WO2022001337A1 - 一种定位地图生成方法、定位方法及装置 - Google Patents

一种定位地图生成方法、定位方法及装置 Download PDF

Info

Publication number
WO2022001337A1
WO2022001337A1 PCT/CN2021/090752 CN2021090752W WO2022001337A1 WO 2022001337 A1 WO2022001337 A1 WO 2022001337A1 CN 2021090752 W CN2021090752 W CN 2021090752W WO 2022001337 A1 WO2022001337 A1 WO 2022001337A1
Authority
WO
WIPO (PCT)
Prior art keywords
grid
map
positioning
threshold
feature value
Prior art date
Application number
PCT/CN2021/090752
Other languages
English (en)
French (fr)
Inventor
陈哲
叶爱学
高亚军
许光林
温丰
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
Publication of WO2022001337A1 publication Critical patent/WO2022001337A1/zh

Links

Images

Classifications

    • 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
    • G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
    • G01C21/30—Map- or contour-matching
    • G01C21/32—Structuring or formatting of map data
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
    • 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

Definitions

  • the embodiments of the present application relate to the field of automatic driving, and in particular, to a method for generating a positioning map, a positioning method, and an apparatus.
  • Prior maps can provide prior knowledge for autonomous vehicle positioning, which can help autonomous vehicles in planning and decision-making.
  • an autonomous vehicle can match current environmental information with a prior map, obtain the position and attitude of the autonomous vehicle in the prior map, and perform path planning based on the position and attitude.
  • the prior map needs to have a complete description of the environment and can fully reflect the information that is helpful for positioning in the environment. Therefore, a large number of positioning references need to be collected during the construction of the prior map. Information about the characteristics of objects such as buildings, trees, roadside landmarks or lanes, etc. Considering that the collection and processing of a large amount of feature information requires a lot of manpower and material resources, the construction cycle of the prior map will not be very frequent, which requires that the positioning reference object used to construct the prior map will not occur for a period of time. Changes (such as shape changes or position changes, etc.). However, with the influence of external factors (such as weather changes or season changes, etc.), the positioning reference object is not absolutely unchanged.
  • the branches of trees move from position 1 to position 2 under the blow of the wind, which has the following Situation:
  • the current prior map has poor compatibility with errors, and it is difficult to ensure the accuracy of positioning.
  • the embodiments of the present application provide a method for generating a positioning map, a positioning method and an apparatus, so as to improve the compatibility of the prior map with respect to errors and improve the robustness of the positioning.
  • an embodiment of the present application provides a method for generating a positioning map.
  • the method can be executed by a network device (such as a single server, a cloud server, or a virtual machine, etc.), or by a chip or a chip system in the network device.
  • a network device such as a single server, a cloud server, or a virtual machine, etc.
  • a chip or a chip system in the network device takes the execution subject being a network device as an example.
  • the method includes: a network device acquires a first map, the first map includes a first grid and a second grid, the feature value of the first grid is greater than or equal to a first threshold, and the feature value of the second grid is less than or equal to the second threshold, where the first threshold is greater than the second threshold, the feature value is the probability that the positioning reference object occupies the grid, and the positioning reference object is used to determine the positioning information of the terminal; according to the feature value of the first grid, the second grid is updated The feature value of the grid is obtained so that the updated feature value of the second grid is greater than the second threshold but smaller than the feature value of the first grid to obtain a second map, and a third map is generated according to the second map.
  • the eigenvalues of the second grid are updated according to the eigenvalues of the first grid, and the updated eigenvalues of the second grid are greater than the second threshold and smaller than the eigenvalues of the first grid, which means an increase in the
  • the probability that the positioning reference object occupies the second grid makes the impact of the updated second grid on positioning correspondingly increased, but the impact of the updated second grid on positioning does not exceed that of the first grid on positioning. Therefore, the third map generated based on the updated second grid can be well compatible with errors caused by dynamic features, bias addition or bias subtraction operations, etc. It can avoid the introduction of additional errors and improve the robustness of positioning. For example, when combined with particle filtering, the third map can reduce the problem of a sudden drop in particle scores that may exist around the correct positioning, thereby effectively reducing the impact of inaccurate positioning caused by a sudden drop in particle scores.
  • the distance between the first grid and the second grid may be less than or equal to the first distance. In this way, only the grids whose distance from the first grid is less than or equal to the first distance needs to be updated, which can avoid introducing additional errors.
  • the larger the distance between the first grid and the second grid the smaller the updated eigenvalue of the second grid. In this way, as the distance between the first grid and the second grid increases, the influence of the updated second grid on the positioning can be gradually reduced, so as to improve the robustness of the positioning.
  • the method may further include: the network device receives a first request message from the terminal, where the first request message is used to request to acquire the third map; the network device sends a first response message to the terminal, the first request message is used to request the acquisition of the third map;
  • the third map is included in a response message.
  • the terminal can acquire the third map and perform positioning based on the third map. Since the eigenvalues of the third grid in the third map are determined according to the eigenvalues of the first grid, and the eigenvalues of the third grid are greater than the second threshold, the third map has good adaptability and is less sensitive to errors. Good compatibility, can help the terminal to obtain accurate positioning information.
  • acquiring the first map includes: acquiring a fourth map, where the fourth map includes a first grid and a fourth grid, and a feature value of the fourth grid is less than or equal to a second threshold; Divide the fourth map to obtain the first map and the seventh map, the seventh map includes the fifth map and/or the sixth map, the fifth map only includes the first grid, and the sixth map only includes the first grid. Including a fourth grid; generating a third map according to the second map, including: generating a third map according to the second map and the seventh map. In this way, after dividing the fourth map, it is possible to obtain the fifth map including only the first grid and/or only the sixth map.
  • the second map and the seventh map can be divided into The third map is obtained by splicing, so that the integrity of the positioning information in the third map can be ensured.
  • the first map may be a two-dimensional grid map or a three-dimensional grid map.
  • the distance between the first grid and the second grid may include any one of a lateral distance, a longitudinal distance, or a radius value radiating from the first grid as a center to the surrounding.
  • the first map is a two-dimensional grid map
  • the horizontal distance may be the distance in the direction parallel to the X axis in the coordinate system
  • the vertical distance may be the distance in the direction perpendicular to the X axis in the coordinate system.
  • the first map is a three-dimensional grid map
  • the lateral distance may be the distance in the direction parallel to the XOY plane in the coordinate system
  • the vertical distance may be the distance in the direction perpendicular to the XOY plane in the coordinate system.
  • the coordinate system may be a world coordinate system, or a coordinate system with the terminal as the origin, or the like.
  • an embodiment of the present application provides a positioning method, which may be executed by a terminal (such as a vehicle, a vehicle-mounted device, or a mobile phone, etc.), or may be executed by a chip or a chip system in the terminal.
  • a terminal such as a vehicle, a vehicle-mounted device, or a mobile phone, etc.
  • a chip or a chip system in the terminal may be executed by a chip or a chip system in the terminal.
  • the method includes: the terminal acquires the environmental information of the environment where the terminal is located, and determines a third map according to the environmental information, where the third map is generated according to the second map, and the second map includes a first grid and a third grid,
  • the eigenvalue of the first grid is greater than or equal to the first threshold
  • the eigenvalue of the third grid is greater than the second threshold and smaller than the eigenvalue of the first grid
  • the eigenvalue of the third grid is based on the first grid.
  • the feature value is determined, wherein the first threshold value is greater than the second threshold value, the feature value is the probability that the positioning reference object occupies the grid, and the positioning reference object is used to determine the positioning information of the terminal; the terminal matches the environmental information with the third map to obtain Positioning information of the terminal.
  • the distance between the first grid and the third grid may be less than or equal to the first distance.
  • the method may further include: the terminal sends a first request message to the network device, where the first request message is used to request acquisition of the third map; the terminal receives a first response message from the network device, the first response The message includes the third map.
  • the distance between the first grid and the third grid may include any one of a lateral distance, a longitudinal distance, or a radius value radiating from the first grid to the surrounding.
  • an embodiment of the present application provides a positioning method, which may be executed by a terminal (such as a vehicle, a vehicle-mounted device, or a mobile phone, etc.), or may be executed by a chip or a chip system in the terminal.
  • a terminal such as a vehicle, a vehicle-mounted device, or a mobile phone, etc.
  • a chip or a chip system in the terminal may be executed by a chip or a chip system in the terminal.
  • the method includes: the terminal acquires environmental information of the environment in which it is located, and acquires a first map according to the environmental information, the first map includes a first grid and a second grid, and the feature value of the first grid is greater than or equal to the first grid threshold, the feature value of the second grid is less than or equal to the second threshold, wherein the first threshold is greater than the second threshold, and the feature value is the probability that the positioning reference object occupies the grid, and the positioning reference object is used to determine the positioning information of the terminal; According to the eigenvalues of the first grid, update the eigenvalues of the second grid so that the updated eigenvalues of the second grid are greater than the second threshold and smaller than the eigenvalues of the first grid to obtain a second map, and A third map is generated according to the second map; the terminal matches the environment information with the third map to obtain the positioning information of the terminal.
  • the distance between the first grid and the second grid may be less than or equal to the first distance.
  • the larger the distance between the first grid and the second grid the smaller the eigenvalue of the updated second grid.
  • acquiring the first map according to the environmental information includes: acquiring a fourth map according to the environmental information, where the fourth map includes a first grid and a fourth grid, and features of the fourth grid The value is less than or equal to the second threshold; by dividing the fourth map, the first map and the seventh map can be obtained, the seventh map includes the fifth map and/or the sixth map, and the fifth map only includes the first grid The sixth map includes only the fourth grid; and generating the third map according to the second map includes: generating the third map according to the second map and the seventh map.
  • the first map may be a two-dimensional grid map or a three-dimensional grid map.
  • the distance between the first grid and the second grid may include any one of a lateral distance, a longitudinal distance, or a radius value radiating from the first grid as a center to the surrounding.
  • an embodiment of the present application provides an apparatus for generating a positioning map
  • the apparatus includes: an acquisition unit, configured to acquire a first map, the first map includes a first grid and a second grid, and the first grid is The feature value is greater than or equal to the first threshold, and the feature value of the second grid is less than or equal to the second threshold, where the first threshold is greater than the second threshold, and the feature value is the probability that the positioning reference object occupies the grid, and the positioning reference object is used for determining the positioning information of the terminal; an update unit, configured to update the feature value of the second grid according to the feature value of the first grid so that the updated feature value of the second grid is greater than the second threshold and smaller than the first grid The feature value of , obtains the second map; the map generating unit is used for generating the third map according to the second map.
  • the distance between the first grid and the second grid may be less than or equal to the first distance.
  • the larger the distance between the first grid and the second grid the smaller the eigenvalue of the updated second grid.
  • the apparatus may further include a transceiving unit, the transceiving unit is configured to receive a first request message from the terminal, where the first request message is used to request to acquire the third map; and send the first request message to the terminal A response message, wherein the third map is included in the first response message.
  • the acquiring unit is specifically configured to: acquire a fourth map, where the fourth map includes a first grid and a fourth grid, and the feature value of the fourth grid is less than or equal to the second threshold; and Divide the fourth map to obtain the first map and the seventh map, the seventh map includes the fifth map and/or the sixth map, the fifth map only includes the first grid, and the sixth map only includes the first grid.
  • a fourth grid is included; the map generating unit is specifically configured to: generate a third map according to the second map and the seventh map.
  • the first map may be a two-dimensional grid map or a three-dimensional grid map.
  • the distance between the first grid and the second grid may include any one of a lateral distance, a longitudinal distance, or a radius value radiating from the first grid to the surrounding.
  • an embodiment of the present application provides a positioning device, the device includes: an acquisition unit for acquiring environmental information of the environment in which it is located; and a positioning unit for determining a third map according to the environmental information, the third map is generated according to the second map, the second map includes a first grid and a third grid, the eigenvalue of the first grid is greater than or equal to the first threshold, the eigenvalue of the third grid is greater than the second threshold, and is smaller than the feature value of the first grid, and the feature value of the third grid is determined according to the feature value of the first grid, wherein the first threshold value is greater than the second threshold value, and the feature value is the probability that the positioning reference object occupies the grid,
  • the positioning reference object is used to determine the positioning information of the terminal; and the environment information is matched with the third map to obtain the positioning information of the terminal.
  • the distance between the first grid and the third grid may be less than or equal to the first distance.
  • the apparatus may further include a transceiving unit, the transceiving unit is configured to send a first request message to the network device, where the first request message is used to request to acquire the third map; and receive the first request message from the network device A response message, the first response message including the third map.
  • the distance between the first grid and the third grid may include any one of a lateral distance, a longitudinal distance, or a radius value radiating from the first grid as a center to the surrounding.
  • an embodiment of the present application provides another positioning device, the device includes: an acquisition unit configured to acquire environmental information of the environment in which the device is located, and acquire a first map according to the environmental information, where the first map includes a first map. grid and second grid, the feature value of the first grid is greater than or equal to the first threshold, the feature value of the second grid is less than or equal to the second threshold, wherein the first threshold is greater than the second threshold, and the feature value is positioning The probability that the reference object occupies the grid, and the positioning reference object is used to determine the positioning information of the terminal; the updating unit is used to update the feature value of the second grid according to the feature value of the first grid, so that the updated second grid The eigenvalue is greater than the second threshold and smaller than the eigenvalue of the first grid to obtain the second map; the map generating unit is used to generate the third map according to the second map; the positioning unit is used to compare the environmental information with the third map match to obtain the positioning information of the terminal.
  • the distance between the first grid and the second grid may be less than or equal to the first distance.
  • the larger the distance between the first grid and the second grid the smaller the eigenvalue of the updated second grid.
  • the obtaining unit is specifically configured to: obtain a fourth map according to the environmental information, where the fourth map includes a first grid and a fourth grid, and the feature value of the fourth grid is less than or equal to the first grid and dividing the fourth map to obtain a first map and a seventh map, the seventh map includes a fifth map and/or a sixth map, the fifth map only includes the first grid, and the seventh map includes only the first grid. Only the fourth grid is included in the six maps; the map generating unit is specifically used for: generating the third map according to the second map and the seventh map.
  • the first map may be a two-dimensional grid map or a three-dimensional grid map.
  • the distance between the first grid and the second grid may include any one of a lateral distance, a longitudinal distance, or a radius value radiating from the first grid as a center to the surrounding.
  • an embodiment of the present application provides a communication device, including a processor and a memory, wherein the memory is used to store a computer program or instruction, and the processor is used to call the computer program or instruction stored in the memory, execute the The above first aspect or any possible design of the first aspect, or the second aspect or any possible design of the second aspect, or the third aspect or any possible design of the third aspect described in Methods.
  • an embodiment of the present application provides a computer-readable storage medium, where the computer-readable storage medium has any possible design for implementing the first aspect or the first aspect, or the second aspect or the first aspect. Any possible design of the second aspect, or a computer program or instructions for the method described in the third aspect or any possible design of the third aspect.
  • an embodiment of the present application further provides a computer program product, including a computer program or instruction, when the computer program or instruction is executed, the first aspect or any possible design of the first aspect can be implemented , or the second aspect or any possible design of the second aspect, or the method described in the third aspect or any possible design of the third aspect.
  • the present application further provides a chip for implementing the first aspect or any possible design of the first aspect, or the second aspect or any possible design of the second aspect, Or the method described in the third aspect or any possible design of the third aspect.
  • FIG. 1 is a schematic diagram of an application scenario adapted to an embodiment of the present application
  • FIG. 2 is a schematic diagram of a change in a positioning reference object in an embodiment of the present application
  • FIG. 3 is another schematic diagram of a change in a positioning reference object in an embodiment of the present application.
  • FIG. 4 is a schematic flowchart of a positioning method provided by an embodiment of the present application.
  • FIG. 5 is a schematic diagram of a first map provided by an embodiment of the present application.
  • 6A is another schematic diagram of a first map provided by an embodiment of the present application.
  • 6B is another schematic diagram of a first map provided by an embodiment of the present application.
  • FIG. 7A is a schematic diagram of a positional relationship between a first grid and a second grid provided by an embodiment of the present application.
  • 7B is another schematic diagram of the positional relationship between the first grid and the second grid provided by an embodiment of the present application.
  • 7C is another schematic diagram of the positional relationship between the first grid and the second grid provided by an embodiment of the present application.
  • 7D is another schematic diagram of the positional relationship between the first grid and the second grid provided by an embodiment of the present application.
  • FIG. 8A is another schematic diagram of a positional relationship between a first grid and a second grid provided by an embodiment of the present application.
  • 8B is another schematic diagram of the positional relationship between the first grid and the second grid provided by an embodiment of the present application.
  • 8C is another schematic diagram of the positional relationship between the first grid and the second grid provided by an embodiment of the present application.
  • FIG. 9 is a schematic diagram of a second map provided by an embodiment of the present application.
  • FIG. 10A is a schematic diagram of projecting a feature provided by an embodiment of the present application to a three-dimensional grid map
  • FIG. 10B is a schematic diagram of projecting a feature provided by an embodiment of the present application to a first map
  • 10C is a schematic diagram of a feature provided by an embodiment of the present application projected onto a third map
  • FIG. 11 is a schematic flowchart of another positioning method provided by an embodiment of the present application.
  • FIG. 12 is a schematic structural diagram of a positioning map generating apparatus provided by an embodiment of the present application.
  • FIG. 13 is a schematic structural diagram of a positioning device provided by an embodiment of the present application.
  • FIG. 14 is another schematic structural diagram of the positioning device provided by the embodiment of the application.
  • FIG. 15 is a schematic structural diagram of a communication device provided by an embodiment of the present application.
  • FIG. 16 is another schematic structural diagram of a communication device provided by an embodiment of the present application.
  • 17 is a schematic diagram of four submaps provided by an embodiment of the present application.
  • FIG. 18 is another schematic diagram of four submaps provided in an embodiment of the present application.
  • the network equipment involved in the embodiments of the present application may include, but are not limited to, a single server, a server cluster, or a cloud server and other devices that provide map construction capabilities and storage capabilities.
  • an application is installed in the terminal, and the network device may be a server corresponding to the application.
  • the application here can be a location-related application.
  • the application is a positioning (application, APP), and the server is a server corresponding to the positioning APP.
  • the apparatus for implementing the function of the network device may be the network device itself, or may be an apparatus capable of supporting the network device to implement the function, such as a chip system, and the apparatus may be installed in the network device.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the terminals involved in the embodiments of this application may include but are not limited to mobile phones, tablet computers, wearable devices (such as glasses, gloves, watches, wristbands, clothing, and shoes, etc.), vehicles, in-vehicle devices (or Vehicle terminal), augmented reality (AR)/virtual reality (VR) device, laptop, ultra-mobile personal computer (UMPC), netbook or personal digital assistant (personal digital assistant, PDA) and other mobile devices that need to be positioned.
  • AR augmented reality
  • VR virtual reality
  • laptop laptop
  • UPC ultra-mobile personal computer
  • PDA personal digital assistant
  • the device for realizing the function of the terminal may be the terminal itself, or may be a device capable of supporting the terminal to realize the function, such as a chip system, and the device may be installed in the terminal.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the prior map involved in the embodiments of the present application may be prior knowledge during terminal positioning, which can comprehensively reflect road conditions and assist the terminal to obtain positioning information.
  • the terminal may match the current environment information with the prior map to obtain its own position in the prior map.
  • the prior map may be a high-precision map with a centimeter-level accuracy.
  • a grid map may refer to a map that divides the environment into a series of grids, where each grid may include a possible feature value.
  • the feature value may be the probability that the positioning reference object occupies the grid, and its value may be 0-1.
  • a grid with a feature value of 1 may indicate that the grid is occupied by a positioning reference object.
  • a grid with an eigenvalue of 0 may indicate that the grid is not occupied by a positioning reference object. The larger the feature value of the grid, the greater the probability that the grid is occupied by the positioning reference object, and the greater the impact of the grid on the positioning.
  • Positioning reference objects The positioning reference objects involved in the embodiments of the present application may include, but are not limited to, lanes, trees, buildings, roadside landmarks, flower beds, and other objects that are helpful for positioning.
  • a map server may receive environmental information collected from a measuring device, extract features of the positioning reference object from the environmental information, and then construct a priori map based on the features of the positioning reference object.
  • the vehicle can collect the current environment information, extract the features of the positioning reference object from the environment information, and then match the features of the positioning reference object with the features of the positioning reference object in the prior map to obtain the position information of the vehicle.
  • “plurality” refers to two or more than two. In view of this, “plurality” may also be understood as “at least two” in the embodiments of the present application. "At least one" can be understood as one or more, such as one, two or more. For example, including at least one refers to including one, two or more, and does not limit which ones are included. For example, including at least one of A, B, and C, then including A, B, C, A and B, A and C, B and C, or A and B and C.
  • ordinal numbers such as “first”, “second”, and “third” are mentioned in the embodiments of the present application to distinguish multiple objects, and are not used to limit the order, sequence, and priority of multiple objects. level or importance.
  • FIG. 1 is a schematic diagram of an application scenario to which this embodiment of the present application is applied.
  • the indication information of the driving direction of the lane includes 4 lanes, of which the driving directions of the two lanes on the left are the same, and the driving directions of the vehicles in the two lanes on the right are the same.
  • the vehicle may be a smart car or a non-smart car, which is not limited in this embodiment of the present application.
  • the vehicle is provided with sensors, which are used to detect targets around the vehicle, such as trees in green belts, roadside landmarks, lane boundaries or lane lines, etc.
  • the sensors may include but are not limited to lidar, millimeter wave Radar or camera etc.
  • the vehicle may be provided with one or more sensors, and the number of each sensor may be one or more.
  • the sensor may be installed on the roof of the vehicle, specifically, may be arranged at a middle position of the roof of the vehicle.
  • the embodiment of the present application does not limit the installation position and number of the sensors in the vehicle.
  • 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
  • vehicle-to-vehicle communication may be implemented based on an inter-vehicle wireless communication technology (eg, vehicle to vehicle (V2V)).
  • 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 vehicles and smart devices such as location-enabled smartphones or mobile devices can be enabled based on 5G.
  • the application scenario shown in FIG. 1 may further include a map server, and the map server may be implemented by a server or a virtual machine in the cloud.
  • the map server may be implemented by a server or a virtual machine in the cloud.
  • the preset area of the vehicle's sensor is shown as a dashed circle in Fig. 1, with the vehicle as the center and the preset distance as the radius.
  • the preset distance may be a value less than or equal to the radius of the coverage area of the lidar signal emitted by the vehicle.
  • the vehicle when constructing a priori map, the vehicle (or other measurement equipment with sensors) can collect lidar data of targets within a preset range through sensors, and then send the collected lidar data to the map server, thereby, The map server can build a priori map from this lidar data. Further, the map server can also send the prior map to the vehicle. For another example, during positioning, the vehicle (or other device to be positioned with a sensor) can collect lidar data of a target within a preset range through the sensor, and then match the collected lidar data with the prior map, thereby , the vehicle (or other device to be located with sensors) can obtain its own position and pose in the prior map. Further, the vehicle can also perform path planning and decision-making based on its own position and pose in the prior map.
  • the number of map servers in the application scenario shown in FIG. 1 may be one or more.
  • the two map servers may be map server 1 and map server 2, respectively.
  • the map server 1 can construct a priori maps of multiple areas, and the multiple areas can include the areas covered by the map server 2, so that the map server 2 can obtain the a priori maps of the covered areas by interacting with the map server 1 and storage.
  • the map server 2 can also interact with the vehicle, and send a prior map of its coverage area to the vehicle, so that the vehicle can locate in the coverage area of the map server 2 .
  • the map server 1 can also interact with the vehicle, and send the prior maps of the multiple areas to the vehicle, so that the vehicle can locate the multiple areas.
  • the map server 2 may also construct and store a priori map of its coverage area.
  • the positioning reference objects may include, but are not limited to, trees, roads, buildings, or roadside landmarks.
  • these characteristic information may include road data (such as lane information such as the location, type, width, slope or curvature of the lane line) and details around the lane (such as traffic signs, traffic lights, roadside landmarks, road edge types, guardrails, etc.) details such as columns or trees).
  • the construction cycle of the prior map will not be very frequent, which requires that the positioning reference object used to construct the prior map will not change within a period of time. , such as position change, shape change, or pose change, etc.
  • the positioning reference object is not absolutely unchanged.
  • the features of the positioning reference object collected in real time by the vehicle cannot completely correspond to the features of the positioning reference object in the prior map, resulting in errors in the matching results between the two, and it is difficult to ensure the accuracy of the positioning information.
  • the wind blows the trees, and the branches and leaves of the trees shake.
  • the characteristics of the trees collected by the vehicle cannot completely correspond to the characteristics of the trees in the prior map.
  • the solid line can be The position of the trees collected by the measuring device when constructing the prior map
  • the dotted line part can be the position of the trees collected by the vehicle during positioning.
  • the two cannot completely correspond.
  • the crowns of trees will change as the seasons change.
  • the shape of the tree collected by the vehicle cannot completely correspond to the shape of the tree in the prior map.
  • the solid line It can be the shape of the trees collected by the measuring device when constructing the prior map
  • the dotted line part can be the shape of the trees collected by the vehicle during positioning.
  • the two cannot completely correspond.
  • the map needs to be offset in the process of constructing the prior map, for example, the offset is 20 cm every 100 meters.
  • the vehicle needs to perform corresponding bias addition processing on the collected features or perform corresponding bias reduction processing on the prior map. Errors will inevitably be introduced in the process of bias addition processing or bias reduction processing, which will also lead to inaccurate positioning results. precise. It can be seen that the current prior map has poor compatibility with errors, and it is difficult to ensure the accuracy of positioning.
  • a first map includes a first grid and a second grid, the feature value of the first grid is greater than or equal to a first threshold, and the second grid The eigenvalue of the grid is less than or equal to the second threshold, and the eigenvalue of the second grid is updated according to the eigenvalue of the first grid, so that the updated eigenvalue of the second grid is greater than the second threshold but smaller than the eigenvalue of the first grid. feature values, and then generate a third map based on the updated second raster.
  • the updated eigenvalue of the second grid is greater than the second threshold but smaller than the eigenvalue of the first grid, which means that the probability of the positioning reference object occupying the second grid is increased, so that the updated second grid has a good impact on positioning.
  • the impact has also increased accordingly, but the impact of the updated second grid on positioning does not exceed the impact of the first grid on positioning, so the third map generated based on the updated second grid can be well compatible.
  • errors are caused by dynamic features, offset addition operations or offset subtraction operations, etc. At the same time, the influence of the original features on the positioning is also guaranteed, additional errors are avoided, and the robustness of the positioning can be improved.
  • FIG. 4 is a schematic flowchart of a positioning method according to an embodiment of the present application.
  • the network device generates a third map, sends the third map to the terminal, and the terminal receives the third map and performs positioning based on the third map.
  • the method can be applied to the communication system shown in FIG. 1 . The method is described below by taking the method applied to the communication system shown in FIG. 1 , where the network device is a map server and the terminal is a vehicle as an example.
  • the map server obtains a fourth map.
  • the map server may acquire the fourth map in the following manner: A1, the measurement device with sensors collects environmental information, and sends the environmental information to the map server, and the map server receives the environmental information; A2, the map server extracts the environmental information from the environmental information
  • the feature of the reference object is located, and a prior map is constructed based on the feature of the located reference object, and the fourth map may be part or all of the prior map.
  • the sensor of the measurement device may include, but is not limited to, at least one of a camera, a lidar sensor, or a millimeter-wave radar.
  • the fourth map may also be a high-precision map with an accuracy of centimeter level.
  • the fourth map may include a first grid and a fourth grid, the feature value of the first grid is greater than or equal to the first threshold, and the feature value of the fourth grid is less than or equal to the second threshold.
  • the first threshold may be greater than the second threshold.
  • the first threshold and the second threshold may be predefined, for example, the first threshold is 1 and the second threshold is 0.
  • the feature value may be the probability that the positioning reference object occupies the grid, and the positioning reference object may be used to determine the positioning information of the vehicle.
  • the fourth map may be a three-dimensional grid map, a two-dimensional grid map, or a probability map, etc.
  • the specific form of the fourth map is not limited in this embodiment of the present application.
  • S402 The map server divides the fourth map to obtain the first map.
  • the map server may obtain one or more first maps by dividing the fourth map.
  • the first map may include a first grid and a second grid.
  • the characteristic value of the second grid is less than or equal to the second threshold.
  • the second grid may be part or all of the fourth grid in the first map.
  • the first map may include the first grid, the second grid, and the fourth grid.
  • the map server may divide the fourth map into multiple sub-maps in an even manner to obtain one or more first maps. If the fourth map is a probability map, the map server may first convert the fourth map into a two-dimensional grid map (or a three-dimensional grid map), and then convert the converted two-dimensional grid map (or three-dimensional grid map) according to the method of equal division.
  • a grid map) is divided into a plurality of sub-maps to obtain one or more first maps.
  • the first map may be a two-dimensional grid map or a three-dimensional grid map, which is not limited in this embodiment of the present application.
  • the fourth map is a two-dimensional grid map
  • the fourth map may include 100 grids
  • the map server may divide the fourth map into 4 sub-maps equally, and obtain 2 first maps, wherein each first map 25 grids are included, as shown in Figure 5.
  • the fourth map is a three-dimensional grid map
  • the fourth map may include 10 layers, each layer includes 100 grids
  • the map server may divide the fourth map into 4 sub-maps equally, and obtain a first map, such as As shown in FIG. 6A , the thick black line in FIG. 6A represents the first grid, and the rest are the fourth grid.
  • 6A includes 5 layers, each layer includes 25 grids, from top to bottom, the first layer, the second layer and the third layer of the first map all include a first grid , the fourth and fifth layers of the first map both include two first grids, as shown in FIG. 6B .
  • the first threshold is 1, and the second threshold is 0. If the eigenvalues of the grids of each layer of the first map shown in FIG.
  • the eigenvalues of the raster for one layer are as follows:
  • a i represents the feature value of the grid of the i-th layer from top to bottom in the first map, and i is an integer greater than or equal to 1 and less than or equal to 5.
  • the second grid may be part of the fourth grid.
  • the second grid may be a grid whose distance from the first grid is less than or equal to the first distance in the fourth grid, that is, the distance between the second grid and the first grid is less than or equal to the first grid. equal to the first distance. That is, updating only the grids whose distance from the first grid is less than or equal to the first distance can avoid introducing additional errors.
  • the distance between the second grid and the first grid may be a horizontal distance, or a vertical distance, or a horizontal distance and a vertical distance, or a distance radiating from the first grid as the center.
  • the distance between the first grid and the second grid may also be a radius value radiating from the center of the first grid to the surrounding in the lateral direction, or the distance in the longitudinal direction. The radius value radiating around the first grid in the direction, or the radius value radiating around the first grid in the horizontal direction and the longitudinal direction, etc.
  • the lateral distance may refer to the distance in the direction parallel to the X axis in the coordinate system
  • the vertical distance may refer to the distance in the direction perpendicular to the X axis in the coordinate system.
  • the lateral distance may be a distance in a direction parallel to the XOY plane in the coordinate system
  • the longitudinal distance may be a distance in a direction perpendicular to the XOY plane in the coordinate system.
  • the coordinate system may be a world coordinate system, or a coordinate system with a terminal as an origin, etc., which is not limited to the comparison of the embodiments of the present application.
  • the first map includes 25 grids, and the first distance is a distance greater than two grids and less than three grids as an example, if the first grid and the second grid The distance between them is the horizontal distance, then the first grid, the third grid and the fourth grid in the fourth row in the first map are the second grids, as shown in FIG. 7A . If the distance between the first grid and the second grid is the vertical distance, the second grid, the third grid and the fifth grid in the second column in the first map are the second grid, As shown in Figure 7B.
  • the first grid, the third grid and the fourth grid in the fourth row in the first map, the third grid and the fourth grid, and the The second grid, the third grid, and the fifth grid in the two columns are the second grids, as shown in FIG. 7C . If the distance between the first grid and the second grid is the radius value radiating around the first grid, then the first grid in the second row, the third row and the fifth row in the first map grid, the second grid, the third grid, and the fourth grid, and the first grid, the third grid, and the fourth grid in the fourth row are the second grid, such as shown in Figure 7D.
  • the first map includes 5 layers, each layer includes 25 grids, the second layer from top to bottom of the first map includes a first grid, and the first distance is greater than The distance between two grids and less than three grids is taken as an example. If the distance between the first grid and the second grid is the radius value radiating from the first grid to the surrounding in the lateral direction, then the first grid the first grid, the second grid, the third grid, and the fourth grid in the second, third, and fifth rows in the second layer from top to bottom in a map, and The first grid, the third grid and the fourth grid in the fourth row are the second grids, as shown in FIG. 8A .
  • first grid and the fifth grid are the second grid, as shown in FIG. 8B .
  • the first, third and fourth layers from top to bottom in the first map
  • the first, second, third, and fourth grids in the third and fifth rows, and the first, third, and third grids in the fourth row in the second layer and the fourth grid is the second grid, as shown in Figure 8C.
  • the map server may divide the fourth map to obtain the first map and the seventh map.
  • the seventh map includes the fifth map and/or the sixth map
  • the fifth map may only include the first grid, as shown in the sub-map in the lower left corner of the fourth map in FIG. 5
  • the sixth map may only include The fourth grid, as shown in the submap in the lower right corner of the fourth map in Figure 5. That is, the map server divides the fourth map to obtain the first map and the fifth map, or the map server divides the fourth map to obtain the first map and the sixth map, or the map server divides the fourth map.
  • the first map, the fifth map and the sixth map can be obtained.
  • the map server updates the feature value of the second grid according to the feature value of the first grid to obtain a second map.
  • the map server may update the feature values of the second grid according to the feature values of the first grid to obtain the second map.
  • the map server may update the feature values of the second grid according to the feature values of the first grid in each layer to obtain the second map.
  • the map server may use at least one of a morphological expansion algorithm, a Gaussian smoothing algorithm, or a linear smoothing algorithm to update the eigenvalues of the second grid to obtain the second map.
  • the embodiment of the present application does not limit the update algorithm.
  • the second map may include a first grid and a third grid, the third grid may also be called an updated second grid, and the feature value of the third grid is greater than the second threshold.
  • the third grid in the second map may be referred to as the updated second grid hereinafter.
  • the second map may further include a fourth grid.
  • the updated eigenvalues of the second grid may be smaller than the eigenvalues of the first grid.
  • the map server updates the eigenvalues of the second grid according to the eigenvalues of the first grid, so that the updated eigenvalues of the second grid are greater than the second threshold but smaller than the eigenvalues of the first grid.
  • the impact of the updated second grid on the positioning should be smaller than that of the first grid, so as to ensure the influence of the original positioning features, thereby improving the prior map.
  • the compatibility of errors and the avoidance of introducing additional errors can improve the robustness of positioning.
  • the map server may also update the feature value of the second grid according to the distance between the first grid and the second grid. For example, the larger the distance between the first grid and the second grid, the smaller the eigenvalue of the updated second grid, so as the distance between the first grid and the second grid increases , the influence of the updated second grid on the positioning is gradually reduced, and the introduction of additional errors can be avoided while being compatible with errors, and the robustness of the positioning can be improved. For example, if the distances between the plurality of second grids and the same first grid are the same, the updated feature values of the plurality of second grids are also the same.
  • the updated eigenvalues of the second grid can be determined from the at least one first grid, and the The eigenvalue of the first grid with the smallest distance between the second grids is determined.
  • the first distance is a distance greater than two grids and less than three grids
  • the distance between the first grid and the second grid is the first grid as The radius value radiating from the center to the surrounding
  • the first threshold is 1
  • the second threshold is 0,
  • the map server updates the feature value of the second grid according to the first grid in each layer, and obtains the second map, in the second map
  • the eigenvalues of the grids of each layer from top to bottom are shown in Figure 9. If the eigenvalues of the grids of each layer in the second map are represented by a matrix, the eigenvalues of the grids of each layer in the second map from top to bottom are as follows:
  • B i represents the feature value of the grid of the i-th layer from top to bottom in the second map, and i is an integer greater than or equal to 1 and less than or equal to 5.
  • S404 The map server generates a third map according to the second map.
  • the map server may generate the third map according to the at least one second map.
  • the map server may generate the third map according to at least one second map and at least one fifth map.
  • the map server may generate the third map according to at least one second map and at least one sixth map.
  • the map server may Generate a third map.
  • the map server may generate a third map according to at least two sub-maps, and the at least two sub-maps include at least one second map.
  • the map server may determine the adjacent eighth map and ninth map in the at least two submaps; update the feature value of the sixth grid in the ninth map according to the feature value of the fifth grid in the eighth map , to obtain the tenth map, wherein the feature value of the sixth grid after the update is greater than the feature value of the sixth grid before the update, and is smaller than the feature value of the fifth grid in the eighth map; the map server can The tenth map and the eighth map generate the third map.
  • the eighth map includes a fifth grid
  • the ninth map includes a sixth grid
  • the feature value of the fifth grid is greater than or equal to the first threshold
  • the feature value of the sixth grid is less than the first threshold
  • the The distance between the sixth grid and the fifth grid is less than or equal to the first distance.
  • the eighth map is the second map
  • the ninth map can be the second map, the fifth map, or the sixth map
  • the eighth map is the fifth map
  • the ninth map can be the sixth map map.
  • the eigenvalues of the sixth grid in another adjacent submap can be updated according to the eigenvalues of the fifth grid in one submap, so as to improve the influence of the sixth grid on positioning, so as to be able to It is better compatible with errors caused by dynamic features, bias addition or subtraction operations in the positioning process, and further improves the robustness of positioning.
  • the distance between the fifth grid and the sixth grid may be a horizontal distance, or a vertical distance, or a horizontal distance and a vertical distance, or a distance radiated from the fifth grid as the center.
  • the distance between the fifth grid and the sixth grid may also be a radius value radiating around the fifth grid in the horizontal direction, or in the longitudinal direction. The above is the radius value radiating from the center of the fifth grid to the surrounding, or the radius value radiating to the surrounding from the center of the fifth grid in the horizontal direction and the longitudinal direction, etc.
  • the first distance is the distance greater than two grids and less than three grids
  • the distance between the fifth grid and the sixth grid is the fifth grid.
  • the radius value radiating from the center to the surrounding area is 1, and the second threshold is 0.
  • the map server updates the feature value of the second grid in the first map
  • two second maps and one fifth map are obtained.
  • a sixth map the eigenvalues of the grids in the four submaps are shown in Figure 17.
  • the map server can update the feature value of the sixth grid in the adjacent submap according to the feature value of the fifth grid in one submap, and the updated feature value of the grid in each submap is shown in Figure 18 .
  • the map server after the map server generates the third map, it can also receive a first request message from the vehicle, where the first request message is used to obtain the third map, that is, the map server can also execute the content shown in steps S405 and S406. .
  • the map server may send the third map to the vehicle, and the vehicle receives and stores the third map.
  • S405 The vehicle sends a first request message to the map server, and the map server receives the first request message.
  • the first request message is used to obtain the third map.
  • the vehicle owner can trigger the vehicle to send a first request message to the map server by operating an application program associated with the map server installed on the vehicle, and the map server receives the first request message.
  • the map server sends a first response message to the vehicle, and the vehicle receives the first response message.
  • the first response message includes a third map.
  • S407 The vehicle obtains environmental information of the environment in which it is located.
  • the vehicle may collect environmental information of the current environment through at least one of sensors such as a camera, a lidar, or a millimeter-wave radar.
  • sensors such as a camera, a lidar, or a millimeter-wave radar.
  • the environment information may be image data and/or video data captured by the camera.
  • the environmental information may be radar data detected by the lidar.
  • S408 The vehicle matches the environmental information with the third map to obtain the positioning information of the vehicle.
  • the vehicle may extract the features of the positioning reference object from the environmental information, and then match the features of the positioning reference object with the features of the positioning reference object in the third map to obtain the position information of the vehicle in the third map.
  • the vehicle may determine the positioning information of the vehicle through a Kalman filter algorithm or a particle filter algorithm.
  • step S408 the specific implementation process of step S408 is as follows: B1, the vehicle extracts the feature of the positioning reference object according to the environmental information; B2, the vehicle generates a particle set according to the environmental information, wherein the particle set includes at least one particle, and the at least one particle Each particle in can represent a possible pose of the vehicle in the third map; B3. The vehicle projects the feature of the positioning reference object into the third map through each particle, and obtains the feature of the positioning reference object in the third map.
  • the projected position (that is, the occupied grid) in B4 the vehicle can accumulate the feature values of the projected position of the feature of the positioning reference object in the third map to obtain the score of each particle; B5, the vehicle can obtain the score of each particle according to the can obtain the position information of the vehicle in the third map.
  • the higher the score of the particle the more likely the particle is to represent the pose of the vehicle in the third map.
  • the score of a particle can be determined according to the following formula:
  • w can represent the score of a particle
  • x, y, z can be the projected position of the feature through the particle projection to the third map
  • g( ) can represent the feature value of the grid in the third map.
  • the map server extracts seven features of the tree, and constructs a three-dimensional grid map according to the seven features. From top to bottom, the positions of the seven features in the three-dimensional grid map are the three-dimensional grid map.
  • the second grid of the second row of the first layer of the raster map, the second grid of the second row of the second layer, the second grid of the second row of the third layer, the second grid of the second row of the fourth layer The second grid and the fourth grid of the third row, the second grid of the second row of the fifth layer and the fourth grid of the third row, as shown in FIG. 6B . Under the blowing of the wind, the branches are shaken and displaced.
  • the map server receives the environmental information from the vehicle, extracts 7 features of the tree according to the environmental information, and projects the 7 features through the particle 1 to the image shown in Figure 6B.
  • the projection positions of the seven features in the three-dimensional grid map are the second grid of the first row of the first layer of the three-dimensional grid map, and the second grid of the second layer of the three-dimensional grid map.
  • the second grid of the first row, the second grid of the first row of the third layer, the second grid of the first row of the fourth layer and the fourth grid of the second row, the fifth layer of the second grid The second grid of a row and the fourth grid of the second row, as shown in Figure 10A.
  • the features of the positioning reference object should all be projected into the first grid through the particles, that is, the features of the positioning reference object collected in real time by the vehicle match the features of the positioning reference object in the prior map.
  • the features of the positioning reference object are also deviated accordingly, so that the features of the positioning reference object cannot all be projected into the first grid through the particles, but Projected into a neighboring grid of the first grid, which may be the fourth grid.
  • the projected position of the 7 features through particle 1 is only one grid away from the correct position (ie, the first grid), but all of them are projected to the fourth grid around the correct position, so that the particle
  • the score of 1 is 0, which greatly reduces the impact of particle 1 on positioning, that is, when the positioning reference object changes or errors are introduced due to the bias addition/subtraction operation, the existing prior map will lead to the correct position surrounding
  • the third map is compatible with errors caused by changes in the positioning reference object or due to bias addition/subtraction operations, which can effectively reduce the inaccurate positioning caused by the sudden drop in particle scores around the correct position. Influence.
  • the map server acquires the first map, the first map includes a first grid and a second grid, the feature value of the first grid is greater than or equal to the first threshold, and the feature value of the second grid less than or equal to the second threshold, update the eigenvalues of the second grid according to the eigenvalues of the first grid, so that the updated eigenvalues of the second grid are greater than the second threshold and smaller than the eigenvalues of the first grid, and A third map is generated from the updated second grid.
  • the feature value of the updated second grid is greater than the second threshold, which means that the probability that the positioning reference object occupies the second grid is increased, so that the impact of the updated second grid on positioning is also increased accordingly.
  • the third map generated by the updated second grid can be well compatible with errors caused by dynamic features, bias addition operations or bias subtraction operations during the positioning process, and at the same time, it also ensures the influence of the original features on positioning and avoids introducing The additional error can improve the robustness of the positioning.
  • the third map when combined with particle filtering, can reduce the problem of a sudden drop in particle scores that may exist around the correct positioning, thereby effectively reducing the impact of inaccurate positioning caused by a sudden drop in particle scores.
  • FIG. 11 is a schematic flowchart of another positioning method provided by an embodiment of the present application. This method can be applied to the communication system shown in Figure 1. The method is described below by taking the method applied to the communication system shown in FIG. 1 , where the network device is a map server and the terminal is a vehicle as an example.
  • S1101 The vehicle acquires environmental information of the environment in which it is located.
  • the vehicle may collect environmental information of the current environment through at least one of sensors such as a camera, a lidar, or a millimeter-wave radar.
  • sensors such as a camera, a lidar, or a millimeter-wave radar.
  • the environment information may be image data and/or video data captured by the camera.
  • the environmental information may be radar data detected by the lidar.
  • S1102 The vehicle acquires the first map according to the environmental information.
  • the first map may include a first grid and a second grid, the feature value of the first grid is greater than or equal to the first threshold, the feature value of the second grid is less than or equal to the second threshold, and the first threshold is greater than the first threshold Two thresholds.
  • the first map may be a two-dimensional grid map, or a three-dimensional grid map.
  • the distance between the first grid and the second grid may be less than or equal to the first distance, as shown in FIG. 7A , FIG. 7B , FIG. 7C , FIG. 8A , FIG. 8B or FIG. 8C .
  • the vehicle may send a second request message to the map server according to the environment information, and the map server receives the second request message, where the second request message is used to request to acquire the fourth map.
  • the vehicle receives a second response message from the map server, the second response message including a fourth map.
  • the vehicle may divide the fourth map to obtain the first map.
  • the process of constructing the fourth map and the process of acquiring the first map may refer to step 401 and step S402 in FIG. 4 respectively, which will not be repeated here.
  • S1103 The vehicle updates the eigenvalues of the second grid according to the eigenvalues of the first grid to obtain a second map.
  • the updated feature value of the second grid may be greater than the second threshold.
  • the updated feature value of the second grid may be greater than the second threshold, but smaller than the feature value of the first grid.
  • the larger the distance between the first grid and the second grid the smaller the eigenvalue of the updated second grid.
  • step S1103 For the specific implementation process of step S1103, reference may be made to the content described in step S403 in FIG. 4, which will not be repeated here.
  • S1104 The vehicle generates a third map according to the second map.
  • S1105 The vehicle matches the environment information with the third map to obtain the positioning information of the vehicle.
  • step S1104 and step S1105 For the specific implementation process of step S1104 and step S1105, reference may be made to the content shown in step S404 and step S408 in FIG. 4 respectively, and details are not repeated here.
  • the terminal itself can process the stored offline map (ie the first map) to generate the third map, that is, update the feature value of the second grid according to the feature value of the first grid, so that the updated The feature value of the second grid is greater than the second threshold, and a third map is generated according to the updated second grid. Then the terminal performs positioning according to the generated third map.
  • the stored offline map ie the first map
  • the third map that is, update the feature value of the second grid according to the feature value of the first grid, so that the updated The feature value of the second grid is greater than the second threshold
  • a third map is generated according to the updated second grid. Then the terminal performs positioning according to the generated third map.
  • the terminal can save the third map in the form of a two-dimensional grid map, which can reduce the map data stored offline and improve the utilization rate of the storage space.
  • the embodiments of the present application further provide a positioning map generation device, the positioning map generation device is used to realize the function of positioning map generation in the above-mentioned FIG. 4 , the positioning map generation device may be a map server or a setting Chip on the map server.
  • the positioning map generating apparatus 1200 includes: an acquiring unit 1201 , an updating unit 1202 and a map generating unit 1203 .
  • the positioning map generating apparatus may further include a transceiver unit 1204 . The following describes the functions and connections of each unit when the positioning map generating apparatus 1200 generates a positioning map.
  • the acquiring unit 1201 is configured to acquire a first map, the first map includes a first grid and a second grid, the feature value of the first grid is greater than or equal to a first threshold, and the feature value of the second grid is less than or equal to The second threshold, wherein the first threshold is greater than the second threshold, the feature value is the probability that the positioning reference object occupies the grid, and the positioning reference object is used to determine the positioning information of the terminal.
  • the updating unit 1202 is configured to update the eigenvalues of the second grid according to the eigenvalues of the first grid so that the updated eigenvalues of the second grid are greater than the second threshold and smaller than the eigenvalues of the first grid to obtain Second map.
  • the map generating unit 1203 is configured to generate a third map according to the second map.
  • the distance between the first grid and the second grid may be less than or equal to the first distance.
  • the greater the distance between the first grid and the second grid the smaller the eigenvalue of the updated second grid.
  • the transceiver unit 1204 is configured to receive a first request message from the terminal, where the first request message is used to request to acquire the third map; and send a first response message to the terminal, in which the first response message is Including the third map.
  • an embodiment of the present application further provides a positioning device, which is used to implement the positioning function in FIG. 4 above.
  • the positioning device may be a vehicle with a radar sensor or set in a vehicle with a radar sensor. chip on the vehicle.
  • the positioning apparatus 1300 includes: an acquisition unit 1301 and a positioning unit 1302 .
  • the positioning device may further include a transceiver unit 1303 . The following describes the functions and connections of each unit of the positioning device 1300 during positioning.
  • the obtaining unit 1301 is configured to obtain the environment information of the environment in which it is located.
  • the positioning unit 1302 is configured to determine a third map according to the environmental information, the third map is generated according to the second map, the second map includes a first grid and a third grid, and the feature value of the first grid is greater than or equal to the first threshold, the eigenvalue of the third grid is greater than the second threshold and smaller than the eigenvalue of the first grid, and the eigenvalue of the third grid is determined according to the eigenvalue of the first grid, wherein the first grid
  • the threshold is greater than the second threshold, and the feature value is the probability that the positioning reference object occupies the grid, and the positioning reference object is used to determine the positioning information of the terminal; and the environment information is matched with the third map to obtain the positioning information of the terminal.
  • the distance between the first grid and the third grid may be less than or equal to the first distance.
  • the larger the distance between the first grid and the third grid the smaller the eigenvalue of the third grid.
  • the transceiver unit 1303 is configured to send a first request message to the network device, where the first request message is used to request to obtain a third map; and receive a first response message from the network device, the first response message Including the third map.
  • an embodiment of the present application further provides a positioning device, the positioning device is used to realize the function of generating the positioning map and the positioning function in the above-mentioned FIG. 11 , and the positioning device may be a vehicle with a radar sensor or A chip placed on a vehicle with a radar sensor.
  • the positioning apparatus 1400 includes: an acquiring unit 1401 , an updating unit 1402 , a map generating unit 1403 and a positioning unit 1404 .
  • the positioning device may further include a transceiver unit 1405 . The following describes the functions and connections of each unit of the positioning device 1400 during positioning.
  • the obtaining unit 1401 is configured to obtain the environment information of the environment where it is located, and obtain a first map according to the environment information, the first map includes a first grid and a second grid, and the feature value of the first grid is greater than or equal to The first threshold, the feature value of the second grid is less than or equal to the second threshold, where the first threshold is greater than the second threshold, the feature value is the probability that the positioning reference object occupies the grid, and the positioning reference object is used to determine the positioning information of the terminal .
  • the updating unit 1402 is configured to update the eigenvalues of the second grid according to the eigenvalues of the first grid so that the updated eigenvalues of the second grid are greater than the second threshold and smaller than the eigenvalues of the first grid to obtain Second map.
  • the map generating unit 1403 is configured to generate a third map according to the second map.
  • the positioning unit 1404 is configured to match the environment information with the third map to obtain the positioning information of the terminal.
  • the distance between the first grid and the second grid may be less than or equal to the first distance.
  • the greater the distance between the first grid and the second grid the smaller the eigenvalue of the updated second grid.
  • each embodiment of the present application Units may be integrated in one processing unit, or may be separate integrated units, or two or more units may be integrated in one unit.
  • One or more of the above-mentioned units may be implemented in software, hardware, firmware, or a combination thereof.
  • the software or firmware includes, but is not limited to, computer program instructions or code, and can be executed by a hardware processor.
  • the hardware includes, but is not limited to, various types of integrated circuits, such as a central processing unit (CPU), a digital signal processor (DSP), a field programmable gate array (FPGA), or an application specific integrated circuit (ASIC).
  • CPU central processing unit
  • DSP digital signal processor
  • FPGA field programmable gate array
  • ASIC application specific integrated circuit
  • the integrated unit if implemented as a software functional unit and sold or used as a stand-alone product, may be stored in a computer-readable storage medium.
  • the technical solution of the present application can be embodied in the form of a software product in essence, or the part that contributes to the prior art, or all or part of the technical solution, and the computer software product can be stored in a storage medium , including several instructions to cause a computer device (which may be a personal computer, a server, or a network device, etc.) or a processor (processor) to execute all or part of the steps of the methods in the various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program codes .
  • an embodiment of the present application further provides a communication device, which can implement the function of generating a positioning map in FIG. 4 , and the communication device can be the map server shown in FIG. 1 .
  • the communication apparatus 1500 includes: a communication interface 1501 , a processor 1502 , and a memory 1503 .
  • the communication interface 1501 and the memory 1503 and the processor 1502 are connected to each other.
  • the communication interface 1501 and the memory 1503 and the processor 1502 can be connected to each other through a bus;
  • the bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, etc.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of representation, only one thick line is shown in FIG. 15, but it does not mean that there is only one bus or one type of bus.
  • the communication interface 1501 is used to realize the communication between the positioning map generating apparatus and other components in the positioning system.
  • the communication interface 1501 may be used to receive a first request message from the vehicle for obtaining a third map, and to send a first response message to the vehicle, the first response message including the third map.
  • the processor 1502 is configured to implement the above-mentioned method for generating a positioning map as shown in FIG. 4 .
  • the processor 1502 may be configured to acquire a first map, and the first map includes a first grid and a second grid. Grid, the eigenvalue of the first grid is greater than or equal to the first threshold, and the eigenvalue of the second grid is less than or equal to the second threshold; according to the eigenvalue of the first grid, the eigenvalue of the second grid is updated to make The updated feature value of the second grid is greater than the second threshold and smaller than the feature value of the first grid, so as to obtain a second map, and generate a third map according to the second map.
  • the processor 1502 may be a central processing unit (central processing unit, CPU), or other hardware chips.
  • the above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof.
  • the above-mentioned PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a general array logic (generic array logic, GAL) or any combination thereof.
  • CPLD complex programmable logic device
  • FPGA field-programmable gate array
  • GAL general array logic
  • the memory 1503 is used to store program instructions, data, and the like.
  • the program instructions may include program code, which includes instructions for computer operation.
  • the memory 1503 may include random access memory (RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage.
  • the processor 1502 executes the program stored in the memory 1503, and implements the above functions through the above components, thereby finally realizing the methods provided by the above embodiments.
  • an embodiment of the present application further provides a communication device, which can implement the function of generating positioning in the above FIG. 4 , or the function of generating a positioning map and the function of positioning in the above FIG. 11 , and the communication
  • the device may be the vehicle shown in FIG. 1 .
  • the communication device 1600 includes: a communication interface 1601 , a processor 1602 , and a memory 1603 .
  • the communication interface 1601 and the memory 1603 and the processor 1602 are connected to each other.
  • the communication interface 1601, the memory 1603 and the processor 1602 can be connected to each other through a bus;
  • the bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (extended industry standard architecture, EISA) bus, etc.
  • PCI peripheral component interconnect
  • EISA extended industry standard architecture
  • the bus can be divided into address bus, data bus, control bus and so on. For ease of presentation, only one thick line is shown in FIG. 16, but it does not mean that there is only one bus or one type of bus.
  • the communication interface 1601 is used to realize the communication between the positioning map generating apparatus and other components in the positioning system.
  • the communication interface 1601 can be used to send a first request message (or a second request message, the second request message is used to obtain the fourth map) to the positioning map, the first request message is used to obtain the third map, and to receive data from The first response message (or the second response message, the second response message including the fourth map) of the map server, the first response message including the third map.
  • the processor 1602 is configured to implement the above-mentioned method for generating a positioning map as shown in FIG. 4 , or the above-mentioned method for generating a positioning map as shown in FIG. 11 .
  • the processor 1602 may be configured to obtain environmental information of the environment where it is located, determine a third map according to the environmental information, and match the environmental information with the third map to obtain the positioning information of the terminal.
  • the processor 1602 can be configured to acquire the first map, and update the feature value of the second grid according to the feature value of the first grid so that the updated feature value of the second grid is greater than the second threshold and less than the first grid
  • a feature value of a grid is used to obtain a second map, and a third map is generated according to the second map, and the environment information is matched with the third map to obtain the positioning information of the terminal.
  • the processor 1602 may be a central processing unit (central processing unit, CPU), or other hardware chips.
  • the above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof.
  • the above-mentioned PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a general array logic (generic array logic, GAL) or any combination thereof.
  • CPLD complex programmable logic device
  • FPGA field-programmable gate array
  • GAL general array logic
  • the processor 1602 implements the above functions, it can be implemented by hardware, and of course, it can also be implemented by executing corresponding software by hardware.
  • the memory 1603 is used to store program instructions, data, and the like.
  • the program instructions may include program code, which includes instructions for computer operation.
  • the memory 1603 may include random access memory (RAM), and may also include non-volatile memory (non-volatile memory), such as at least one disk storage.
  • the processor 1602 executes the program stored in the memory 1603, and implements the above-mentioned functions through the above-mentioned various components, thereby finally realizing the methods provided by the above-mentioned embodiments.
  • the embodiments of the present application further provide a computer program, when the computer program runs on a computer, the computer executes the methods provided by the above embodiments.
  • embodiments of the present application further provide a computer storage medium, where a computer program is stored in the computer storage medium, and when the computer program is executed by a computer, the computer executes the methods provided by the above embodiments.
  • the embodiments of the present application also provide a computer product, the computer product includes a computer program or instructions, when the computer program or instructions are executed, the computer product can be made to execute the methods provided by the above embodiments.
  • an embodiment of the present application further provides a chip, where the chip is used to read a computer program stored in a memory to implement the methods provided by the above embodiments.
  • the embodiments of the present application provide a chip system, where the chip system includes a processor for supporting a computer device to implement the functions involved in the high-precision map generation device and/or the positioning device in the methods provided by the above embodiments. functions involved.
  • the chip system further includes a memory for storing necessary programs and data of the computer device.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions
  • the apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

Landscapes

  • Engineering & Computer Science (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Navigation (AREA)

Abstract

一种定位地图生成方法、定位方法、定位地图生成装置、定位装置、通信装置、计算机可读存储介质、计算机程序产品及芯片，涉及自动驾驶领域，用以提高先验地图对误差的兼容能力，提高定位的鲁棒性。其中该定位地图生成方法包括：获取第一地图，第一地图中包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，其中，第一阈值大于第二阈值，特征值为定位参考对象占据栅格的概率，定位参考对象用于确定终端的定位信息；根据第一栅格的特征值，更新第二栅格的特征值使得更新后的第二栅格的特征值大于第二阈值且小于第一栅格的特征值，得到第二地图；根据第二地图生成第三地图。

Description

一种定位地图生成方法、定位方法及装置
相关申请的交叉引用
本申请要求在2020年06月30日提交中国专利局、申请号为202010623974.0、申请名称为“一种定位地图生成方法、定位方法及装置”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
本申请实施例涉及自动驾驶领域，尤其涉及一种定位地图生成方法、定位方法及装置。
背景技术
自动驾驶车辆的正常运行依赖于先验地图。先验地图可以为自动驾驶车辆定位时的先验知识，能够帮助自动驾驶车辆进行规划和决策。例如，自动驾驶车辆可以将当前的环境信息与先验地图进行匹配，得到该自动驾驶车辆在先验地图中的位置和姿态，并基于该位置和姿态进行路径规划。
先验地图作为自动驾驶车辆定位时的先验知识，需要对环境的描述是完备的、且能够全面反映环境中有助于定位的信息，因此先验地图在构建过程中需要采集大量的定位参考对象(如建筑、树木、路边地标或车道等)的特征信息。考虑到大量特征信息的采集和处理需要较多的人力和物力开销，因此先验地图的构建周期不会很频繁，这就要求用于构建先验地图的定位参考对象在一段时间内不会发生变化(如形状变化或位置变化等)。但随着外在因素(如天气变化或季节更换等)的影响，定位参考对象并不是绝对不变的，例如树木的树枝在风的吹动下从位置1移动到位置2，这就存在以下情况：自动驾驶车辆实时采集的树枝的位置2与先验地图中该树枝的位置1之间存在误差，导致实时采集的树枝的特征与先验地图中该树枝的特征无法完全对应，从而难以保证定位的准确性。可见，目前的先验地图对误差的兼容能力较差，难以保证定位的准确性。
发明内容
本申请实施例提供了一种定位地图生成方法、定位方法及装置，用以提高先验地图对误差的兼容能力，提高定位的鲁棒性。
第一方面，本申请实施例提供一种定位地图生成方法，该方法可以由网络设备(如单服务器，云端服务器或虚拟机等)执行，也可以由网络设备中的芯片或芯片系统执行。下面以执行主体是网络设备为例进行描述。该方法包括：网络设备获取第一地图，第一地图中包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，其中，第一阈值大于第二阈值，特征值为定位参考对象占据栅格的概率，定位参考对象用于确定终端的定位信息；根据第一栅格的特征值，更新第二栅格的特征值以使得更新后的第二栅格的特征值大于第二阈值但小于第一栅格的特征值，得到第二地图，并根据第二地图生成第三地图。
在上述技术方案中，根据第一栅格的特征值更新第二栅格的特征值，更新后的第二栅 格的特征值大于第二阈值且小于第一栅格的特征值，意味着增加了定位参考对象占据第二栅格的概率，使得更新后的第二栅格对定位的影响也相应增大了，但更新后的第二栅格对定位的影响未超过第一栅格对定位的影响，从而根据该更新后的第二栅格生成的第三地图能够很好地兼容定位过程中因动态特征、加偏运算或减偏运算等引起误差，同时还保障了原有特征对定位的影响，避免引入额外的误差，能够提高定位的鲁棒性。例如，在结合粒子滤波时，第三地图可以减少正确定位周边可能存在的粒子评分骤降的问题，从而有效减少因粒子评分骤降导致定位不准确的影响。
在一种可能的设计中，所述第一栅格与所述第二栅格之间的距离可以小于或等于第一距离。采用这种方式，仅需要更新与第一栅格之间的距离小于或等于第一距离的栅格，这样可以避免引入额外的误差。
在一种可能的设计中，所述第一栅格与所述第二栅格之间的距离越大，更新后的所述第二栅格的特征值越小。采用这种方式，随着第一栅格与第二栅格之间的距离的增大，更新后的第二栅格对定位的影响可以逐渐减小，以提高定位的鲁棒性。
在一种可能的设计中，该方法还可以包括：网络设备接收来自终端的第一请求消息，第一请求消息用于请求获取所述第三地图；网络设备向终端发送第一响应消息，第一响应消息中包括所述第三地图。采用这种方式，终端可以获取到第三地图，并基于该第三地图进行定位。由于第三地图中第三栅格的特征值是根据第一栅格的特征值确定的、且第三栅格的特征值大于第二阈值，因此第三地图的适应性好、且对误差具有良好的兼容能力，能够帮助终端获取准确的定位信息。
在一种可能的设计中，获取第一地图，包括：获取第四地图，该第四地图中包括第一栅格和第四栅格，第四栅格的特征值小于或等于第二阈值；对第四地图进行划分，可以得到第一地图和第七地图，第七地图中包括第五地图和/或第六地图，该第五地图中仅包括第一栅格，该第六地图中仅包括第四栅格；根据第二地图，生成第三地图，包括：根据第二地图和第七地图，生成第三地图。采用这种方式，对第四地图进行划分后，可能得到仅包括第一栅格的第五地图和/或仅包括第六地图，在生成定位地图时，可以对第二地图和第七地图进行拼接得到第三地图，从而可以确保第三地图中定位信息的完整性。
在一种可能的设计中，该第一地图可以为二维栅格地图，或者为三维栅格地图。
在一种可能的设计中，该第一栅格与第二栅格之间的距离可以包括横向距离、纵向距离或以第一栅格为中心向四周辐射的半径值等中的任一种。例如，若第一地图为二维栅格地图，则横向距离可以为平行于坐标系中X轴的方向上的距离，纵向距离可以为垂直于坐标系中X轴的方向上的距离。再例如，若第一地图为三维栅格地图，则横向距离可以为平行于坐标系中XOY平面的方向上的距离，纵向距离可以为垂直于坐标系中XOY平面的方向上的距离。其中，坐标系可以为世界坐标系，或为以终端为原点的坐标系等。
第二方面，本申请实施例提供一种定位方法，该方法可以由终端(如车辆，车载设备或手机等)执行，也可以由终端中的芯片或芯片系统执行。下面以执行主体是终端为例进行描述。该方法包括：终端获取其所处环境的环境信息，根据环境信息，确定第三地图，该第三地图是根据第二地图生成的，第二地图中包括第一栅格和第三栅格，第一栅格的特征值大于或等于第一阈值，第三栅格的特征值大于第二阈值、且小于第一栅格的特征值，第三栅格的特征值是根据第一栅格的特征值确定的，其中，第一阈值大于第二阈值，特征值为定位参考对象占用栅格的概率，定位参考对象用于确定终端的定位信息；终端将环境 信息与第三地图进行匹配，得到终端的定位信息。
在一种可能的设计中，第一栅格与第三栅格之间的距离可以小于或等于第一距离。
在一种可能的设计中，第一栅格与第三栅格之间的距离越大，第三栅格的特征值越小。
在一种可能的设计中，该方法还可以包括：终端向网络设备发送第一请求消息，第一请求消息用于请求获取第三地图；终端接收来自网络设备的第一响应消息，第一响应消息包括所述第三地图。
在一种可能的设计中，该第一栅格与第三栅格之间的距离可以包括横向距离、纵向距离或以第一栅格为中心向四周辐射的半径值中的任一种。
第三方面，本申请实施例提供一种定位方法，该方法可以由终端(如车辆，车载设备或手机等)执行，也可以由终端中的芯片或芯片系统执行。下面以执行主体是终端为例进行描述。该方法包括：终端获取其所处环境的环境信息，根据环境信息，获取第一地图，第一地图中包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，其中，第一阈值大于第二阈值，特征值为定位参考对象占用栅格的概率，定位参考对象用于确定终端的定位信息；终端根据第一栅格的特征值，更新第二栅格的特征值以使得更新后的第二栅格的特征值大于第二阈值、且小于第一栅格的特征值，得到第二地图，并根据第二地图生成第三地图；终端将环境信息与第三地图进行匹配，得到终端的定位信息。
在一种可能的设计中，第一栅格与第二栅格之间的距离可以小于或等于第一距离。
在一种可能的设计中，第一栅格与第二栅格之间的距离越大，更新后的第二栅格的特征值越小。
在一种可能的设计中，根据环境信息，获取第一地图，包括：根据环境信息，获取第四地图，该第四地图中包括第一栅格和第四栅格，第四栅格的特征值小于或等于第二阈值；对第四地图进行划分，可以得到第一地图和第七地图，第七地图中包括第五地图和/或第六地图，该第五地图中仅包括第一栅格，该第六地图中仅包括第四栅格；根据第二地图，生成第三地图，包括：根据第二地图和第七地图，生成第三地图。
在一种可能的设计中，该第一地图可以为二维栅格地图，或者为三维栅格地图。
在一种可能的设计中，该第一栅格与第二栅格之间的距离可以包括横向距离、纵向距离或以第一栅格为中心向四周辐射的半径值等中的任一种。
第四方面，本申请实施例提供一种定位地图生成装置，该装置包括：获取单元，用于获取第一地图，第一地图中包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，其中，第一阈值大于第二阈值，特征值为定位参考对象占据栅格的概率，定位参考对象用于确定终端的定位信息；更新单元，用于根据第一栅格的特征值，更新第二栅格的特征值以使得更新后的第二栅格的特征值大于第二阈值且小于第一栅格的特征值，得到第二地图；地图生成单元，用于根据第二地图生成第三地图。
在一种可能的设计中，第一栅格与第二栅格之间的距离可以小于或等于第一距离。
在一种可能的设计中，第一栅格与第二栅格之间的距离越大，更新后的第二栅格的特征值越小。
在一种可能的设计中，该装置还可以包括收发单元，该收发单元用于接收来自终端的第一请求消息，第一请求消息用于请求获取所述第三地图；以及向终端发送第一响应消息，第一响应消息中包括所述第三地图。
在一种可能的设计中，获取单元具体用于：获取第四地图，该第四地图中包括第一栅格和第四栅格，第四栅格的特征值小于或等于第二阈值；以及对第四地图进行划分，可以得到第一地图和第七地图，第七地图中包括第五地图和/或第六地图，该第五地图中仅包括第一栅格，该第六地图中仅包括第四栅格；地图生成单元具体用于：根据第二地图和第七地图，生成第三地图。
在一种可能的设计中，该第一地图可以为二维栅格地图，或者为三维栅格地图。
在一种可能的设计中，该第一栅格与第二栅格之间的距离可以包括横向距离、纵向距离或以第一栅格为中心向四周辐射的半径值中的任一种。
第五方面，本申请实施例提供一种定位装置，该装置包括：获取单元，用于获取其所处环境的环境信息；定位单元，用于根据环境信息，确定第三地图，该第三地图是根据第二地图生成的，第二地图中包括第一栅格和第三栅格，第一栅格的特征值大于或等于第一阈值，第三栅格的特征值大于第二阈值、且小于第一栅格的特征值，第三栅格的特征值是根据第一栅格的特征值确定的，其中，第一阈值大于第二阈值，特征值为定位参考对象占用栅格的概率，定位参考对象用于确定终端的定位信息；以及将环境信息与第三地图进行匹配，得到终端的定位信息。
在一种可能的设计中，第一栅格与第三栅格之间的距离可以小于或等于第一距离。
在一种可能的设计中，第一栅格与第三栅格之间的距离越大，第三栅格的特征值越小。
在一种可能的设计中，该装置还可以包括收发单元，该收发单元，用于向网络设备发送第一请求消息，第一请求消息用于请求获取第三地图；以及接收来自网络设备的第一响应消息，第一响应消息包括所述第三地图。
在一种可能的设计中，该第一栅格与第三栅格之间的距离可以包括横向距离、纵向距离或以第一栅格为中心向四周辐射的半径值等中的任一种。
第六方面，本申请实施例提供另一种定位装置，该装置包括：获取单元，用于获取其所处环境的环境信息，以及根据环境信息，获取第一地图，第一地图中包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，其中，第一阈值大于第二阈值，特征值为定位参考对象占用栅格的概率，定位参考对象用于确定终端的定位信息；更新单元，用于根据第一栅格的特征值，更新第二栅格的特征值以使得更新后的第二栅格的特征值大于第二阈值且小于第一栅格的特征值，得到第二地图；地图生成单元，用于根据第二地图生成第三地图；定位单元，用于将环境信息与第三地图进行匹配，得到终端的定位信息。
在一种可能的设计中，第一栅格与第二栅格之间的距离可以小于或等于第一距离。
在一种可能的设计中，第一栅格与第二栅格之间的距离越大，更新后的第二栅格的特征值越小。
在一种可能的设计中，获取单元具体用于：根据环境信息，获取第四地图，该第四地图中包括第一栅格和第四栅格，第四栅格的特征值小于或等于第二阈值；以及对第四地图 进行划分，可以得到第一地图和第七地图，第七地图中包括第五地图和/或第六地图，该第五地图中仅包括第一栅格，该第六地图中仅包括第四栅格；地图生成单元具体用于：根据第二地图和第七地图，生成第三地图。
在一种可能的设计中，该第一地图可以为二维栅格地图，或者为三维栅格地图。
在一种可能的设计中，该第一栅格与第二栅格之间的距离可以包括横向距离、纵向距离或以第一栅格为中心向四周辐射的半径值等中的任一种。
第七方面，本申请实施例提供一种通信装置，包括处理器和存储器，其中所述存储器用于存储计算机程序或指令，所述处理器用于调用所述存储器中存储的计算机程序或指令，执行上述第一方面或第一方面的任一种可能的设计，或者第二方面或第二方面的任一种可能的设计，或者第三方面或第三方面的任一种可能的设计中所述的方法。
第八方面，本申请实施例提供一种计算机可读存储介质，所述计算机可读存储介质具有用于执行上述第一方面或第一方面的任一种可能的设计，或者第二方面或第二方面的任一种可能的设计，或者第三方面或第三方面的任一种可能的设计中所述的方法的计算机程序或指令。
第九方面，本申请实施例还提供一种计算机程序产品，包括计算机程序或指令，当所述计算机程序或指令被执行时，可以实现上述第一方面或第一方面的任一种可能的设计，或者第二方面或第二方面的任一种可能的设计，或者第三方面或第三方面的任一种可能的设计中所述的方法。
第十方面，本申请还提供一种芯片，所述芯片用于实现上述第一方面或第一方面的任一种可能的设计，或者第二方面或第二方面的任一种可能的设计，或者第三方面或第三方面的任一种可能的设计中所述的方法。
关于第二方面至第十方面或各种可能的设计所能达到的技术效果，可参考对于第一方面或第一方面相应的设计所能达到的技术效果的介绍，这里不再重复赘述。
附图说明
图1为本申请实施例适应的一种应用场景的示意图；
图2为本申请实施例中定位参考对象发生变化的一种示意图；
图3为本申请实施例中定位参考对象发生变化的另一种示意图；
图4为本申请实施例提供的一种定位方法的流程示意图；
图5为本申请实施例提供的第一地图的一种示意图；
图6A为本申请实施例提供的第一地图的另一种示意图；
图6B为本申请实施例提供的第一地图的另一种示意图；
图7A为本申请实施例提供的第一栅格与第二栅格之间的位置关系的一种示意图；
图7B为本申请实施例提供的第一栅格与第二栅格之间的位置关系的另一种示意图；
图7C为本申请实施例提供的第一栅格与第二栅格之间的位置关系的另一种示意图；
图7D为本申请实施例提供的第一栅格与第二栅格之间的位置关系的另一种示意图；
图8A为本申请实施例提供的第一栅格与第二栅格之间的位置关系的另一种示意图；
图8B为本申请实施例提供的第一栅格与第二栅格之间的位置关系的另一种示意图；
图8C为本申请实施例提供的第一栅格与第二栅格之间的位置关系的另一种示意图；
图9为本申请实施例提供的第二地图的一种示意图；
图10A为本申请实施例提供的特征投影到三维栅格地图的示意图；
图10B为本申请实施例提供的特征投影到第一地图的示意图；
图10C为本申请实施例提供的特征投影到第三地图的示意图；
图11为本申请实施例提供的另一种定位方法的流程示意图；
图12为本申请实施例提供的定位地图生成装置的一种结构示意图；
图13为本申请实施例提供的定位装置的一种结构示意图；
图14为本申请实施例提供的定位装置的另一种结构示意图；
图15为本申请实施例提供的通信装置的一种结构示意图；
图16为本申请实施例提供的通信装置的另一种结构示意图；
图17为本申请实施例提供的四个子地图的一种示意图；
图18为本申请实施例提供的四个子地图的另一种示意图。
具体实施方式
为了便于理解，下面先对本申请实施例涉及到的专用概念和名词进行解释。
(1)网络设备，本申请实施例涉及的网络设备可以包括但不限于单服务器，服务器集群，或者云端服务器等提供地图构建能力和存储能力的装置。例如，终端中安装应用程序，网络设备可以是该应用程序对应的服务器。这里的应用程序可以是与定位相关的应用程序。例如应用程序是定位(application，APP)，那么服务器是该定位APP对应的服务器。
本申请实施例中，用于实现网络设备的功能的装置可以是网络设备本身，也可以是能够支持网络设备实现该功能的装置，例如芯片系统，该装置可以被安装在网络设备中。本申请实施例中，芯片系统可以由芯片构成，也可以包括芯片和其他分立器件。下文中，以用于实现网络设备的功能的装置是网络设备为例进行描述。
(2)终端，本申请实施例涉及的终端可以包括但不限于手机、平板电脑、可穿戴设备(如眼镜、手套、手表、手环、服饰及鞋等)、车辆、车载设备(或者称为车载终端)、增强现实(augmented reality，AR)/虚拟现实(virtual reality，VR)设备、笔记本电脑、超级移动个人计算机(ultra-mobile personal computer，UMPC)、上网本或个人数字助理(personal digital assistant，PDA)等需要定位的移动设备。本申请实施例对终端的具体类型不作任何限制。
本申请实施例中，用于实现终端的功能的装置可以是终端本身，也可以是能够支持终端实现该功能的装置，例如芯片系统，该装置可以被安装在终端中。本申请实施例中，芯片系统可以由芯片构成，也可以包括芯片和其他分立器件。下文中，以用于实现终端的功能的装置是终端为例进行描述。
(3)先验地图，本申请实施例涉及的先验地图可以为终端定位时的先验知识，可以全面地反映道路状况，辅助终端获取定位信息。例如，终端可以将当前的环境信息与先验地图进行匹配，得到自身在先验地图中的位置。再例如，该先验地图可以是精度为厘米级的高精度地图。
(4)栅格地图可以指将环境划分成一系列的栅格的地图，其中每一个栅格可以包括一个可能的特征值。该特征值可以是定位参考对象占据栅格的概率，其取值可以是0～1。例如，栅格的特征值为1可以表示该栅格被定位参考对象占据。例如，栅格的特征值为0 可以表示该栅格没有被定位参考对象占据。栅格的特征值越大，则该栅格被定位参考对象占据的概率越大，该栅格对定位的影响也就越大。
(5)定位参考对象，本申请实施例涉及的定位参考对象可以包括但不限于车道、树木、建筑物、路边地标或花坛等有助于定位的对象。例如，地图服务器可以接收来自测量设备采集的环境信息，从环境信息中提取定位参考对象的特征，然后基于定位参考对象的特征构建先验地图。再例如，车辆可以采集当前所处的环境信息，从环境信息中提取定位参考对象的特征，然后将定位参考对象的特征与先验地图中定位参考对象的特征进行匹配，得到车辆的位置信息。
(6)本申请实施例中“多个”是指两个或两个以上，鉴于此，本申请实施例中也可以将“多个”理解为“至少两个”。“至少一个”，可理解为一个或多个，例如理解为一个、两个或更多个。例如，包括至少一个，是指包括一个、两个或更多个，而且不限制包括的是哪几个，例如，包括A、B和C中的至少一个，那么包括的可以是A、B、C、A和B、A和C、B和C、或A和B和C。“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这三种情况。另外，字符“/”，如无特殊说明，一般表示前后关联对象是一种“或”的关系。
除非有相反的说明，本申请实施例提及“第一”、“第二”、“第三”等序数词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。
下面结合附图进一步介绍本申请实施例提供的定位地图生成方法及定位方法。
图1所示为本申请实施例适用的一种应用场景的示意图。如图1所示的车道行驶方向的指示信息，包括4个车道，其中左侧两个车道的行驶方向一致，右侧两个车道的车辆行驶方向一致。车辆可以是智能车或非智能车，本申请实施例对此不做限定。车辆上设置有传感器，该传感器用于探测车辆周边的目标，例如，绿化带中的树木、路边地标、车道边界或车道线等目标，其中，传感器可以包括但不限定于激光雷达、毫米波雷达或相机等。该车辆可以设置一种或多种传感器，每种传感器的个数可以为一个或多个。传感器可以安装在车辆的顶部、具体可以设置在车辆顶部的中间位置，本申请实施例对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，可以基于车辆间无线通信技术(例如，vehicle to vehicle(V2V))实现车辆与车辆之间的通信。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实现车辆与智能设备(如支持定位功能的智能手机或移动设备)之间的通信。
示例的，图1所示的应用场景中还可以包括地图服务器，该地图服务器可以由云端的服务器或虚拟机实现。以图1所示的场景中传感器为激光雷达传感器为例，车辆的传感器的预设区域如图1中虚线框圆圈所示，以车辆为中心，以预设距离为半径的区域。该预设距离可以是小于或等于车辆所发出的激光雷达信号的覆盖范围的半径的一个值。例如，在构建先验地图时，车辆(或其它带有传感器的测量设备)可以通过传感器采集预设范围内的目标的激光雷达数据，然后将采集到的激光雷达数据发送给地图服务器，从而，地图服务器可以根据该激光雷达数据构建先验地图。进一步，地图服务器还可以将先验地图发送给车辆。再例如，在定位时，车辆(或其它带有传感器的待定位设备)可以通过传感器采集预设范围内的目标的激光雷达数据，然后将采集到的激光雷达数据与先验地图进行匹配， 从而，车辆(或其它带有传感器的待定位设备)可以得到自身在先验地图中的位置和位姿。进一步，车辆还可以根据自身在先验地图中的位置和位姿进行路径规划、决策等。
示例的，图1所示的应用场景中地图服务器的个数可以为一个或多个。例如，两个地图服务器可以分别为地图服务器1和地图服务器2。其中，地图服务器1可以构建多个区域的先验地图，该多个区域可以包括地图服务器2覆盖的区域，从而，地图服务器2可以通过与地图服务器1进行交互获取其覆盖区域的先验地图并存储。进一步地，地图服务器2还可以与车辆进行交互，将其覆盖区域的先验地图发送给车辆，以使得车辆可以在地图服务器2的覆盖区域进行定位。可选的，地图服务器1也可以与车辆进行交互，将该多个区域的先验地图发送给车辆，以使得车辆可以在该多个区域内进行定位。再例如，地图服务器2也可以构建其覆盖区域的先验地图并存储。
先验地图作为车辆进行定位的先验知识，需要对环境的描述是完备的、且能够全面的反映环境中的有助于定位的信息，因此带有传感器的测量设备需要采集大量的定位参考对象的特征信息来构建先验地图。例如，该定位参考对象可以包括但不限定于树木、道路、建筑或路边地标等。例如，这些特征信息可以包括道路数据(如车道线的位置、类型、宽度、坡度或曲率等车道信息)和车道周边的细节信息(如交通标志、交通信号灯、路边地标、道路边缘类型、防护栏或树木等细节信息)。考虑大量特征信息的获取以及处理需要较多的人力和物力开销，因此先验地图的构建周期不会很频繁，这就要求用于构建先验地图的定位参考对象在一段时间内不会发生变化，例如位置变化、形状变化或姿态变化等。
但随着外在因素(如天气变化或季节更换等)的影响，定位参考对象并不是绝对不变的。当定位参考对象发生变化时，车辆实时采集的定位参考对象的特征与先验地图中的该定位参考对象的特征无法完全对应，导致两者的匹配结果存在误差，难以保证定位信息的准确性。例如，风吹动树木，树木的枝叶发生晃动，在此情况下，车辆采集到的树木的特征与先验地图中的该树木的特征无法完全对应，如图2所示，实线部分可为构建先验地图时测量设备所采集的树木的位置，虚线部分可为定位时车辆所采集的树木的位置，显然两者无法完全对应。再例如，随着季节更换树木的树冠会发生变化，在此情况下，车辆采集到的树木的形状与先验地图中该树木的形状也是无法完全对应的，如图3所示，实线部分可为构建先验地图时测量设备所采集的树木的形状，虚线部分可为定位时车辆所采集的树木的形状，显然两者无法完全对应。另外，根据制图标准的要求，在构建先验地图的过程需要对地图进行加偏处理，例如，每100米加偏20厘米。相应的，在定位时车辆需要对采集的特征进行相应的加偏处理或对先验地图进行相应的减偏处理，加偏处理或减偏处理过程中难免会引入误差，也会导致定位结果不准确。可见，目前的先验地图对误差的兼容能力较差，难以保证定位的准确性。
鉴于此，本申请实施例提供一种定位地图生成方法，该方法中，第一地图包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，根据第一栅格的特征值更新第二栅格的特征值，使得更新后的第二栅格的特征值大于第二阈值但小于第一栅格的特征值，然后根据更新后的第二栅格生成第三地图。更新后的第二栅格的特征值大于第二阈值但小于第一栅格的特征值，意味着增加了定位参考对象占据第二栅格的概率，使得更新后的第二栅格对定位的影响也相应增大了，但更新后的第二栅格对定位的影响未超过第一栅格对定位的影响，从而根据该更新后的第二栅格生成的第三地图能够很好地兼容定位过程中因动态特征、加偏运算或减偏运算等引起误差，同 时还保障了原有特征对定位的影响，避免引入额外的误差，能够提高定位的鲁棒性。
图4所示为本申请实施例提供的一种定位方法的流程示意图。网络设备生成第三地图，将该第三地图发送给终端，终端接收第三地图，并基于该第三地图进行定位。该方法可以应用于图1所示的通信系统。下面以该方法应用于图1所示的通信系统，网络设备为地图服务器，终端为车辆为例，对该方法进行介绍。
S401：地图服务器获取第四地图。
作为一个示例，地图服务器可以按照以下方式获取第四地图：A1，具备传感器的测量设备采集环境信息，并将环境信息发送给地图服务器，地图服务器接收环境信息；A2，地图服务器从环境信息中提取定位参考对象的特征，并基于定位参考对象的特征构建先验地图，第四地图可以是该先验地图的部分或全部。其中，测量设备的传感器可以包括但不限于相机、激光雷达传感器或毫米波雷达中的至少一种。示例的，第四地图还可以是精度为厘米级的高精度地图。
作为一个示例，第四地图可以包括第一栅格和第四栅格，第一栅格的特征值大于或等于第一阈值，第四栅格的特征值小于或等于第二阈值。其中，第一阈值可以大于第二阈值。该第一阈值、第二阈值可以是预先定义的，例如，第一阈值为1，第二阈值为0。该特征值可以为定位参考对象占据栅格的概率，定位参考对象可以用于确定车辆的定位信息。
作为一个示例，第四地图可以是三维栅格地图，也可以是二维栅格地图，还可以是概率地图等，本申请实施例对第四地图的具体形式不作限定。
S402：地图服务器对第四地图进行划分得到第一地图。
例如，地图服务器对第四地图进行划分可以得到一个或多个第一地图。该第一地图可以包括第一栅格和第二栅格。其中，第二栅格的特征值小于或等于第二阈值。例如，第二栅格可以是第一地图中的部分或全部的第四栅格。例如，如果第二栅格是第一地图中的部分的第四栅格，则第一地图可以包括第一栅格、第二栅格和第四栅格。
作为一个示例，如果第四地图是二维栅格地图或三维栅格地图，则地图服务器可以按照均分的方式将第四地图划分为多个子地图，得到一个或多个第一地图。如果第四地图是概率地图，则地图服务器可以先将第四地图转换为二维栅格地图(或三维栅格地图)，然后按照均分的方式将转换得到的二维栅格地图(或三维栅格地图)划分为多个子地图，得到一个或多个第一地图。其中，第一地图可以为二维栅格地图，或者为三维栅格地图，本申请实施例对此并不限定。
例如，第四地图是二维栅格地图，第四地图可以包括100个栅格，地图服务器可以将第四地图均分为4个子地图，得到2个第一地图，其中，每个第一地图包括25个栅格，如图5所示。再例如，第四地图是三维栅格地图，第四地图可以包括10层，每层包括100个栅格，地图服务器可以将第四地图均分为4个子地图，得到1个第一地图，如图6A所示，图6A中的黑粗线表示第一栅格，其余为第四栅格。其中，图6A所示的第一地图包括5层，每层包括25个栅格，从上往下，该第一地图的第一层、第二层以及第三层皆包括一个第一栅格，该第一地图的第四层和第五层皆包括两个第一栅格，如图6B所示。
示例的，第一阈值为1，第二阈值为0，若将图6B所示的第一地图的每一层的栅格的特征值用矩阵表示，则第一地图中从上往下的每一层的栅格的特征值如下所示：
Figure PCTCN2021090752-appb-000001
Figure PCTCN2021090752-appb-000002
其中，A i表示第一地图中从上往下的第i层的栅格的特征值，i为大于或等于1、且小于或等于5的整数。
作为另一个示例，第二栅格可以是部分的第四栅格。例如，第二栅格可以是第四栅格中与第一栅格之间的距离小于或等于第一距离的栅格，也即是第二栅格与第一栅格之间的距离小于或等于第一距离。也就是说，只更新与第一栅格之间的距离小于或等于第一距离的栅格可以避免引入额外的误差。
示例的，第二栅格与第一栅格之间的距离可以是横向距离，或者是纵向距离，或者是横向距离和纵向距离，或者是以第一栅格为中心向四周辐射的距离等。在第一地图为三维栅格地图时，该第一栅格与第二栅格之间的距离还可以是沿横向方向上以第一栅格为中心向四周辐射的半径值，或者是沿纵向方向上以第一栅格为中心向四周辐射的半径值，或者是沿横向方向上和纵向方向上以第一栅格为中心向四周辐射的半径值等。例如，如果第一地图二维栅格地图，则横向距离可以指平行于坐标系中X轴的方向上的距离，纵向距离可以指垂直于坐标中X轴的方向上的距离。再例如，如果第一地图为三维地图，则横向距离可以是平行于坐标系中XOY平面的方向上的距离，纵向距离可以指垂直于坐标系中XOY平面的方向上的距离。其中，坐标系可以为世界坐标系，或为以终端为原点的坐标系等，本申请实施例对比并不限定。
以第一地图为二维栅格地图，第一地图包括25个栅格，第一距离为大于两个栅格且小于三个栅格的距离为例，若第一栅格与第二栅格之间距离为横向距离，则第一地图中第四行的第一个栅格、第三个栅格和第四个栅格为第二栅格，如图7A所示。若第一栅格与第二栅格之间的距离为纵向距离，则第一地图中第二列的第二个栅格、第三个栅格和第五个栅格为第二栅格，如图7B所示。若第一栅格与第二栅格之间的距离包括横向距离和纵向距离，则第一地图中第四行的第一个栅格、第三个栅格和第四个栅格，以及第二列的第二个栅格、第三个栅格和第五个栅格为第二栅格，如图7C所示。若第一栅格与第二栅格之间的距离为以第一栅格为中心向四周辐射的半径值，则第一地图中第二行、第三行和第五行中的第一个栅格、第二个栅格、第三个栅格和第四个栅格，以及第四行中的第一个栅格、第三个栅格和第四个栅格为第二栅格，如图7D所示。
以第一地图为三维栅格，该第一地图包括5层，每一层包括25个栅格，该第一地图从上往下的第二层包括一个第一栅格，第一距离为大于两个栅格且小于三个栅格的距离为例，若第一栅格与第二栅格之间的距离为沿横向方向上以第一栅格为中心向四周辐射的半 径值，则第一地图中从上往下的第二层中的第二行、第三行和第五行中的第一个栅格、第二个栅格、第三个栅格和第四个栅格，以及第四行中的第一个栅格、第三个栅格和第四个栅格为第二栅格，如图8A所示。若第一栅格与第二栅格之间的距离为沿纵向方向上以第一栅格为中心向四周辐射的半径值，则第一地图中从上往下的第一层、第三层、第四层中第二列的第二个栅格、第三个栅格、第四个栅格和第五个栅格，以及第二层中第二列的第二个栅格、第三个栅格和第五个栅格为第二栅格，如图8B所示。若第一栅格与第二栅格之间的距离为以第一栅格为中心向四周辐射的半径值，则第一地图中从上往下的第一层、第三层、第四层中第二行、第三行、第四行和第五行的第一个栅格、第二个栅格、第三个栅格和第四个栅格，以及第二层中第二行、第三行和第五行的第一个栅格、第二个栅格、第三个栅格和第四个栅格，以及第二层中第四行的第一个栅格、第三个栅格和第四个栅格为第二栅格，如图8C所示。
在一种可能的实施方式中，地图服务器对第四地图划分可以得到第一地图和第七地图。其中，第七地图中包括第五地图和/或第六地图，第五地图可以仅包括第一栅格，如图5中第四地图的左下角的子地图所示，第六地图可以仅包括第四栅格，如图5中第四地图的右下角的子地图所示。也即是，地图服务器对第四地图进行划分可以得到第一地图和第五地图，或者地图服务器对第四地图进行划分可以得到第一地图和第六地图，或者地图服务器对第四地图进行划分可以得到第一地图、第五地图和第六地图。
S403：地图服务器根据第一栅格的特征值，更新第二栅格的特征值，得到第二地图。
示例的，如果第一地图为二维栅格地图，则地图服务器可以根据第一栅格的特征值更新第二栅格的特征值，得到第二地图。或者，如果第一地图为三维栅格地图，则地图服务器可以根据每一层中第一栅格的特征值更新第二栅格的特征值，得到第二地图。例如，地图服务器可以采用形态学膨胀算法、高斯平滑算法或线性平滑算法等算法中的至少一种更新第二栅格的特征值，得到第二地图，本申请实施例对更新算法不作限定。其中，第二地图可以包括第一栅格和第三栅格，第三栅格又可以称为更新后的第二栅格，第三栅格的特征值大于第二阈值。为了表述方便，下文中可将第二地图中的第三栅格称为更新后的第二栅格。可选的，第二地图还可以包括第四栅格。
作为一个示例，更新后的第二栅格的特征值可以小于第一栅格的特征值。地图服务器根据第一栅格的特征值对第二栅格的特征值进行更新，使得更新后的第二栅格的特征值大于第二阈值但小于第一栅格的特征值，意味着在提高第二栅格对定位的影响的同时还要使得更新后的第二栅格对定位的影响小于第一栅格对定位的影响，保证了原有的定位特征的影响，从而在提高先验地图对误差的兼容能力的同时避免引入额外的误差，可以提高定位的鲁棒性。
作为另一示例，地图服务器还可以根据第一栅格与第二栅格之间的距离，更新第二栅格的特征值。例如，第一栅格与第二栅格之间的距离越大，更新后的第二栅格的特征值越小，这样随着第一栅格与第二栅格之间的距离的增大，更新后的第二栅格对定位的影响逐渐减小，在兼容误差的同时可以避免引入额外的误差，提高定位的鲁棒性。例如，如果多个第二栅格与同一个第一栅格之间的距离相同，则更新后的该多个第二栅格的特征值也相同。再例如，如果第二栅格与至少一个第一栅格之间的距离皆小于或等于第一距离，则更新后的第二栅格的特征值可以由该至少一个第一栅格中、与第二栅格之间的距离最小的第一栅格的特征值确定。
以图6B所示的第一地图为例，第一距离为大于两个栅格且小于三个栅格的距离，第一栅格与第二栅格之间的距离为以第一栅格为中心向四周辐射的半径值，第一阈值为1，第二阈值为0，地图服务器根据每一层中的第一栅格更新第二栅格的特征值，得到第二地图，第二地图中从上往下的每一层的栅格的特征值如图9所示。若第二地图中每一层的栅格的特征值用矩阵表示，则从上往下第二地图中的每一层的栅格的特征值如下所示：
Figure PCTCN2021090752-appb-000003
Figure PCTCN2021090752-appb-000004
其中，B i表示第二地图中从上往下的第i层的栅格的特征值，i为大于或等于1、且小于或等于5的整数。
S404：地图服务器根据第二地图，生成第三地图。
示例的，如果地图服务器将第四地图划分为至少一个第一地图，则地图服务器可以根据至少一个第二地图生成第三地图。或者，如果地图服务器将第四地图划分为至少一个第一地图和至少一个第五地图，则地图服务器可以根据至少一个第二地图和至少一个第五地图生成第三地图。或者如果地图服务器将第四地图划分为至少一个第一地图和至少一个第六地图，则地图服务器可以根据至少一个第二地图和至少一个第六地图生成第三地图。或者如果地图服务器将第四地图划分为至少一个第一地图、至少一个第五地图和至少一个第六地图，则地图服务器可以根据至少一个第二地图、至少一个第五地图和至少一个第六地图生成第三地图。
作为一个示例，如果地图服务器将第四地图划分为多个子地图，则在步骤S404中地图服务器可以根据至少两个子地图生成第三地图，该至少两个子地图中包括至少一个第二地图。例如，地图服务器可以确定该至少两个子地图中相邻的第八地图和第九地图；根据第八地图中的第五栅格的特征值，更新第九地图中的第六栅格的特征值，得到第十地图，其中，更新后的第六栅格的特征值大于更新前该第六栅格的特征值、且小于第八地图中的第五栅格的特征值；地图服务器可以根据第十地图和第八地图生成第三地图。其中，第八地图中包括第五栅格，第九地图中包括第六栅格，第五栅格的特征值大于或等于第一阈值，第六栅格的特征值小于第一阈值、且第六栅格与第五栅格之间的距离小于或等于第一距离。例如，若第八地图为第二地图，则第九地图可以为第二地图，或为第五地图，或为第六地图；若第八地图为第五地图，则第九地图可以为第六地图。采用这种方式，可以根据一个子地图中的第五栅格的特征值更新相邻的另一个子地图中的第六栅格的特征值，以提高第六栅格对定位的影响，从而能够更好地兼容定位过程中因动态特征、加偏运算或减偏运算等引起误差，进一步提高定位的鲁棒性。
示例的，第五栅格与第六栅格之间的距离可以是横向距离，或者是纵向距离，或者是横向距离和纵向距离，或者是以第五栅格为中心向四周辐射的距离等。在子地图为三维栅格地图时，该第五栅格与第六栅格之间的距离还可以是沿横向方向上以第五栅格为中心向四周辐射的半径值，或者是沿纵向方向上以第五栅格为中心向四周辐射的半径值，或者是沿横向方向上和纵向方向上以第五栅格为中心向四周辐射的半径值等。
以图5所示的第四地图为例，第一距离为大于两个栅格且小于三个栅格的距离，第五栅格与第六栅格之间的距离为以第五栅格为中心向四周辐射的半径值，第一阈值为1，第二阈值为0，地图服务器对第一地图中的第二栅格的特征值进行更新后，得到两个第二地图、一个第五地图和一个第六地图，该四个子地图中栅格的特征值如图17所示。进一步，地图服务器可以根据一个子地图中的第五栅格的特征值更新其相邻的子地图中第六栅格的特征值，更新后各子地图中栅格的特征值如图18所示。
可选的，地图服务器生成第三地图后，还可以接收来自车辆的第一请求消息，该第一请求消息用于获取第三地图，即地图服务器还可以执行步骤S405和步骤S406所示的内容。或者，地图服务器在生成第三地图后，可以将第三地图发送给车辆，车辆接收该第三地图并存储。
S405：车辆向地图服务器发送第一请求消息，地图服务器接收第一请求消息。
其中，第一请求消息用于获取第三地图。例如，车主通过操作车辆安装的与地图服务器关联的应用程序，可以触发车辆向地图服务器发送第一请求消息，地图服务器接收该第一请求消息。
S406：地图服务器向车辆发送第一响应消息，车辆接收第一响应消息。
其中，第一响应消息中包括第三地图。
S407：车辆获取所处环境的环境信息。
示例的，车辆可以通过相机、激光雷达或毫米波雷达等传感器中的至少一个采集当前所处环境的环境信息。以传感器为相机为例，该环境信息可以是该相机拍摄到的图像数据和/或视频数据。以传感器为激光雷达为例，该环境信息可以是该激光雷达探测到的雷达数据。
S408：车辆将环境信息与第三地图进行匹配，得到车辆的定位信息。
示例的，车辆可以从环境信息中提取定位参考对象的特征，然后将定位参考对象的特征与第三地图中的定位参考对象的特征进行匹配，可以得到车辆在第三地图中的位置信息。具体的，车辆可以通过卡尔曼滤波算法或粒子滤波算法确定车辆的定位信息。
以粒子滤波为例，步骤S408的具体实现过程如下：B1、车辆根据环境信息提取定位参考对象的特征；B2、车辆根据环境信息生成粒子集，其中，粒子集中包括至少一个粒子，该至少一个粒子中的每一个粒子可以表示车辆在第三地图中的一个可能的位姿；B3、车辆将定位参考对象的特征通过每个粒子投影到第三地图中，得到定位参考对象的特征在第三地图中的投影位置(即占据的栅格)；B4、车辆可以将定位参考对象的特征在第三地图中的投影位置的特征值进行累加，得到每个粒子的评分；B5、车辆根据每个粒子的评分可以得到该车辆在第三地图中的位置信息。通常粒子的评分越高，则该粒子最有可能表示车辆在第三地图中的位姿。
例如，一个粒子的评分可以根据如下公式确定：
Figure PCTCN2021090752-appb-000005
其中，w可表示一个粒子的评分，x,y,z可为特征通过粒子投影到第三地图中的投影位置，g(·)可表示第三地图中栅格的特征值。
以定位参考对象为树木为例，地图服务器提取树木的7个特征，根据该7个特征构建三维栅格地图，从上往下，该7个特征在三维栅格地图中的位置分别为该三维栅格地图的第一层第二行的第二个栅格，第二层第二行的第二个栅格，第三层第二行的第二个栅格，第四层第二行的第二个栅格和第三行的第四个栅格，第五层第二行的第二个栅格和第三行的第四个栅格，如图6B所示。在风的吹动下，树枝晃动发生位移，在此情况下，地图服务器接收来自车辆的环境信息，根据环境信息提取到树木的7个特征，将该7个特征通过粒子1投影到图6B所示的三维栅格地图中，从上往下，该7个特征在三维栅格地图中的投影位置分别为该三维栅格地图的第一层第一行的第二个栅格，第二层第一行的第二个栅格，第三层第一行的第二个栅格，第四层第一行的第二个栅格和第二行的第四个栅格，第五层第一行的第二个栅格和第二行的第四个栅格，如图10A所示。如果将该7个特征通过粒子1投影到第一地图中，如图10B所示，则该粒子1的评分为w＝0+0+0+0+0+0+0＝0。如果将该7个特征通过粒子1投影到第三地图中，如图10C所示，则该粒子1的评分为w＝0.8+0.8+0.8+0.8+0.8+0.8+0.8＝5.6。
在定位参考对象没有发生变化时，定位参考对象的特征通过粒子应该全部投影到第一栅格中，即车辆实时采集的定位参考对象的特征与先验地图中该定位参考对象的特征相匹配。在定位参考对象发生变化或因加偏/减偏运算引入误差时，定位参考对象的特征也相应地发生了偏差，从而定位参考对象的特征通过粒子不能全部投影到第一栅格中，而是投影到第一栅格的邻近栅格中，第一栅格的邻近栅格可能是第四栅格。如图10B所示，7个特征通过粒子1的投影位置仅偏离了正确位置(即第一栅格)一个栅格的距离，但全部投影到该正确位置周边的第四栅格中，使得粒子1的评分为0，极大降低了粒子1对定位的影响，也就是说，当定位参考对象发生变化或因加偏/减偏运算引入误差时，现有的先验地图会导致正确位置周边存在粒子评分骤降的问题，极大降低了粒子对定位的影响，从而导致定位不准确。从图10B和图10C可以看出，第三地图可以兼容因定位参考对象发生变化或因加偏/减偏运算引入的误差，能够有效减少因正确位置周边的粒子评分骤降导致定位不准确的影响。
本申请的上述实施例中，地图服务器获取第一地图，第一地图包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，根据第一栅格的特征值更新第二栅格的特征值，使得更新后的第二栅格的特征值大于第二阈值且小于第一栅格的特征值，并根据更新后的第二栅格生成第三地图。更新后的第二栅格的特征值大于第二阈值，意味着增加了定位参考对象占据第二栅格的概率，使得更新后的第二栅格对定位的影响也相应增大了，从而根据该更新后的第二栅格生成的第三地图能够很好地兼容定位过程中因动态特征、加偏运算或减偏运算等引起误差，同时还保障了原有特征对定位的影响，避免引入额外的误差，能够提高定位的鲁棒性。例如，在结合粒子滤波时，第三地图可以减少正确定位周边可能存在的粒子评分骤降的问题，从而有效减少因粒子评分骤降导致定位不准确的影响。
图11所示为本申请实施例提供的另一种定位方法的流程示意图。该方法可以应用于图 1所示的通信系统。下面以该方法应用于图1所示的通信系统，网络设备为地图服务器，终端为车辆为例，对该方法进行介绍。
S1101：车辆获取所处环境的环境信息。
示例的，车辆可以通过相机、激光雷达或毫米波雷达等传感器中的至少一个采集当前所处环境的环境信息。以相机为例，该环境信息可以是该相机拍摄到的图像数据和/或视频数据。以激光雷达为例，该环境信息可以是该激光雷达探测到的雷达数据。
S1102：车辆根据环境信息获取第一地图。
其中，第一地图可以包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，第一阈值大于第二阈值。例如，第一地图可以为二维栅格地图，或为三维栅格地图。
示例的，第一栅格与第二栅格之间的距离可以小于或等于第一距离，如图7A、图7B、图7C、图8A、图8B或图8C所示。
示例的，车辆可以根据环境信息向地图服务器发送第二请求消息，地图服务器接收第二请求消息，该第二请求消息用于请求获取第四地图。车辆接收来自地图服务器的第二响应消息，该第二响应消息包括第四地图。进一步地，车辆可以对第四地图进行划分得到第一地图。其中，第四地图的构建过程以及第一地图的获取过程可以分别参考图4中的步骤401和步骤S402，在此不再赘述。
S1103：车辆根据第一栅格的特征值，更新第二栅格的特征值，得到第二地图。
其中，更新后的第二栅格的特征值可以大于第二阈值。
示例的，更新后的第二栅格的特征值可以大于第二阈值，但小于第一栅格的特征值。
示例的，第一栅格与第二栅格之间的距离越大，更新后的第二栅格的特征值越小。
步骤S1103的具体实现过程可参考图4中步骤S403所述的内容，在此不再赘述。
S1104：车辆根据所述第二地图，生成第三地图。
S1105：车辆将环境信息与第三地图进行匹配，得到车辆的定位信息。
步骤S1104、步骤S1105的具体实现过程可分别参考图4中步骤S404和步骤S408所示的内容，在此不再赘述。
本申请的上述实施例中，终端自身可以对存储的离线地图(即第一地图)进行处理生成第三地图，即根据第一栅格的特征值更新第二栅格的特征值，使得更新后的第二栅格的特征值大于第二阈值，并根据更新后的第二栅格生成第三地图。然后终端根据生成的第三地图进行定位。由于更新后的第二栅格的特征值大于第二阈值，意味着增加了定位参考对象占据第二栅格的概率，使得更新后的第二栅格对定位的影响也相应增大了，从而根据该更新后的第二栅格生成的第三地图能够很好地兼容定位过程中因动态特征、加偏运算或减偏运算等引起误差，能够提高定位的鲁棒性。另外，终端可以采用二维栅格地图的形式保存第三地图，可以减少离线存储的地图数据，提高存储空间的利用率。
基于以上方法实施例，本申请实施例还提供了一种定位地图生成装置，该定位地图生成装置用于实现上述图4中的定位地图生成的功能，该定位地图生成装置可以为地图服务器或设置在地图服务器上的芯片。参阅图12所示，该定位地图生成装置1200包括：获取单元1201、更新单元1202和地图生成单元1203。可选的，该定位地图生成装置还可以包括收发单元1204。下面介绍定位地图生成装置1200在生成定位地图时，各个单元的功能和联系。
获取单元1201，用于获取第一地图，第一地图中包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，其中，第一阈值大于第二阈值，特征值为定位参考对象占据栅格的概率，定位参考对象用于确定终端的定位信息。
更新单元1202，用于根据第一栅格的特征值，更新第二栅格的特征值以使得更新后的第二栅格的特征值大于第二阈值且小于第一栅格的特征值，得到第二地图。
地图生成单元1203，用于根据第二地图生成第三地图。
一种可能的实现方式，第一栅格与第二栅格之间的距离可以小于或等于第一距离。
一种可能的实现方式，第一栅格与第二栅格之间的距离越大，更新后的第二栅格的特征值越小。
一种可能的实现方式，收发单元1204，用于接收来自终端的第一请求消息，第一请求消息用于请求获取所述第三地图；以及向终端发送第一响应消息，第一响应消息中包括所述第三地图。
基于以上方法实施例，本申请实施例还提供了一种定位装置，该定位装置用于实现上述图4中的定位的功能，该定位装置可以为具有雷达传感器的车辆或者设置在具有雷达传感器的车辆上的芯片。参阅图13所示，该定位装置1300包括：获取单元1301和定位单元1302。可选的，该定位装置还可以包括收发单元1303。下面介绍定位装置1300在定位时，各个单元的功能和联系。
获取单元1301，用于获取其所处环境的环境信息。
定位单元1302，用于根据环境信息，确定第三地图，该第三地图是根据第二地图生成的，第二地图中包括第一栅格和第三栅格，第一栅格的特征值大于或等于第一阈值，第三栅格的特征值大于第二阈值小于第一栅格的特征值、且第三栅格的特征值是根据第一栅格的特征值确定的，其中，第一阈值大于第二阈值，特征值为定位参考对象占用栅格的概率，定位参考对象用于确定终端的定位信息；以及将环境信息与第三地图进行匹配，得到终端的定位信息。
一种可能的实现方式，第一栅格与第三栅格之间的距离可以小于或等于第一距离。
一种可能的实现方式，第一栅格与第三栅格之间的距离越大，第三栅格的特征值越小。
一种可能的实现方式，该收发单元1303，用于向网络设备发送第一请求消息，第一请求消息用于请求获取第三地图；以及接收来自网络设备的第一响应消息，第一响应消息包括所述第三地图。
基于以上方法实施例，本申请实施例还提供了一种定位装置，该定位装置用于实现上述图11中的定位地图生成的功能和定位的功能，该定位装置可以为具有雷达传感器的车辆或者设置在具有雷达传感器的车辆上的芯片。参阅图14所示，该定位装置1400包括：获取单元1401、更新单元1402、地图生成单元1403和定位单元1404。可选的，该定位装置还可以包括收发单元1405。下面介绍定位装置1400在定位时，各个单元的功能和联系。
获取单元1401，用于获取其所处环境的环境信息，以及根据环境信息，获取第一地图，第一地图中包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值，其中，第一阈值大于第二阈值，特征值为定位参考对象占用栅格的概率，定位参考对象用于确定终端的定位信息。
更新单元1402，用于根据第一栅格的特征值，更新第二栅格的特征值以使得更新后的 第二栅格的特征值大于第二阈值且小于第一栅格的特征值，得到第二地图。
地图生成单元1403，用于根据第二地图生成第三地图。
定位单元1404，用于将环境信息与第三地图进行匹配，得到终端的定位信息。
一种可能的实现方式，第一栅格与第二栅格之间的距离可以小于或等于第一距离。
一种可能的实现方式，第一栅格与第二栅格之间的距离越大，更新后的第二栅格的特征值越小。
需要说明的是，本申请上述实施例中对单元的划分是示意性的，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，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处理单元中，也可以是单独的集成的单元，也可以两个或两个以上单元集成在一个单元中。上述各个单元中的一个或多个可以软件、硬件、固件或其结合实现。所述软件或固件包括但不限于计算机程序指令或代码，并可以被硬件处理器所执行。所述硬件包括但不限于各类集成电路，如中央处理单元(CPU)、数字信号处理器(DSP)、现场可编程门阵列(FPGA)或专用集成电路(ASIC)。
集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品可以存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)或处理器(processor)执行本申请各个实施例方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read-Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
基于以上实施例，本申请实施例还提供了一种通信装置，该装置可以实现上述图4中的生成定位地图的功能，该通信装置可以为图1所示的地图服务器。参阅图15所示，通信装置1500中包括：通信接口1501、处理器1502，以及存储器1503。
通信接口1501和存储器1503与处理器1502之间相互连接。可选的，通信接口1501和存储器1503与处理器1502之间可以通过总线相互连接；总线可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图15中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
通信接口1501用于实现定位地图生成装置与定位系统中的其他部件通信。例如，通信接口1501可以用于接收来自车辆的第一请求消息，该第一请求消息用于获取第三地图，以及向车辆发送第一响应消息，该第一响应消息包括第三地图。
处理器1502用于实现上述如图4所示的定位地图生成方法，一种可能的实现方式中，处理器1502，可以用于获取第一地图，第一地图中包括第一栅格和第二栅格，第一栅格的特征值大于或等于第一阈值，第二栅格的特征值小于或等于第二阈值；根据第一栅格的特征值，更新第二栅格的特征值以使得更新后的第二栅格的特征值大于第二阈值且小于第一栅格的特征值，得到第二地图，并根据第二地图生成第三地图。具体可以参见上述图4所示的实施例中的描述，此处不再赘述。可选的，处理器1502可以是中央处理器(central processing unit，CPU)，或者其他硬件芯片。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device， PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，现场可编程逻辑门阵列(field-programmable gate array，FPGA)，通用阵列逻辑(generic array logic，GAL)或其任意组合。处理器1502在实现上述功能时，可以通过硬件实现，当然也可以通过硬件执行相应的软件实现。
存储器1503用于存放程序指令和数据等。具体地，程序指令可以包括程序代码，该程序代码包括计算机操作的指令。存储器1503可能包含随机存取存储器(random access memory，RAM)，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。处理器1502执行存储器1503所存放的程序，并通过上述各个部件，实现上述功能，从而最终实现以上实施例提供的方法。
基于以上实施例，本申请实施例还提供了一种通信装置，该装置可以实现上述图4中的生成定位的功能，或者实现上述图11中的定位地图生成的功能和定位的功能，该通信装置可以为图1所示的车辆。参阅图16所示，通信装置1600中包括：通信接口1601、处理器1602，以及存储器1603。
通信接口1601和存储器1603与处理器1602之间相互连接。可选的，通信接口1601和存储器1603与处理器1602之间可以通过总线相互连接；总线可以是外设部件互连标准(peripheral component interconnect，PCI)总线或扩展工业标准结构(extended industry standard architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等。为便于表示，图16中仅用一条粗线表示，但并不表示仅有一根总线或一种类型的总线。
通信接口1601用于实现定位地图生成装置与定位系统中的其他部件通信。例如，通信接口1601可以用于向定位地图发送第一请求消息(或第二请求消息，第二请求消息用于获取第四地图)，该第一请求消息用于获取第三地图，以及接收来自地图服务器的第一响应消息(或第二响应消息，第二响应消息包括第四地图)，该第一响应消息包括第三地图。
处理器1602用于实现上述如图4所示的定位地图生成方法，或上述如图11所示的定位地图生成方法。一种可能的实现方式中，处理器1602，可以用于获取所处环境的环境信息，根据环境信息确定第三地图，将环境信息与第三地图进行匹配，得到终端的定位信息。或者，处理器1602，可以用于获取第一地图，根据第一栅格的特征值，更新第二栅格的特征值以使得更新后的第二栅格的特征值大于第二阈值且小于第一栅格的特征值，得到第二地图，并根据第二地图生成第三地图，将环境信息与第三地图进行匹配，得到终端的定位信息。具体可以参见上述图4或图11所示的实施例中的描述，此处不再赘述。可选的，处理器1602可以是中央处理器(central processing unit，CPU)，或者其他硬件芯片。上述硬件芯片可以是专用集成电路(application-specific integrated circuit，ASIC)，可编程逻辑器件(programmable logic device，PLD)或其组合。上述PLD可以是复杂可编程逻辑器件(complex programmable logic device，CPLD)，现场可编程逻辑门阵列(field-programmable gate array，FPGA)，通用阵列逻辑(generic array logic，GAL)或其任意组合。处理器1602在实现上述功能时，可以通过硬件实现，当然也可以通过硬件执行相应的软件实现。
存储器1603用于存放程序指令和数据等。具体地，程序指令可以包括程序代码，该程序代码包括计算机操作的指令。存储器1603可能包含随机存取存储器(random access memory，RAM)，也可能还包括非易失性存储器(non-volatile memory)，例如至少一个磁盘存储器。处理器1602执行存储器1603所存放的程序，并通过上述各个部件，实现上述 功能，从而最终实现以上实施例提供的方法。
基于以上实施例，本申请实施例还提供了一种计算机程序，当计算机程序在计算机上运行时，使得计算机执行以上实施例提供的方法。
基于以上实施例，本申请实施例还提供了一种计算机存储介质，该计算机存储介质中存储有计算机程序，计算机程序被计算机执行时，使得计算机执行以上实施例提供的方法。
基于以上实施例，本申请实施例还提供了一种计算机产品，该计算机产品包括计算机程序或指令，当所述计算机程序或指令被执行时，可以使得计算机产品执行以上实施例提供的方法。
基于以上实施例，本申请实施例还提供了一种芯片，芯片用于读取存储器中存储的计算机程序，实现以上实施例提供的方法。
基于以上实施例，本申请实施例提供了一种芯片系统，该芯片系统包括处理器，用于支持计算机装置实现以上实施例提供的方法中高精度地图生成装置所涉及的功能和/或定位装置所涉及的功能。在一种可能的设计中，芯片系统还包括存储器，存储器用于保存该计算机装置必要的程序和数据。该芯片系统，可以由芯片构成，也可以包含芯片和其他分立器件。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的保护范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。

Claims (19)

  1. 一种定位地图生成方法，其特征在于，包括：
    获取第一地图，所述第一地图中包括第一栅格和第二栅格；其中，所述第一栅格的特征值大于或等于第一阈值，所述第二栅格的特征值小于或等于第二阈值，所述第一阈值大于所述第二阈值，所述特征值为定位参考对象占据栅格的概率，所述定位参考对象用于确定终端的定位信息；
    根据所述第一栅格的特征值，更新所述第二栅格的特征值，得到第二地图，更新后的第二栅格的特征值大于所述第二阈值、且小于所述第一栅格的特征值；
    根据所述第二地图，生成第三地图。
  2. 如权利要求1所述的方法，其特征在于，
    所述第一栅格与所述第二栅格之间的距离小于或等于第一距离。
  3. 如权利要求1或2项所述的方法，其特征在于，
    所述第一栅格与所述第二栅格之间的距离越大，更新后的所述第二栅格的特征值越小。
  4. 如权利要求1～3中任一项所述的方法，其特征在于，所述方法还包括：
    接收来自所述终端的第一请求消息，所述第一请求消息用于请求获取所述第三地图；
    向所述终端发送第一响应消息，所述第一响应消息中包括所述第三地图。
  5. 一种定位方法，其特征在于，包括：
    获取终端所处环境的环境信息；
    根据所述环境信息，确定第三地图，所述第三地图是根据第二地图生成的，所述第二地图中包括第一栅格和第三栅格，所述第一栅格的特征值大于或等于第一阈值，所述第三栅格的特征值大于第二阈值、且小于所述第一栅格的特征值，所述第三栅格的特征值是根据所述第一栅格的特征值确定的，所述特征值为定位参考对象占用栅格的概率，所述定位参考对象用于确定终端的定位信息，所述第一阈值大于所述第二阈值；
    将所述环境信息与所述第三地图进行匹配，得到所述终端的定位信息。
  6. 如权利要求5所述的方法，其特征在于，
    所述第一栅格与所述第三栅格之间的距离小于或等于第一距离。
  7. 如权利要求5或6所述的方法，其特征在于，
    所述第一栅格与所述第三栅格之间的距离越大，所述第三栅格的特征值越小。
  8. 如权利要求5～7中任一项所述的方法，其特征在于，所述方法还包括：
    向网络设备发送第一请求消息，所述第一请求消息用于请求获取所述第三地图；
    接收来自所述网络设备的第一响应消息，所述第一响应消息包括所述第三地图。
  9. 一种定位方法，其特征在于，包括：
    获取终端所处环境的环境信息；
    根据所述环境信息，获取第一地图，所述第一地图中包括第一栅格和第二栅格，其中，所述第一栅格的特征值大于或等于第一阈值，所述第二栅格的特征值小于或等于第二阈值，所述第一阈值大于所述第二阈值，所述特征值为定位参考对象占用栅格的概率，所述定位参考对象用于确定终端的定位信息；
    根据所述第一栅格的特征值，更新所述第二栅格的特征值，得到第二地图，更新后的第二栅格的特征值大于所述第二阈值、且小于所述第一栅格的特征值；
    根据所述第二地图，生成第三地图；
    将所述环境信息与所述第三地图进行匹配，得到所述终端的定位信息。
  10. 如权利要求9所述的方法，其特征在于，
    所述第一栅格与所述第二栅格之间的距离小于或等于第一距离。
  11. 如权利要求9或10所述的方法，其特征在于，
    所述第一栅格与所述第二栅格之间的距离越大，更新后的所述第二栅格的特征值越小。
  12. 一种定位地图生成装置，其特征在于，包括：
    获取单元，用于获取第一地图，所述第一地图中包括第一栅格和第二栅格；其中，所述第一栅格的特征值大于或等于第一阈值，所述第二栅格的特征值小于或等于第二阈值，所述第一阈值大于所述第二阈值，所述特征值为定位参考对象占据栅格的概率，所述定位参考对象用于确定终端的定位信息；
    更新单元，用于根据所述第一栅格的特征值，更新所述第二栅格的特征值，得到第二地图，更新后的第二栅格的特征值大于所述第二阈值、且小于所述第一栅格的特征值；
    地图生成单元，用于根据所述第二地图，生成第三地图。
  13. 一种定位装置，其特征在于，包括：
    获取单元，用于获取终端所处环境的环境信息；
    定位单元，用于根据所述环境信息，确定第三地图，所述第三地图是根据第二地图生成的，所述第二地图中包括第一栅格和第三栅格，所述第一栅格的特征值大于或等于第一阈值，所述第三栅格的特征值大于第二阈值、且小于所述第一栅格的特征值，所述第三栅格的特征值是根据所述第一栅格的特征值确定的，所述特征值为定位参考对象占用栅格的概率，所述定位参考对象用于确定终端的定位信息；将所述环境信息与所述第三地图进行匹配，得到所述终端的定位信息，所述第一阈值大于所述第二阈值。
  14. 一种定位装置，其特征在于，包括：
    获取单元，用于获取终端所处环境的环境信息；根据所述环境信息，获取第一地图，所述第一地图中包括第一栅格和第二栅格，其中，所述第一栅格的特征值大于或等于第一阈值，所述第一阈值大于所述第二阈值，所述第二栅格的特征值小于或等于第二阈值，所述特征值为定位参考对象占用栅格的概率，所述定位参考对象用于确定终端的定位信息；
    更新单元，用于根据所述第一栅格的特征值，更新所述第二栅格的特征值，得到第二地图，更新后的第二栅格的特征值大于所述第二阈值、且小于所述第一栅格的特征值；
    地图生成单元，用于根据所述第二地图，生成第三地图；
    定位单元，用于将所述环境信息与所述第三地图进行匹配，得到所述终端的定位信息。
  15. 一种通信装置，其特征在于，包括存储器和处理器；
    所述存储器，存储有计算机程序或指令；
    所述处理器，用于调用所述存储器中存储的计算机程序或指令，执行如权利要求1-4中任一项所述的方法。
  16. 一种通信装置，其特征在于，包括存储器和处理器；
    所述存储器，存储有计算机程序或指令；
    所述处理器，用于调用所述存储器中存储的计算机程序或指令，执行如权利要求5-8中任一项所述的方法，或执行如权利要求9-11中任一项所述的方法。
  17. 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中存储有计算机 程序或指令，当所述计算机程序或指令被驾驶决策装置执行时，实现如权利要求1-4中任一项所述的方法，或实现如权利要求5-8中任一项所述的方法，或实现如权利要求9-11中任一项所述的方法。
  18. 一种计算机程序产品，其特征在于，包括计算机程序或指令，当所述计算机程序或指令被执行时，实现如权利要求1-4中任一项所述是的方法，或实现如权利要求5-8中任一项所述是的方法，或实现如权利要求9-11中任一项所述的方法。
  19. 一种芯片，其特征在于，包括一个或多个处理器和存储器；
    所述存储器存储有计算机程序或指令；
    所述一个或多个处理器用于读取所述存储器存储的计算机程序或指令，实现如权利要求1-4中任一项所述是的方法，或实现如权利要求5-8中任一项所述是的方法，或实现如权利要求9-11中任一项所述的方法。
PCT/CN2021/090752 2020-06-30 2021-04-28 一种定位地图生成方法、定位方法及装置 WO2022001337A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010623974.0A CN113865598A (zh) 2020-06-30 2020-06-30 一种定位地图生成方法、定位方法及装置
CN202010623974.0 2020-06-30

Publications (1)

Publication Number Publication Date
WO2022001337A1 true WO2022001337A1 (zh) 2022-01-06

Family

ID=78980992

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/090752 WO2022001337A1 (zh) 2020-06-30 2021-04-28 一种定位地图生成方法、定位方法及装置

Country Status (2)

Country Link
CN (1) CN113865598A (zh)
WO (1) WO2022001337A1 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101413806A (zh) * 2008-11-07 2009-04-22 湖南大学 一种实时数据融合的移动机器人栅格地图创建方法
DE102011081740A1 (de) * 2010-08-30 2012-03-08 Denso Corporation Fahrumgebung-Erkennungseinrichtung und Fahrumgebung-Erkennungsverfahren
JP2017157087A (ja) * 2016-03-03 2017-09-07 株式会社デンソー 占有格子地図作成装置
US20190206122A1 (en) * 2017-12-29 2019-07-04 Baidu Online Network Technology (Beijing) Co., Ltd. Method and apparatus for generating raster map
CN110858076A (zh) * 2018-08-22 2020-03-03 杭州海康机器人技术有限公司 一种设备定位、栅格地图构建方法及移动机器人
CN110968083A (zh) * 2018-09-30 2020-04-07 科沃斯机器人股份有限公司 栅格地图的构建方法、避障的方法、设备及介质
CN111256711A (zh) * 2020-02-18 2020-06-09 北京百度网讯科技有限公司 车辆位姿矫正方法、装置、设备及存储介质
CN111307166A (zh) * 2018-12-11 2020-06-19 北京图森智途科技有限公司 一种构建占据栅格地图的方法及其装置、处理设备

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6559535B2 (ja) * 2015-10-22 2019-08-14 株式会社東芝 障害物マップ生成装置、その方法、及び、そのプログラム
CN106940704B (zh) * 2016-11-25 2019-12-20 北京儒博科技有限公司 一种基于栅格地图的定位方法及装置
CN110867132B (zh) * 2019-10-15 2022-03-01 阿波罗智能技术(北京)有限公司 环境感知的方法、装置、电子设备和计算机可读存储介质
CN110967011B (zh) * 2019-12-25 2022-06-28 苏州智加科技有限公司 一种定位方法、装置、设备及存储介质
CN111273305B (zh) * 2020-02-18 2022-03-25 中国科学院合肥物质科学研究院 基于全局与局部栅格图多传感器融合道路提取与索引方法

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101413806A (zh) * 2008-11-07 2009-04-22 湖南大学 一种实时数据融合的移动机器人栅格地图创建方法
DE102011081740A1 (de) * 2010-08-30 2012-03-08 Denso Corporation Fahrumgebung-Erkennungseinrichtung und Fahrumgebung-Erkennungsverfahren
JP2017157087A (ja) * 2016-03-03 2017-09-07 株式会社デンソー 占有格子地図作成装置
US20190206122A1 (en) * 2017-12-29 2019-07-04 Baidu Online Network Technology (Beijing) Co., Ltd. Method and apparatus for generating raster map
CN110858076A (zh) * 2018-08-22 2020-03-03 杭州海康机器人技术有限公司 一种设备定位、栅格地图构建方法及移动机器人
CN110968083A (zh) * 2018-09-30 2020-04-07 科沃斯机器人股份有限公司 栅格地图的构建方法、避障的方法、设备及介质
CN111307166A (zh) * 2018-12-11 2020-06-19 北京图森智途科技有限公司 一种构建占据栅格地图的方法及其装置、处理设备
CN111256711A (zh) * 2020-02-18 2020-06-09 北京百度网讯科技有限公司 车辆位姿矫正方法、装置、设备及存储介质

Also Published As

Publication number Publication date
CN113865598A (zh) 2021-12-31

Similar Documents

Publication Publication Date Title
CN108253975B (zh) 一种建立地图信息及车辆定位的方法与设备
US20210148722A1 (en) Method, apparatus, computer program, and computer-readable recording medium for producing high-definition map
CN111052132B (zh) 利用多个传感器的基于运动的车道检测的验证模块系统和方法
US20190206122A1 (en) Method and apparatus for generating raster map
CN112414417B (zh) 自动驾驶地图生成方法、装置、电子设备及可读存储介质
US11869251B2 (en) Driving support method and driving support device
CN109849930B (zh) 自动驾驶汽车的相邻车辆的速度计算方法和装置
US11774571B2 (en) Method and system for navigating autonomous ground vehicle using radio signal and vision sensor
CN111380510B (zh) 重定位方法及装置、机器人
CN112912894B (zh) 道路边界识别方法和装置
CN111353510A (zh) 多传感器目标检测方法、装置、计算机设备和存储介质
JP7343054B2 (ja) 位置推定方法、位置推定装置、および位置推定プログラム
CN116997771A (zh) 车辆及其定位方法、装置、设备、计算机可读存储介质
WO2022078342A1 (zh) 动态占据栅格估计方法及装置
WO2021056339A1 (zh) 定位方法、系统及可移动平台
KR102408981B1 (ko) Nd 맵 생성방법 및 그를 활용한 맵 업데이트 방법
EP3798665A1 (en) Method and system for aligning radar detection data
WO2022001337A1 (zh) 一种定位地图生成方法、定位方法及装置
CN114631124A (zh) 三维点云分割方法和装置、可移动平台
JPWO2020054293A1 (ja) 判定方法、及び判定装置
CN114694106A (zh) 道路检测区域的提取方法、装置、计算机设备和存储介质
CN113433566A (zh) 地图建构系统以及地图建构方法
CN111596288B (zh) 测量速度的方法、装置、车载终端和车载测速系统
US11804131B2 (en) Communication system for determining vehicle context and intent of a target vehicle based on perceived lane of travel
WO2022089173A1 (zh) 一种地图更新方法、相关装置、可读存储介质和系统

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: 21831607

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21831607

Country of ref document: EP

Kind code of ref document: A1