数据采集设备的历史地图元素识别准确率，指示数据采集设备上报的地图元素的类型信息，比如该数据采集设备针对某一个或几个类别的地图元素的识别准确率较高，则可以指示数据采集设备仅上报这几种类型的地图元素的信息，或者将这几种类型的地图元素的信息的上报周期缩短。
再比如，历史地图元素识别准确率可以根据数据采集环境(例如：白天还是晚上、晴天还是雨天、是否下雪、郊区还是城市、高速道路还是城市道路、道路崎岖还是平坦、是否拥堵等)等不同的统计，并根据细分数据采集环境分类下的历史地图元素识别准确率对数据采集设备指示与数据采集设备所处的数据采集环境相关的数据上报策略，以综合利用 每个数据采集设备在特定数据采集环境下的数据精确度优势，最终提高多个数据采集设备融合后的地图信息准确度。
本申请实施例中的“至少一个”是指一个或者多个，“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B的情况，其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如，a,b,或c中的至少一项(个)，可以表示：a,b,c,a-b,a-c,b-c,或a-b-c，其中a,b,c可以是单个，也可以是多个。
以及，除非有特别说明，本申请实施例提及“第一”、“第二”等序数词是用于对多个对象进行区分，不用于限定多个对象的顺序、时序、优先级或者重要程度。例如，第一数据类型和第二数据类型，只是为了区分不同的数据类型，而并不是表示这两个数据类型的优先级或者重要程度等的不同。
需要说明的是，上述各个消息的名称仅仅是作为示例，随着通信技术的演变，上述任意消息均可能改变其名称，但不管其名称如何发生变化，只要其含义与本申请上述消息的含义相同，则均落入本申请的保护范围之内。
上述主要从各个网元之间交互的角度对本申请提供的方案进行了介绍。可以理解的是，上述实现各网元为了实现上述功能，其包含了执行各个功能相应的硬件结构和/或软件模块。本领域技术人员应该很容易意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，本发明能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
根据前述方法，图4为本申请实施例提供可执行如图2所示地图更新方法的地图更新装置的结构示意图，如图4所示，该地图更新装置可以为服务器侧的地图更新装置。也可以为芯片或电路，比如可设置于服务器侧的地图更新装置内的芯片或电路。
进一步的，该地图更新装置1301还可以进一步包括总线系统，其中，处理器1302、存储器1304、收发器1303可以通过总线系统相连。
应理解，上述处理器1302可以是一个芯片。例如，该处理器1302可以是现场可编程门阵列(field programmable gate array，FPGA)，可以是专用集成芯片(application specific integrated circuit，ASIC)，还可以是系统芯片(system on chip，SoC)，还可以是中央处理器(central processor unit，CPU)，还可以是网络处理器(network processor，NP)，还可以是数字信号处理电路(digital signal processor，DSP)，还可以是微控制器(micro controller unit，MCU)，还可以是可编程控制器(programmable logic device，PLD)或其他集成芯片。
在实现过程中，上述方法的各步骤可以通过处理器1302中的硬件的集成逻辑电路或者软件形式的指令完成。结合本申请实施例所公开的方法的步骤可以直接体现为硬件处理器执行完成，或者用处理器1302中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器1304，处理器1302读取存储器1304 中的信息，结合其硬件完成上述方法的步骤。
应注意，本申请实施例中的处理器1302可以是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法实施例的各步骤可以通过处理器中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现场可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本申请实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器，处理器读取存储器中的信息，结合其硬件完成上述方法的步骤。
可以理解，本申请实施例中的存储器1304可以是易失性存储器或非易失性存储器，或可包括易失性和非易失性存储器两者。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。应注意，本文描述的系统和方法的存储器旨在包括但不限于这些和任意其它适合类型的存储器。
该地图更新装置可以包括处理器1302、收发器1303和存储器1304。该存储器1304用于存储指令，该处理器1302用于执行该存储器1304存储的指令，以实现如上图1至图3中所示的任一项或任多项对应的方法中地图更新装置的相关方案。
一种可能的实施方式中，收发器1303，用于从多个数据采集设备接收第一数据类型的数据和第二数据类型的数据。处理器1302，用于从第一数据类型的数据中得到地图元素的第一信息；从第二数据类型的数据中得到地图元素的第二信息；根据第一信息和第二信息，确定地图元素在地图上的目标信息，其中，目标信息包括地图元素的位置信息、内容信息或属性信息中的至少一项。其中，第一数据类型和第二数据类型为：原始数据、特征级数据或目标级数据中的两种数据类型；原始数据为传感器采集到的数据；特征级数据为从传感器采集到的原始数据中提取的能够表征被探测物特征的数据；目标级数据为从原始数据或者特征级数据中提取的能够表征被探测物属性的数据。
可以看出，本申请实施例中由于可以综合考虑多种数据类型的数据来确定目标信息，因此，可以提高目标信息的准确性。举个例子，比如，特征级数据由于对原始数据进行了过滤，因此可能会可能滤掉一些关键信息。若结合原始数据和特征级数据确定地图元素的目标信息，则可以进一步提高地图元素的目标信息的准确度。再举个例子，比如目标级数据由于对原始数据进行了较多的信息过滤，因此相比原始数据和特征级数据，可能会滤掉 一些关键信息，因此将目标级数据和特征级数据，或者将目标级数据和原始级数据综合考虑，以确定地图元素的目标信息，则可以进一步提高地图元素的目标信息的准确度。
在一种可能的实施方式中，多个数据采集设备包括第一数据采集设备和第二数据采集设备。处理器1302，具体用于：从第一数据采集设备获取的第一数据中得到地图元素的第三信息；第一数据为第一数据类型的数据；从第二数据采集设备获取的第二数据中得到地图元素的第四信息；第二数据为第一数据类型的数据；根据第三信息和第四信息，得到地图元素的第一信息。
在一种可能的实施方式中，处理器1302，具体用于：根据第一数据的可信度或第二数据的可信度中的至少一项，以及第三信息和第四信息，确定第一信息。
在一种可能的实施方式中，处理器1302，具体用于：根据第一数据的可信度或第二数据的可信度中的至少一项，确定第一权重，第一权重用于表示第三信息对第一信息的影响程度；根据第一数据的可信度或第二数据的可信度中的至少一项，确定第二权重，第二权重用于表示第四信息对第一信息的影响程度；根据第一权重、第二权重、第三信息和第四信息，确定第一信息。
在一种可能地实施方式中，第一数据的可信度与以下内容中的至少一项相关：述第一数据采集设备的历史地图元素识别准确率；或者，第一数据的置信度。如此，当结合第一数据采集设备的历史地图元素识别准确率时，可能可以将第一数据采集设备本身的硬件准确度问题都考虑在内，即可以依据历史上的表现来推测第一数据的可信度，因此可以进一步提高可信度的准确性。另一方面，当结合数据的置信度来确定数据的可信度时，可以进一步提高可信度的准确性。
在一种可能地实施方式中，第二数据的可信度与以下内容中的至少一项相关：第二数据采集设备的历史地图元素识别准确率；或者，第二数据的置信度。如此，可以进一步提高第一数据的可信度。如此，当结合第二数据采集设备的历史地图元素识别准确率时，可能可以将第二数据采集设备本身的硬件准确度问题都考虑在内，即可以依据历史上的表现来推测第二数据的可信度，因此可以进一步提高可信度的准确性。另一方面，当结合数据的置信度来确定数据的可信度时，可以进一步提高可信度的准确性。
在一种可能地实施方式中，第一数据的置信度与采集第一数据的传感器装置参数，或采集第一数据的传感器装置与地图元素的相对位置关系中的至少一项相关。如此，第一数据的置信度可以更加准确的反映出第一数据的可靠性。
在一种可能地实施方式中，第二数据的置信度与采集第二数据的传感器装置参数，或采集第二数据的传感器装置与地图元素的相对位置关系中的至少一项相关。如此，第二数据的置信度可以更加准确的反映出第二数据的可靠性。
在一种可能的实施方式中，处理器1302，具体用于：根据第一参数信息或第二参数信息中的至少一项，以及第一信息和第二信息，确定目标信息；其中，第一参数信息用于表示第一数据类型的数据中数据的可信程度，第二参数信息用于表示第二数据类型的数据中数据的可信程度。
在一种可能的实施方式中，处理器1302，具体用于：根据第一参数信息或第二参数信息中的至少一项，确定第三权重，第三权重用于表示第一信息对目标信息的影响程度；根据第一参数信息或第二参数信息中的至少一项，确定第四权重，第四权重用于表示第二信息对目标信息的影响程度；根据第三权重、第四权重、第一信息和第二信息，确定目标信 息。
在一种可能的实施方式中，处理器1302，具体用于：根据第一参数信息和第二参数信息，将第一信息和第二信息中可信程度较大的信息确定为目标信息。
在一种可能的实施方式中，处理器1302，还用于：通过收发器1303将目标信息发送给第一数据采集设备，目标信息用于使第一数据采集设备结合第三信息确定第一数据采集设备的历史地图元素识别准确率。
在一种可能的实施方式中，处理器1302，还用于：通过收发器1303将目标信息发送给第二数据采集设备，目标信息用于使第二数据采集设备结合第四信息确定第二数据采集设备的历史地图元素识别准确率。
在一种可能的实施方式中，处理器1302，还用于：根据目标信息和第三信息，确定第一数据采集设备的历史地图元素识别准确率；通过收发器1303向第一数据采集设备发送第一数据采集设备的历史地图元素识别准确率。
在一种可能的实施方式中，处理器1302，还用于：根据目标信息和第四信息，确定第二数据采集设备的历史地图元素识别准确率；通过收发器1303向第二数据采集设备发送第二数据采集设备的历史地图元素识别准确率。
在一种可能的实施方式中，处理器1302，还用于：根据从多个数据采集设备接收的数据，以及目标信息，更新多个数据采集设备中的至少一个数据采集设备的历史地图元素识别准确率，至少一个数据采集设备为提供第一数据类型的数据的设备。
在一种可能的实施方式中，收发器1303，还用于：向至少一个数据采集设备指示数据上报策略，数据上报策略是根据历史地图元素识别准确率确定的。
在一种可能的实施方式中，收发器1303，具体用于：根据至少一个数据采集设备的针对特定数据类型的历史地图元素识别准确率，向至少一个数据采集设备指示：特定数据类型的数据的上报周期。
在一种可能的实施方式中，收发器1303，具体用于：根据至少一个数据采集设备的针对特定地图元素类型的历史地图元素识别准确率，向至少一个数据采集设备指示：特定地图元素类型的地图元素的数据的上报周期。
在一种可能的实施方式中，收发器1303，具体用于：根据至少一个数据采集设备的针对特定数据采集环境的历史地图元素识别准确率，向至少一个数据采集设备指示：特定数据采集环境下的数据的上报周期。
相关其他描述可以参见前述方法实施例的内容，在此不再赘述。该地图更新装置所涉及的与本申请实施例提供的技术方案相关的概念，解释和详细说明及其他步骤请参见前述方法或其他实施例中关于这些内容的描述，此处不做赘述。
根据前述方法，图5为本申请实施例提供的地图更新装置的结构示意图，如图5所示，地图更新装置1401可以包括通信接口1403、处理器1402和存储器1404。通信接口1403，用于输入和/或输出信息；处理器1402，用于执行计算机程序或指令，使得地图更新装置1401实现上述图1至图3的相关方案中地图更新装置1401实现上述图1至图3的相关方案中地图更新装置侧的方法。本申请实施例中，通信接口1403可以实现上述图4的收发器1303所实现的方案，处理器1402可以实现上述图4的处理器1302所实现的方案，存储器1404可以实现上述图4的存储器1304所实现的方案，在此不再赘述。
基于以上实施例以及相同构思，图6为本申请实施例提供的可实现如图2所示的地图 更新方法的地图更新装置的示意图，如图6所示，该地图更新装置1501可以为服务器侧的地图更新装置，也可以为芯片或电路，比如可设置于服务器侧的地图更新装置的芯片或电路。
通信单元1503，用于从多个数据采集设备接收第一数据类型的数据和第二数据类型的数据。处理单元1502，用于从第一数据类型的数据中得到地图元素的第一信息，从第二数据类型的数据中得到地图元素的第二信息，根据第一信息和第二信息，确定地图元素在地图上的目标信息，其中，目标信息包括位置信息或道路标识的内容中的至少一项。
一种可能地实施方式中，第一数据类型和第二数据类型为：原始数据、特征级数据或目标级数据中的两种数据类型；原始数据为传感器采集到的数据；特征级数据为从传感器采集到的原始数据中提取的能够表征被探测物特征的数据；目标级数据为从原始数据或者特征级数据中提取的能够表征被探测物属性的数据。
可以看出，本申请实施例中由于可以综合考虑多种数据类型的数据来确定目标信息，因此，可以提高目标信息的准确性。举个例子，比如，特征级数据由于对原始数据进行了过滤，因此可能会可能滤掉一些关键信息。若结合原始数据和特征级数据确定地图元素的目标信息，则可以进一步提高地图元素的目标信息的准确度。再举个例子，比如目标级数据由于对原始数据进行了较多的信息过滤，因此相比原始数据和特征级数据，可能会滤掉一些关键信息，因此将目标级数据和特征级数据，或者将目标级数据和原始级数据综合考虑，以确定地图元素的目标信息，则可以进一步提高地图元素的目标信息的准确度。
该地图更新装置1501对应上述方法中的服务器侧的地图更新装置的情况下，通信单元1503，用于接收第一消息。处理单元1502，用于对第一消息进行解析，得到第一数据，根据第一数据更新地图。第一数据是根据车辆的至少一个传感器采集到的数据得到的，第一消息包括第一数据。第一消息包括第一指示信息、第二指示信息和第三指示信息中的至少一项。
该地图更新装置所涉及的与本申请实施例提供的技术方案相关的概念，解释和详细说明及其他步骤请参见前述方法或其他实施例中关于这些内容的描述，此处不做赘述。
可以理解的是，上述地图更新装置1501中各个单元的功能可以参考相应方法实施例的实现，此处不再赘述。
应理解，以上地图更新装置的单元的划分仅仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。本申请实施例中，通信单元1503可以由上述图4的收发器1303实现，处理单元1502可以由上述图4的处理器1302实现。
根据本申请实施例提供的方法，本申请还提供一种计算机程序产品，该计算机程序产品包括：计算机程序代码或指令，当该计算机程序代码或指令在计算机上运行时，使得该计算机执行图1至图3所示实施例中任意一个实施例的方法。
根据本申请实施例提供的方法，本申请还提供一种计算机可读存储介质，该计算机可读介质存储有程序代码，当该程序代码在计算机上运行时，使得该计算机执行图1至图3所示实施例中任意一个实施例的方法。
根据本申请实施例提供的方法，本申请还提供一种芯片系统，该芯片系统可以包括处理器。该处理器与存储器耦合，可用于执行图1至图3所示实施例中任意一个实施例的方法。可选地，该芯片系统还包括存储器。存储器，用于存储计算机程序(也可以称为代码，或指令)。处理器，用于从存储器调用并运行计算机程序，使得安装有芯片系统的设备执 行图1至图3所示实施例中任意一个实施例的方法。
根据本申请实施例提供的方法，本申请还提供一种系统，其包括前述的一个或多个车辆以及服务器侧的地图更新装置，车辆中设置有上述数据采集设备。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机指令时，全部或部分地产生按照本申请实施例的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line，DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。可用介质可以是磁性介质(例如，软盘、硬盘、磁带)、光介质(例如，高密度数字视频光盘(digital video disc，DVD))、或者半导体介质(例如，固态硬盘(solid state disc，SSD))等。
需要指出的是，本专利申请文件的一部分包含受著作权保护的内容。除了对专利局的专利文件或记录的专利文档内容制作副本以外，著作权人保留著作权。
上述各个装置实施例中地图更新装置和方法实施例中的地图更新装置对应，由相应的模块或单元执行相应的步骤，例如通信单元(收发器)执行方法实施例中接收或发送的步骤，除发送、接收外的其它步骤可以由处理单元(处理器)执行。具体单元的功能可以参考相应的方法实施例。其中，处理器可以为一个或多个。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
以上，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应以权利要求的保护范围为准。

Claims (30)

  1. 一种地图更新方法，其特征在于，包括：
    从多个数据采集设备接收第一数据类型的数据和第二数据类型的数据；
    从所述第一数据类型的数据中得到地图元素的第一信息；
    从所述第二数据类型的数据中得到所述地图元素的第二信息；
    根据所述第一信息和所述第二信息，确定所述地图元素在地图上的目标信息，其中，所述目标信息包括所述地图元素的位置信息、内容信息或属性信息中的至少一项；
    其中，所述第一数据类型和所述第二数据类型为：原始数据、特征级数据或目标级数据中的两种数据类型；
    所述原始数据为传感器采集到的数据；
    所述特征级数据为从传感器采集到的原始数据中提取的能够表征被探测物特征的数据；
    所述目标级数据为从原始数据或者特征级数据中提取的能够表征被探测物属性的数据。
  2. 如权利要求1所述的方法，其特征在于，所述多个数据采集设备包括第一数据采集设备和第二数据采集设备，所述从所述第一数据类型的数据中得到地图元素的第一信息，包括：
    从所述第一数据采集设备获取的第一数据中得到所述地图元素的第三信息，所述第一数据为所述第一数据类型的数据；
    从所述第二数据采集设备获取的第二数据中得到所述地图元素的第四信息，所述第二数据为所述第一数据类型的数据；
    根据所述第三信息和所述第四信息，得到所述地图元素的第一信息。
  3. 如权利要求2所述的方法，其特征在于，所述根据所述第三信息和所述第四信息，得到所述地图元素的第一信息，包括：
    根据所述第一数据的可信度或所述第二数据的可信度中的至少一项，以及所述第三信息和所述第四信息，确定所述第一信息。
  4. 如权利要求3所述的方法，其特征在于，所述根据所述第一数据的可信度或所述第二数据的可信度中的至少一项，以及所述第三信息和所述第四信息，包括：
    根据所述第一数据的可信度或所述第二数据的可信度中的至少一项，确定第一权重，所述第一权重用于表示所述第三信息对所述第一信息的影响程度；
    根据所述第一数据的可信度或所述第二数据的可信度中的至少一项，确定第二权重，所述第二权重用于表示所述第四信息对所述第一信息的影响程度；
    根据所述第一权重、所述第二权重、所述第三信息和所述第四信息，确定所述第一信息。
  5. 如权利要求3或4所述的方法，其特征在于，所述第一数据的可信度与以下内容中的至少一项相关：
    所述第一数据采集设备的历史地图元素识别准确率；或者，
    所述第一数据的置信度；
    其中，所述第二数据的可信度与以下内容中的至少一项相关：
    所述第二数据采集设备的历史地图元素识别准确率；或者，
    所述第二数据的置信度。
  6. 如权利要求1-5任一项所述的方法，其特征在于，所述根据所述地图元素的第一信息和所述第二信息，确定所述地图元素在地图上的目标信息，包括：
    根据第一参数信息或第二参数信息中的至少一项，以及所述第一信息和所述第二信息，确定所述目标信息；
    其中，所述第一参数信息用于表示所述第一数据类型的数据的可信程度，所述第二参数信息用于表示所述第二数据类型的数据的可信程度。
  7. 如权利要求6所述的方法，其特征在于，所述根据第一参数信息或第二参数信息中的至少一项，以及所述第一信息和所述第二信息，确定所述目标信息，包括：
    根据所述第一参数信息或所述第二参数信息中的至少一项，确定第三权重，所述第三权重用于表示所述第一信息对所述目标信息的影响程度；
    根据所述第一参数信息或所述第二参数信息中的至少一项，确定第四权重，所述第四权重用于表示所述第二信息对所述目标信息的影响程度；
    根据所述第三权重、所述第四权重、所述第一信息和所述第二信息，确定所述目标信息。
  8. 如权利要求6所述的方法，其特征在于，所述根据第一参数信息或第二参数信息中的至少一项，以及所述第一信息和所述第二信息，确定所述目标信息，包括：
    根据所述第一参数信息和所述第二参数信息，将所述第一信息和所述第二信息中可信程度较大的信息确定为所述目标信息。
  9. 如权利要求7或8所述的方法，其特征在于，所述第一参数信息包括以下内容中的至少一项：
    预设的所述第一数据类型的优先级等级；
    所述第一数据类型的数据的数据量；
    所述第一数据类型的数据的置信度；或者，
    所述第一数据类型的数据对应的数据采集设备的历史地图元素识别准确率；
    其中，所述第二参数信息包括以下内容中的至少一项：
    预设的所述第二数据类型的优先级等级；
    所述第二数据类型的数据的数据量；
    所述第二数据类型的数据的置信度；或者，
    所述第二数据类型的数据对应的数据采集设备的历史地图元素识别准确率。
  10. 如权利要求1-9任一项所述的方法，其特征在于，所述方法还包括：
    根据从所述多个数据采集设备接收的数据，以及所述目标信息，更新所述多个数据采集设备中的至少一个数据采集设备的历史地图元素识别准确率，所述至少一个数据采集设备为提供所述第一数据类型或所述第二数据类型的数据的设备；
    向所述至少一个数据采集设备指示数据上报策略，所述数据上报策略是根据所述历史地图元素识别准确率确定的。
  11. 如权利要求10所述的方法，其特征在于，所述至少一个数据采集设备的历史地图元素识别准确率包括以下内容中的至少一项：
    在预设时间段内，所述至少一个数据采集设备的检测成功率；
    在预设时间段内，所述至少一个数据采集设备对云端融合的有效贡献次数；
    在预设时间段内，所述至少一个数据采集设备的可信度的星级；
    在预设时间段内，所述至少一个数据采集设备发生检测错误的次数；
    在预设时间段内，所述至少一个数据采集设备的检测误差；或者
    在预设时间段内，所述至少一个数据采集设备检测结果精度的星级。
  12. 如权利要求10或11所述的方法，其特征在于，所述至少一个数据采集设备的所述历史地图元素识别准确率为：
    针对特定数据类型的历史地图元素识别准确率；
    针对特定地图元素类型的历史地图元素识别准确率，或，
    针对特定数据采集环境的历史地图元素识别准确率。
  13. 如权利要求10-12任一项所述的方法，其特征在于，所述向所述至少一个数据采集设备指示数据上报策略，包括以下内容中的至少一项：
    根据所述至少一个数据采集设备的针对特定数据类型的历史地图元素识别准确率，向所述至少一个数据采集设备指示：所述特定数据类型的数据的上报周期；
    根据所述至少一个数据采集设备的针对特定地图元素类型的历史地图元素识别准确率，向所述至少一个数据采集设备指示：所述特定地图元素类型的地图元素的数据的上报周期；或，
    根据所述至少一个数据采集设备的针对特定数据采集环境的历史地图元素识别准确率，向所述至少一个数据采集设备指示：所述特定数据采集环境下的数据的上报周期。
  14. 一种地图更新装置，其特征在于，包括：
    通信单元，用于从多个数据采集设备接收第一数据类型的数据和第二数据类型的数据；
    处理单元，用于从所述第一数据类型的数据中得到地图元素的第一信息；从所述第二数据类型的数据中得到所述地图元素的第二信息；根据所述第一信息和所述第二信息，确定所述地图元素在地图上的目标信息，其中，所述目标信息包括所述地图元素的位置信息、内容信息或属性信息中的至少一项；
    其中，所述第一数据类型和所述第二数据类型为：原始数据、特征级数据或目标级数据中的两种数据类型；
    所述原始数据为传感器采集到的数据；
    所述特征级数据为从传感器采集到的原始数据中提取的能够表征被探测物特征的数据；
    所述目标级数据为从原始数据或者特征级数据中提取的能够表征被探测物属性的数据。
  15. 如权利要求14所述的地图更新装置，其特征在于，所述处理单元，具体用于：
    从所述第一数据采集设备获取的第一数据中得到所述地图元素的第三信息，所述第一数据为所述第一数据类型的数据；
    从所述第二数据采集设备获取的第二数据中得到所述地图元素的第四信息，所述第二数据为所述第一数据类型的数据；
    根据所述第三信息和所述第四信息，得到所述地图元素的第一信息。
  16. 如权利要求15所述的地图更新装置，其特征在于，所述处理单元，具体用于：
    根据所述第一数据的可信度或所述第二数据的可信度中的至少一项，以及所述第三信息和所述第四信息，确定所述第一信息。
  17. 如权利要求16所述的地图更新装置，其特征在于，所述处理单元，具体用于：
    根据所述第一数据的可信度或所述第二数据的可信度中的至少一项，确定第一权重，所述第一权重用于表示所述第三信息对所述第一信息的影响程度；
    根据所述第一数据的可信度或所述第二数据的可信度中的至少一项，确定第二权重，所述第二权重用于表示所述第四信息对所述第一信息的影响程度；
    根据所述第一权重、所述第二权重、所述第三信息和所述第四信息，确定所述第一信息。
  18. 如权利要求16或17所述的地图更新装置，其特征在于，所述第一数据的可信度与以下内容中的至少一项相关：
    所述第一数据采集设备的历史地图元素识别准确率；或者，
    所述第一数据的置信度；
    其中，所述第二数据的可信度与以下内容中的至少一项相关：
    所述第二数据采集设备的历史地图元素识别准确率；或者，
    所述第二数据的置信度。
  19. 如权利要求14-18任一项所述的地图更新装置，其特征在于，所述处理单元，具体用于：
    根据第一参数信息或第二参数信息中的至少一项，以及所述第一信息和所述第二信息，确定所述目标信息；
    其中，所述第一参数信息用于表示所述第一数据类型的数据的可信程度，所述第二参数信息用于表示所述第二数据类型的数据的可信程度。
  20. 如权利要求19所述的地图更新装置，其特征在于，所述处理单元，具体用于：
    根据所述第一参数信息或所述第二参数信息中的至少一项，确定第三权重，所述第三权重用于表示所述第一信息对所述目标信息的影响程度；
    根据所述第一参数信息或所述第二参数信息中的至少一项，确定第四权重，所述第四权重用于表示所述第二信息对所述目标信息的影响程度；
    根据所述第三权重、所述第四权重、所述第一信息和所述第二信息，确定所述目标信息。
  21. 如权利要求20所述的地图更新装置，其特征在于，所述处理单元，具体用于：
    根据所述第一参数信息和所述第二参数信息，将所述第一信息和所述第二信息中可信程度较大的信息确定为所述目标信息。
  22. 如权利要求20或21所述的地图更新装置，其特征在于，所述第一参数信息包括以下内容中的至少一项：
    预设的所述第一数据类型的优先级等级；
    所述第一信息和所述第二信息中与所述第一信息匹配的信息的数量；
    所述第一数据类型的数据的数据量；
    所述第一数据类型的数据的置信度；或者，
    所述第一数据类型的数据对应的数据采集设备的历史地图元素识别准确率；
    其中，所述第二参数信息包括以下内容中的至少一项：
    预设的所述第二数据类型的优先级等级；
    所述第一信息和所述第二信息中与所述第二信息匹配的信息的数量；
    所述第二数据类型的数据的数据量；
    所述第二数据类型的数据的置信度；或者，
    所述第二数据类型的数据对应的数据采集设备的历史地图元素识别准确率。
  23. 如权利要求14-22任一项所述的地图更新装置，其特征在于，所述处理单元，还用于：
    根据从所述多个数据采集设备接收的数据，以及所述目标信息，更新所述多个数据采集设备中的至少一个数据采集设备的历史地图元素识别准确率，所述至少一个数据采集设备为提供所述第一数据类型或所述第二数据类型的数据的设备；或者，
    所述通信单元，还用于：
    向所述至少一个数据采集设备指示数据上报策略，所述数据上报策略是根据所述历史地图元素识别准确率确定的。
  24. 如权利要求23所述的地图更新装置，其特征在于，所述至少一个数据采集设备的历史地图元素识别准确率包括以下内容中的至少一项：
    在预设时间段内，所述至少一个数据采集设备的检测成功率；
    在预设时间段内，所述至少一个数据采集设备对云端融合的有效贡献次数；
    在预设时间段内，所述至少一个数据采集设备的可信度的星级；
    在预设时间段内，所述至少一个数据采集设备发生检测错误的次数；
    在预设时间段内，所述至少一个数据采集设备的检测误差；
    在预设时间段内，所述至少一个数据采集设备检测结果精度的星级。
  25. 如权利要求23或24所述的地图更新装置，其特征在于，所述至少一个数据采集设备的所述历史地图元素识别准确率为以下内容中的至少一项：
    针对特定数据类型的历史地图元素识别准确率；
    针对特定地图元素类型的历史地图元素识别准确率，或，
    针对特定数据采集环境的历史地图元素识别准确率。
  26. 如权利要求23-25任一项所述的地图更新装置，其特征在于，所述通信单元，具体用于：
    根据所述至少一个数据采集设备的针对特定数据类型的历史地图元素识别准确率，向所述至少一个数据采集设备指示：所述特定数据类型的数据的上报周期；
    根据所述至少一个数据采集设备的针对特定地图元素类型的历史地图元素识别准确率，向所述至少一个数据采集设备指示：所述特定地图元素类型的地图元素的数据的上报周期；或，
    根据所述至少一个数据采集设备的针对特定数据采集环境的历史地图元素识别准确率，向所述至少一个数据采集设备指示：所述特定数据采集环境下的数据的上报周期。
  27. 一种地图更新装置，其特征在于，包括处理器和存储器，所述存储器用于存储计算机可执行指令，所述处理器执行所述存储器中的计算机可执行指令使所述地图更新装置执行权利要求1-13中任一项所述的方法。
  28. 一种地图更新装置，其特征在于，包括处理器和通信接口，
    所述通信接口，用于输入和/或输出信息；
    所述处理器，用于执行计算机程序，使得权利要求1-13中任一项所述的方法被执行。
  29. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机可执行程序，所述计算机可执行程序在被处理器执行时，使得所述地图更新装置执行如权利要求1-13任一项所述的方法。
  30. 一种计算机程序产品，其特征在于，当所述计算机程序产品在处理器上运行时，使得所述地图更新装置执行如权利要求1-13任一项所述的方法。
PCT/CN2021/132759 2021-01-25 2021-11-24 地图更新方法、装置和计算机可读存储介质 WO2022156352A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP21920728.9A EP4283484A1 (en) 2021-01-25 2021-11-24 Method and apparatus for updating map, and computer-readable storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110097462.X 2021-01-25
CN202110097462.XA CN114791917A (zh) 2021-01-25 2021-01-25 地图更新方法、装置和计算机可读存储介质

Publications (1)

Publication Number Publication Date
WO2022156352A1 true WO2022156352A1 (zh) 2022-07-28

Family

ID=82460683

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132759 WO2022156352A1 (zh) 2021-01-25 2021-11-24 地图更新方法、装置和计算机可读存储介质

Country Status (3)

Country Link
EP (1) EP4283484A1 (zh)
CN (1) CN114791917A (zh)
WO (1) WO2022156352A1 (zh)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104391869A (zh) * 2014-10-27 2015-03-04 百度在线网络技术（北京）有限公司 电子地图数据更新方法和装置
CN106228160A (zh) * 2016-08-03 2016-12-14 浙江宇视科技有限公司 前端设备定位方法及装置
CN108834064A (zh) * 2018-06-19 2018-11-16 品信科技有限公司 一种基于电子围栏地图的站点匹配方法及装置
CN111427985A (zh) * 2020-03-25 2020-07-17 北京小马智行科技有限公司 地图更新的方法及装置、存储介质、处理器

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104391869A (zh) * 2014-10-27 2015-03-04 百度在线网络技术（北京）有限公司 电子地图数据更新方法和装置
CN106228160A (zh) * 2016-08-03 2016-12-14 浙江宇视科技有限公司 前端设备定位方法及装置
CN108834064A (zh) * 2018-06-19 2018-11-16 品信科技有限公司 一种基于电子围栏地图的站点匹配方法及装置
CN111427985A (zh) * 2020-03-25 2020-07-17 北京小马智行科技有限公司 地图更新的方法及装置、存储介质、处理器

Also Published As

Publication number Publication date
EP4283484A1 (en) 2023-11-29
CN114791917A (zh) 2022-07-26

Similar Documents

Publication Publication Date Title
WO2022083402A1 (zh) 障碍物检测方法、装置、计算机设备和存储介质
EP4152204A1 (en) Lane line detection method, and related apparatus
US20200309538A1 (en) System for producing and/or updating a digital model of a digital map
US9983022B2 (en) Vehicle position estimation system, device, method, and camera device
EP4089659A1 (en) Map updating method, apparatus and device
JP7413543B2 (ja) データ伝送方法および装置
DE112012005624T5 (de) System zum Herstellen eines aufspannenden Waldes in einem Fahrzeugnetzwerk
US20210325901A1 (en) Methods and systems for automated driving system monitoring and management
US20230345216A1 (en) Data transmission method and apparatus for internet of vehicles, storage medium, and system
DE102019108083A1 (de) Verkehrszeichenerkennung für vernetzte Fahrzeuge
CN115470884A (zh) 用于自动驾驶系统的感知系统开发的平台
WO2021057324A1 (zh) 数据处理方法、装置、芯片系统及介质
US20210323577A1 (en) Methods and systems for managing an automated driving system of a vehicle
WO2022156352A1 (zh) 地图更新方法、装置和计算机可读存储介质
CN111133487B (zh) 方法和装置
CN115421122A (zh) 目标对象检测方法、装置、电子设备和可读存储介质
Lee et al. The real-time implementation for the parking line departure warning system
CN115148043A (zh) 一种信息获取方法、装置和计算机可读存储介质
US11815362B2 (en) Map data generation apparatus
CN116033387B (zh) 道路环境协同感知决策方法及装置
EP4325446A1 (en) Method and system for in-vehicle self-supervised training of perception functions for an automated driving system
Mekala et al. Object-aware Multi-criteria Decision-Making Approach using the Heuristic data-driven Theory for Intelligent Transportation Systems
CN115620069A (zh) 目标识别方法、装置、终端设备及存储介质
CN116412804A (zh) 交通标志牌的激光雷达视觉融合建图方法、装置及介质
CN116246456A (zh) 车路协同方法、路侧通信设备及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21920728

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2021920728

Country of ref document: EP

Effective date: 20230823