WO2020063814A1 - 用于车辆传感器的数据融合方法及装置 - Google Patents

用于车辆传感器的数据融合方法及装置 Download PDF

Info

Publication number
WO2020063814A1
WO2020063814A1 PCT/CN2019/108400 CN2019108400W WO2020063814A1 WO 2020063814 A1 WO2020063814 A1 WO 2020063814A1 CN 2019108400 W CN2019108400 W CN 2019108400W WO 2020063814 A1 WO2020063814 A1 WO 2020063814A1
Authority
WO
WIPO (PCT)
Prior art keywords
parameter
attribute
target
parameter attribute
data fusion
Prior art date
Application number
PCT/CN2019/108400
Other languages
English (en)
French (fr)
Inventor
葛建勇
王天培
张凯
刘宏伟
刘洪亮
任亚星
和林
李小川
Original Assignee
长城汽车股份有限公司
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 长城汽车股份有限公司 filed Critical 长城汽车股份有限公司
Priority to US17/281,557 priority Critical patent/US20210362734A1/en
Priority to EP19866352.8A priority patent/EP3859385A4/en
Priority to KR1020217013023A priority patent/KR102473269B1/ko
Priority to JP2021517842A priority patent/JP7174150B2/ja
Publication of WO2020063814A1 publication Critical patent/WO2020063814A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0205—Diagnosing or detecting failures; Failure detection models
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0225—Failure correction strategy
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/66—Radar-tracking systems; Analogous systems
    • G01S13/72—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
    • G01S13/723—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar by using numerical data
    • G01S13/726—Multiple target tracking
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/865—Combination of radar systems with lidar systems
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
    • G01S13/867—Combination of radar systems with cameras
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • 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
    • G01S17/66—Tracking systems using electromagnetic waves other than radio waves
    • 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
    • G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • 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
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/25—Fusion techniques
    • G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
    • G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0002—Automatic control, details of type of controller or control system architecture
    • B60W2050/0004—In digital systems, e.g. discrete-time systems involving sampling
    • B60W2050/0005—Processor details or data handling, e.g. memory registers or chip architecture
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0062—Adapting control system settings
    • B60W2050/0075—Automatic parameter input, automatic initialising or calibrating means
    • B60W2050/0083—Setting, resetting, calibration
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/02—Ensuring safety in case of control system failures, e.g. by diagnosing, circumventing or fixing failures
    • B60W50/0205—Diagnosing or detecting failures; Failure detection models
    • B60W2050/0215—Sensor drifts or sensor failures
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/408—Radar; Laser, e.g. lidar
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/801—Lateral distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/804—Relative longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/35—Data fusion
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Y—INDEXING SCHEME RELATING TO ASPECTS CROSS-CUTTING VEHICLE TECHNOLOGY
    • B60Y2400/00—Special features of vehicle units
    • B60Y2400/30—Sensors
    • 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
    • G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
    • 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
    • G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
    • G01S13/88—Radar or analogous systems specially adapted for specific applications
    • G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
    • G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
    • G01S2013/932—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles using own vehicle data, e.g. ground speed, steering wheel direction

Definitions

  • the present invention relates to the field of data fusion, and in particular, to a data fusion method and device for vehicle sensors.
  • the target data detected by multiple sensors is directly output, it will cause a huge amount of data transmission, and there will be the following problems: false detection of the target, such as the output of obstacles without obstacles; missed detection of the target, such as the presence of obstacles, but no output ; The same target attributes are inconsistent; the optimal attributes of the target cannot be obtained.
  • the present invention aims to propose a data fusion method for vehicle sensors, which is used to at least solve the technical problem of huge data transmission caused by direct output of target data detected by multiple sensors.
  • a data fusion method for a vehicle sensor comprising: reading a parameter attribute set of each target detected by a sensor arranged on a vehicle, the parameter attribute set including at least one or more of the following: longitudinal velocity , Longitudinal distance, and lateral distance; generating an attribute combination based on the parameter attribute set of each target detected by each of the sensors, wherein each of the attribute combinations includes a target detected from each of the sensors, respectively A parameter attribute set of a target selected from the parameter attribute set of the sine; and determining a coincidence degree of the parameter attribute set in each of the attribute combinations, and performing data fusion based on the coincidence degree to obtain a first data fusion list, where
  • the first data fusion list includes a coincidence degree of each of the attribute combinations and a parameter attribute set corresponding to the coincidence degree of each of the attribute combinations, wherein the coincidence degree refers to that the attribute combination corresponds to The number of parameter attribute sets for the same target.
  • the determining the coincidence degree of the parameter attribute set in each of the attribute combinations includes performing the following steps for each of the attribute combinations: calculating n parameter attributes of each of the n parameter attribute sets of the same type, respectively. Whether the dispersion of each of the n parameter attributes of the same type is within a respective predetermined range; if the dispersion of each of the n parameter attributes of the same type is within a respective predetermined range Within the range, it is determined that the degree of coincidence of the parameter attribute set in the attribute combination is n; and if the dispersion degree of each of the n parameter attributes of the same type does not satisfy all within their respective predetermined ranges, then the determined The degree of coincidence of the parameter attribute set in the attribute combination is 1, wherein n is a positive integer, and the value of n is greater than or equal to 2 and less than or equal to the number of parameter attribute sets of the target in the attribute combination. .
  • the maximum value of the multiple values is selected as the coincidence degree of the parameter attribute set in the attribute combination.
  • determining the degree of coincidence of the parameter attribute set in each of the attribute combinations includes: for each of the attribute combinations, starting from the maximum value of n and decrementing the value of n in turn until it is determined The coincidence degree of the parameter attribute set in the attribute combination is obtained.
  • the predetermined range is determined according to the following steps: selecting a predetermined range corresponding to a parameter attribute detected by a specific sensor among the n parameter attributes from a pre-stored predetermined range list, where the predetermined range list includes a specific sensor detection And a predetermined range corresponding to the range of each parameter attribute detected by the specific sensor.
  • the dispersion is a standard deviation, a variance, or an average deviation.
  • the method further includes: deleting repeated fused data from the first data fusion list to obtain a second data fusion list.
  • the parameter attribute set further includes a target ID
  • the method includes deleting duplicated fusion data according to the following steps: determining whether a set of target IDs corresponding to the coincidence degree p is included in a target ID of q corresponding to the coincidence degree Within the set of values, where the value of q is greater than the value of p; if the set of target IDs corresponding to the degree of coincidence p is included in the set of target IDs of q corresponding to the degree of coincidence, then fused from the first data
  • the data corresponding to the coincidence degree p is deleted from the list, where p and q are positive integers, the value of p is greater than or equal to 1 and less than the maximum value of the coincidence degree, and the value of q is greater than 1 and less than or equal to Maximum coincidence.
  • generating the attribute combination according to the parameter attribute set of each target detected by each sensor read includes: adding an empty parameter attribute set of the target to the parameter attribute set of the target detected by each sensor, respectively. ; And generating the attribute combination based on a parameter attribute set after adding an empty target parameter attribute set.
  • the data fusion method for vehicle sensors described in the present invention has the following advantages:
  • the data fusion method for vehicle sensors combines the parameter attribute sets of each target detected by each sensor, determines the coincidence degree of the parameter attribute sets in each attribute combination, and then performs the analysis based on the coincidence degree. Data fusion to obtain a first data fusion list.
  • the first data fusion list is fused to the parameter attribute set of the same target, which makes it easier for subsequent decision-making systems to use the data fusion list, simplifies the judgment logic of subsequent decision-making systems, and improves the security and operating efficiency of the entire system.
  • Another object of the present invention is to provide a data fusion device for a vehicle sensor, which is used to at least solve the technical problem of huge data transmission caused by direct output of target data detected by multiple sensors.
  • a data fusion device for a vehicle sensor includes a memory and a processor, and the memory stores instructions for enabling the processor to execute the foregoing data fusion method for a vehicle sensor .
  • the data fusion device for a vehicle sensor has the same advantages as the above-mentioned data fusion method for a vehicle sensor over the prior art, and details are not described herein again.
  • FIG. 1 is a schematic flowchart of a data fusion method for a vehicle sensor according to an embodiment of the present invention
  • FIG. 2 is a schematic flowchart of determining a coincidence degree of a parameter attribute set in an attribute combination according to an embodiment of the present invention.
  • FIG. 3 shows a structural block diagram of a data fusion device for a vehicle sensor according to an embodiment of the present invention.
  • the “sensor” mentioned in the embodiment of the present invention may refer to any type of device arranged on a vehicle for detecting a target, and may be, for example, a camera, a lidar, a millimeter wave radar, or the like.
  • the “target” mentioned in the embodiment of the present invention may refer to any moving or stationary object in front, rear, or side of the vehicle, such as a vehicle, a person, a building, or the like.
  • FIG. 1 is a schematic flowchart of a data fusion method for a vehicle sensor according to an embodiment of the present invention.
  • an embodiment of the present invention provides a data fusion method for a vehicle sensor.
  • the method may be set to be executed in real time or set to be executed at a predetermined time.
  • the method may include steps S110 to S130.
  • step S110 a parameter attribute set of each target detected by a sensor arranged on the vehicle is read.
  • the parameter attribute set of each target detected by each sensor of a plurality of sensors selected in advance may be read, and the parameter attribute set of each target detected by each sensor of all sensors may be read, where each sensor
  • the types can be the same or different.
  • the sensor can detect one or more targets, and for each target, the sensor can determine the parameter attribute set of each target.
  • the parameter attribute set includes multiple types of parameter attributes, such as parameters about speed, distance, etc. Attributes.
  • the parameter attribute set read in step S110 may include one or more of the following: longitudinal speed, longitudinal distance, and lateral distance.
  • the longitudinal speed may refer to the speed of the detected target along the direction of the vehicle
  • the longitudinal distance may refer to the longitudinal distance of the detected target relative to the vehicle
  • the lateral distance may refer to the lateral distance of the detected target relative to the vehicle.
  • the longitudinal speed, longitudinal distance, and lateral distance can be determined in the vehicle coordinate system.
  • the parameter attribute set of the target may include other parameter attributes, such as lateral speed, target longitudinal acceleration, target lateral acceleration, target length, and / or target width, and the like.
  • the read parameter attribute set detected by the sensor is a parameter attribute set detected by each sensor at about the same time.
  • step S120 an attribute combination is generated according to the parameter attribute set of each target detected by each of the sensors read.
  • Each of the generated attribute combinations may include a parameter attribute set of a target selected from a parameter attribute set of a target detected by each of the sensors, respectively.
  • the attribute combination includes the same parameter attribute set as the number of sensors, and each parameter attribute set included is obtained by different sensors.
  • a parameter attribute set of a target detected by a sensor can be obtained in turn to generate an attribute combination.
  • the number of generated attribute combinations may be the product of the number of targets detected by each sensor.
  • Sensor A detects two targets and obtains the parameter attribute sets of these two targets, denoted as A1 and A2.
  • Sensor B detects three targets and obtains the parameter attribute sets of these three targets, denoted as B1, B2, and B3.
  • Sensor C detects a target and obtains the parameter attribute set of the target, denoted as C1. Read the parameter attribute set of each target detected by sensors A, B, and C, and generate 6 attribute combinations based on the parameter attribute set of each target read.
  • step S130 the coincidence degree of the parameter attribute set in each of the attribute combinations is determined, and data fusion is performed based on the coincidence degree to obtain a first data fusion list.
  • the first data fusion list may include a coincidence degree of each attribute combination and a parameter attribute set corresponding to the coincidence degree of each attribute combination.
  • the coincidence degree refers to the number of parameter attribute sets corresponding to the same target in the attribute combination.
  • the coincidence degree of the attribute combination can be determined to be 2.
  • the obtained first data fusion list may include coincidence degree 2 and parameter attribute sets A1 and B1 corresponding to the coincidence degree 2.
  • multiple coincidence degrees may also be determined.
  • the multiple coincidence degrees and the parameter attribute set corresponding to each coincidence degree corresponding to the multiple coincidence degrees may be included in the first data fusion list. .
  • the subsequent decision system makes it easier to use the parameter attributes of the target, thereby simplifying the decision logic of the decision system.
  • the sensor may not detect the target, and accordingly will not output the parameter attribute set of the target, that is, the parameter attribute set of the target cannot be read from the sensor.
  • an empty target parameter attribute set can be added for each sensor first, which is equivalent to A detection target is virtualized for each sensor. For example, if the sensor actually detects 10 targets and obtains the parameter attribute set of the 10 targets, after adding the empty parameter attribute set, the sensor corresponds to the parameter attribute set of 11 targets. After adding an empty target parameter attribute set, you can use the added parameter attribute set to generate a combination of attributes. It can be understood that there will be an attribute combination including the parameter attribute set of all empty targets in the generated attribute combination.
  • the attribute combination is an invalid attribute combination that has no practical meaning. The invalid attribute combination can be deleted in the actual running process. .
  • the number of parameter attribute sets corresponding to these 5 sensors is N1, N2, N3, N4, and N5.
  • An empty target parameter attribute set is added for each sensor, and the number of parameter attribute sets corresponding to the five sensors becomes N1 + 1, N2 + 1, N3 + 1, N4 + 1, and N5 + 1.
  • the parameter attribute sets of one target corresponding to each sensor can be obtained in turn.
  • the number of attribute combinations generated is N1 + 1, N2 + 1, N3 + 1, N4 + 1, and N5 + 1.
  • N1, N2, N3, N4, and N5 are all integers greater than or equal to zero.
  • the number of parameter attribute sets in the attribute combination can be guaranteed to be the same as the number of corresponding sensors, which simplifies the complexity of subsequent coincidence degree calculations and improves program operation efficiency.
  • FIG. 2 is a schematic flowchart of determining a coincidence degree of a parameter attribute set in an attribute combination according to an embodiment of the present invention. As shown in FIG. 2, based on any of the foregoing embodiments, steps S202 to S208 may be performed for each combination of attributes to determine the degree of coincidence.
  • step S202 the dispersion of the n parameter attributes of each of the n parameter attribute sets in the attribute combination is respectively calculated.
  • the dispersion in the embodiment of the present invention may be a standard deviation, a variance, or an average deviation, and the standard deviation may be preferably used, but the embodiment of the present invention is not limited thereto, and any data that can represent the dispersion may be used.
  • n is a positive integer, and the value of n is greater than or equal to 2 and less than or equal to the number of parameter attribute sets of the target in the attribute combination.
  • the dispersion can be calculated for any n parameter attribute sets in the attribute combination, that is, the dispersion calculation can be performed for the n parameter attributes indicating the longitudinal distance, the dispersion calculation can be performed for the n parameter attributes indicating the lateral distance, and The dispersion of n parameter attributes pointing to the longitudinal distance is calculated.
  • step S204 it is determined whether the dispersion of each of the n parameter attributes of the same type is within a corresponding predetermined range.
  • the predetermined range corresponding to different types of parameter attributes may be a fixed value.
  • the predetermined ranges corresponding to different types of parameter attributes may be different, and / or for the same type of parameter attributes, if the parameter attribute ranges are different, the corresponding predetermined ranges may also be different.
  • a predetermined range list may be stored in advance, and the predetermined range list may include a range of parameter attributes detected by the specific sensor and a predetermined range corresponding to the range of each parameter attribute detected by the specific sensor. That is, a range of parameter attributes detected by a specific sensor is selected as a reference to determine a predetermined range.
  • the specific sensor selected for different types of parameter attributes can be different.
  • a sensor with a higher accuracy rate may be used as the specific sensor.
  • a lidar may be used as a specific sensor, and the lidar detects different longitudinal distance ranges correspondingly stored in different predetermined ranges.
  • step S204 If it is determined in step S204 that the dispersion of each of the n parameter attributes of the same type is within a corresponding predetermined range, step S206 is performed. If it is determined in step S202 that the dispersion degree of each of the n parameter attributes of the same type does not meet the respective predetermined ranges, then step S208 is performed.
  • the coincidence degree of the parameter attribute sets in the attribute combination can be determined to be n, that is, the n parameter attribute sets correspond to the same detection target, and the n parameter attribute sets can be fused.
  • the determined coincidence degree may be multiple values, and the maximum value of the multiple values may be selected as the coincidence degree of the parameter attribute set in the attribute combination.
  • step S208 it can be determined that the coincidence degree of the parameter attribute sets in the attribute combination is 1, that is, the n parameter attribute sets respectively correspond to different detection targets, and the n parameter attribute sets cannot be fused.
  • each of the n parameter attribute sets and their coincidence degree may be included in the first data fusion list.
  • the determination of the coincidence degree may be performed by sequentially decrementing the value of n starting from the value of n until the coincidence degree of the parameter attribute set in the attribute combination is determined.
  • the number of parameter attribute sets corresponding to the five sensors is E1, E2, E3, E4, and E5. Attribute combinations are generated based on the parameter attribute sets corresponding to the five sensors. The generated attribute combinations The number is denoted as F.
  • E1, E2, E3, E4, E5, and F are all positive numbers.
  • the value of F is the product of E1, E2, E3, E4, and E5, or the value of F is the product of E1, E2, E3, E4, and E5 minus 1, and each attribute combination has 5 parameter attribute sets, and this
  • n is 2 to 5.
  • n the maximum value 5
  • first use the five parameter attribute sets in the attribute combination to determine the coincidence degree. If the dispersion of the 5 parameter attributes of each type of the parameter attributes in the 5 parameter attribute sets is in the corresponding predetermined range, that is, the dispersion of the 5 longitudinal velocities is in the corresponding first predetermined range, and 5 longitudinal The dispersion of the distance is in the corresponding second predetermined range, and the dispersion of the five lateral distances is in the corresponding third predetermined range. It can be determined that the coincidence degree of the parameter attribute set in the attribute combination is 5.
  • the coincidence degree is continuously determined using any 4 parameter attribute sets in the attribute combination.
  • the parameter attributes in the attribute combination may be determined.
  • the coincidence of the sets is 4. If any four parameter attribute sets do not satisfy the condition 'the dispersion of the four parameter attributes of each type of parameter attribute in the four parameter attribute sets are in their respective predetermined ranges', then any three of the attribute combinations continue to be used The set of parameter attributes determines the degree of coincidence.
  • the parameter attributes in the attribute combination may be determined The coincidence of the sets is 3. If any three parameter attribute sets do not satisfy the condition 'the dispersion of the three parameter attributes of each type of parameter attribute in the three parameter attribute sets are in their respective predetermined ranges', then continue to use any two of the attribute combinations The set of parameter attributes determines the degree of coincidence. In any two parameter attribute sets, if the dispersion of the two parameter attributes of each type of parameter attribute in the two parameter attribute sets are in their respective predetermined ranges, the parameter attributes in the attribute combination can be determined The coincidence degree of the set is 2. If any two parameter attribute sets do not satisfy the condition 'the dispersion of the two parameter attributes of each type of parameter attribute in the two parameter attribute sets are within their respective predetermined ranges', the overlap of the parameter attribute sets may be determined Degree is 1.
  • data fusion may be performed, so that the first data fusion list includes each coincidence degree of each attribute combination and each parameter attribute set corresponding to each coincidence degree.
  • the obtained first data fusion list there may be some duplicated fusion data, that is, multiple parameter attribute sets may be stored for the same target. If the first data fusion list is directly output to the subsequent decision-making stage, then May cause false targets.
  • the data fusion method for a vehicle sensor provided in the embodiment of the present invention may further include deleting duplicated fused data from the first data fusion list to obtain a second data fusion list.
  • the parameter attribute set in the embodiment of the present invention may further include a target ID.
  • the set of target IDs corresponding to a single coincidence degree p is included in the set of target IDs corresponding to a single coincidence degree q, it means that the parameter attribute set corresponding to the coincidence degree p is repeatedly fused data and can be deleted, otherwise the coincidence may not be Degree p deletes the corresponding parameter attribute set.
  • the first data fusion list has the following target ID sets: the set ID1 / ID2 / ID3 / ID4 / ID5 of the target ID corresponding to the coincidence degree 5; the set ID1 / ID2 of the target ID corresponding to the coincidence degree 4 / ID3 / ID4; the set ID1 / ID2 of the target ID corresponding to the coincidence degree 2.
  • the parameter attribute set corresponding to the target ID set ID1 / ID2 / ID3 / ID4 and the parameter attribute set corresponding to the target ID set ID1 / ID2 can be obtained from the first data Removed from the fusion list.
  • the second data fusion list can be obtained by deleting all the repeatedly fused data in the first data fusion list according to the target ID. It can be understood that the determination of the repeated fusion data is not limited to using the target ID, and whether the set of parameter attributes corresponding to a single coincidence degree p is included in the parameter attribute set corresponding to a coincidence degree q to determine the repeatedly fused data, If the parameter attribute set corresponding to a single coincidence degree p is included in the parameter attribute set corresponding to a single coincidence degree q, it can be determined that the parameter attribute set corresponding to the single coincidence degree p is repeatedly fused data and can be deleted.
  • the streamlined second data fusion list is obtained by deleting the repeatedly fused data in the first data fusion list, so that when the second data fusion list is used in subsequent decision-making stages, false targets will not be generated, and execution decisions in subsequent decision-making stages are improved. Accuracy.
  • an embodiment of the present invention further provides a machine-readable storage medium having instructions stored on the machine-readable storage medium, which are used to enable a machine to execute data for a vehicle sensor according to any embodiment of the present invention. Fusion approach.
  • the machine-readable medium may include any one or more of the following: any entity or device capable of carrying the computer program code, a recording medium, a U disk, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM (Read-Only Memory), Random Access Memory (RAM, Random Access Memory), electric carrier signals, telecommunication signals, and software distribution media.
  • FIG. 3 shows a structural block diagram of a data fusion device for a vehicle sensor according to an embodiment of the present invention.
  • an embodiment of the present invention further provides a data fusion device for a vehicle sensor.
  • the device may include a memory 310 and a processor 320.
  • the memory 310 may store instructions that enable the processor 320 to enable A data fusion method for a vehicle sensor according to any embodiment of the present invention is performed.
  • the processor 320 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), ready-made Field-Programmable Gate Array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc.
  • CPU central processing unit
  • DSP digital signal processors
  • ASIC application specific integrated circuits
  • FPGA Field-Programmable Gate Array
  • the memory 310 may be configured to store the computer program instructions, and the processor implements the data fusion device for a vehicle sensor by running or executing computer program instructions stored in the memory and calling data stored in the memory.
  • the memory 310 may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, an internal memory, a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) card, Flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
  • a non-volatile memory such as a hard disk, an internal memory, a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) card, Flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
  • the program is stored in a storage medium and includes several instructions to make a single chip, chip or processor (processor) executes all or part of the steps of the method described in each embodiment of the present application.
  • the foregoing storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disks or optical disks and other media that can store program codes .

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Electromagnetism (AREA)
  • Automation & Control Theory (AREA)
  • Theoretical Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Data Mining & Analysis (AREA)
  • Human Computer Interaction (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Physics (AREA)
  • Databases & Information Systems (AREA)
  • Computational Linguistics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Traffic Control Systems (AREA)
  • Radar Systems Or Details Thereof (AREA)

Abstract

一种用于车辆传感器的数据融合方法及装置，该方法包括：读取布置在车辆上的传感器探测的每一个目标的参数属性集合（S110），参数属性集合至少包括以下一者或多者：纵向速度、纵向距离和横向距离；根据所读取的每一个传感器探测的每一个目标的参数属性集合生成属性组合（S120）；确定每一个属性组合中的参数属性集合的重合度，并基于重合度进行数据融合以得到第一数据融合列表（S130），其中第一数据融合列表包括每一个属性组合的重合度及与每一个属性组合的重合度对应的参数属性集合。该方法简化了后续决策系统的判断逻辑，提高了整个系统的安全性和运行效率。

Description

用于车辆传感器的数据融合方法及装置 技术领域
本发明涉及数据融合领域，具体地，涉及一种用于车辆传感器的数据融合方法及装置。
背景技术
由于单一传感器自身的性能缺陷，某些情况无法实现针对障碍物的目标探测，例如，摄像头在光照比较差的工况下无法探测目标。因此，自动驾驶汽车需要多种传感器对目标进行探测才能实现对周围环境的全面感知。
如果对多个传感器探测的目标数据进行直接输出，将造成数据传输量巨大，且会存在以下问题：目标误检，例如没有障碍物却输出障碍物；目标漏检，例如存在障碍物却没有输出；同一目标属性不一致；无法获得目标最优属性等。这些问题将对后续决策系统的判断逻辑带来很大不便，降低整个系统的安全性和运行效率。
发明内容
有鉴于此，本发明旨在提出一种用于车辆传感器的数据融合方法，用于至少解决对多个传感器探测的目标数据进行直接输出所造成数据传输量巨大的技术问题。
为达到上述目的，本发明的技术方案是这样实现的：
一种用于车辆传感器的数据融合方法，所述方法包括：读取布置在车辆上的传感器探测的每一个目标的参数属性集合，所述参数属性集合至少包括以下一者或多者：纵向速度、纵向距离和横向距离；根据所读取的每一个所述传感器探测的每一个目标的参数属性集合生成属性组合，其中每一所述属性组合包括分别从所述每一个所述传感器探测的目标的参数属性集合中选择的一个目标的参数属性集合；以及确定每一个所述属性组合中的参数属性集合的重合度，并基于所述重合度进行数据融合以得到第一数据融合列表，其中所述第一数据融合列表包括每一个所述属性组合的重合度及与所述每一个所述属性组合的重合度对应的参数属性集合，其中，所述重合度是指所述属性组合中对应于同一目标的参数属性集合的数量。
进一步的，所述确定每一个所述属性组合中的参数属性集合的重合度包括针对每一个所述属性组合执行以下步骤：分别计算n个参数属性集合中的每一个相同类型的n个参数属性的离散度；判断所述每一个相同类型的n个参数属性的离散度是否均处于各自对应的预定范围内；如果所述每一个相同类型的n个参数属性的离散度均处于各自对应的预定范围内，则确定所述属性组合中的参数属性集合的重合度为n；以及如果所述每一个相同类型的n个参数属性的离散度不满足均处于各自对应的预定范围内，则确定所述属性组合中的参数属性集合的重合度为1，其中，所述n为正整数，所述n的取值为大于或等于2且小于或等于所述属性组合中目标的参数属性集合的数量。
进一步的，在确定出的所述属性组合中的参数属性集合的重合度为多个数值时，选择这多个数值中的最大值作为所述属性组合中的参数属性集合的重合度。
进一步的，所述确定每一个所述属性组合中的参数属性集合的重合度包括：针对每一个所述属性组合，从所述n的值为最大值开始依次递减所述n的值，直到确定出所述属性组合中的参数属性集合的重合度。
进一步的，根据以下步骤确定所述预定范围：从预先存储的预定范围列表中选取所述n个参数属性中特定传感器探测的参数属性所对应的预定范围，其中所述预定范围列表包括特定传感器探测的参数属性的范围及与所述特定传感器探测的每一参数属性的范围对应的预定范围。
进一步的，所述离散度为标准差、方差或平均差。
进一步的，所述方法还包括：从所述第一数据融合列表中删除重复融合的数据以得到第二数据融合列表。
进一步的，所述参数属性集合还包括目标ID，所述方法包括根据以下步骤删除重复融合的数据：判断与重合度p对应的目标ID的集合是否被包含在与重合度对应的q的目标ID的集合内，其中q的取值大于p的取值；如果与重合度p对应的目标ID的集合被包含在与重合度对应的q的目标ID的集合内，则从所述第一数据融合列表中删除与所述重合度p对应的数据，其中p和q均为正整数，p的取值为大于或等于1且小于重合度的最大值，q的取值为大于1且小于 或等于重合度的最大值。
进一步的，所述根据所读取的每一个传感器探测的每一个目标的参数属性集合生成属性组合包括：分别针对所述每一个传感器探测的目标的参数属性集合增加一个空的目标的参数属性集合；以及基于增加空的目标的参数属性集合后的参数属性集合来生成所述属性组合。
相对于现有技术，本发明所述的用于车辆传感器的数据融合方法具有以下优势：
本发明所述的用于车辆传感器的数据融合方法，通过对每一个传感器探测的每一个目标的参数属性集合进行组合，并确定每一个属性组合中参数属性集合的重合度，然后基于重合度进行数据融合以得到第一数据融合列表。该第一数据融合列表针对同一目标的参数属性集合进行了融合，使得后续决策系统便于使用该数据融合列表，简化了后续决策系统的判断逻辑，提高了整个系统的安全性和运行效率。
本发明的另一目的在于提出一种用于车辆传感器的数据融合装置，用于至少解决对多个传感器探测的目标数据进行直接输出所造成数据传输量巨大的技术问题。
为达到上述目的，本发明的技术方案是这样实现的：
一种用于车辆传感器的数据融合装置，所述装置包括存储器和处理器，所述存储器中存储有指令，所述指令用于使得所述处理器能够执行上述的用于车辆传感器的数据融合方法。
所述用于车辆传感器的数据融合装置与上述用于车辆传感器的数据融合方法相对于现有技术所具有的优势相同，在此不再赘述。
本发明实施例的其它特征和优点将在随后的具体实施方式部分予以详细说明。
附图说明
附图是用来提供对本发明实施例的进一步理解，并且构成说明书的一部分，与下面的具体实施方式一起用于解释本发明实施例，但并不构成对本发明实施例的限制。在附图中：
图1示出了根据本发明一实施例的用于车辆传感器的数据融合方法的流程示意图；
图2示出了根据本发明一实施例的属性组合中的参数属性集合的重合度确定流程示意图；以及
图3示出了根据本发明一实施例的用于车辆传感器的数据融合装置的结构框图。
附图标记说明
310存储器    320处理器
具体实施方式
以下结合附图对本发明实施例的具体实施方式进行详细说明。应当理解的是，此处所描述的具体实施方式仅用于说明和解释本发明实施例，并不用于限制本发明实施例。
本发明实施例中提到的“传感器”可以指布置在车辆上用于探测 目标的任意类型的装置，例如可以是摄像头、激光雷达、毫米波雷达等。本发明实施例中提到的“目标”可以指在车辆前方、后方或侧方的移动的或静止的任意物体，例如，车辆、人、建筑物等。
图1示出了根据本发明一实施例的用于车辆传感器的数据融合方法的流程示意图。如图1所示，本发明实施例提供一种用于车辆传感器的数据融合方法，该方法可以设置为实时执行或设置为每隔预定时间执行一次。所述方法可以包括步骤S110至步骤S130。
在步骤S110，读取布置在车辆上的传感器探测的每一个目标的参数属性集合。
这里，可以读取预先选定的多个传感器中每一个传感器探测的每一个目标的参数属性集合，也可以读取全部传感器中每一个传感器探测的每一个目标的参数属性集合，其中，各传感器的类型可以相同也可以不同。
传感器可以探测到一个或多个目标，并且针对每一个目标，传感器可以确定出每一个目标的参数属性集合，该参数属性集合包括多种类型的参数属性，例如，有关速度、距离等等的参数属性。在步骤S110中读取的参数属性集合可以包括以下一者或多者：纵向速度、纵向距离和横向距离。本发明实施例中的纵向速度可以是指探测的目标沿车辆行驶方向的速度，纵向距离可以是指探测的目标相对车辆的纵向距离，横向距离可以是指探测的目标相对车辆的横向距离，其中纵向速度、纵向距离和横向距离可以是在车辆坐标系下确定得出的。可以理解，目标的参数属性集合可以包括其它参数属性，例如横向速 度、目标纵向加速度、目标横向加速度、目标长度和/或目标宽度等。
可以理解，在步骤S110，所读取的传感器探测的参数属性集合是各传感器在大致的同一时间探测到的参数属性集合。
在步骤S120，根据所读取的每一个所述传感器探测的每一个目标的参数属性集合生成属性组合。
所生成的每一个属性组合可以包括分别从每一个所述传感器探测的目标的参数属性集合中选择的一个目标的参数属性集合。也就是说，属性组合包括与传感器数量相同的参数属性集合，且所包括的每一个参数属性集合是不同的传感器探测得到的。实际执行时，可以依次分别获取一个传感器探测的一个目标的参数属性集合来生成属性组合。可以理解，所生成的属性组合的数量可为每一个传感器探测得到的目标的数量之积。
简单举例来讲，假设具有三个传感器，这三个传感器分别表示为A、B、C。传感器A探测到两个目标，并分别获得这两个目标的参数属性集合，表示为A1和A2。传感器B探测到三个目标，并分别获得这三个目标的参数属性集合，表示为B1、B2和B3。传感器C探测到一个目标，并获得该一个目标的参数属性集合，表示为C1。读取传感器A、B和C探测的每一个目标的参数属性集合，并根据所读取的每一个目标的参数属性集合可以生成6个属性组合，这6个属性组合例如分别是：{A1，B1，C1}、{A1，B2，C1}、{A1，B3，C1}、{A2，B1，C1}、{A2，B2，C1}、{A2，B3，C1}。
在步骤S130，确定每一个所述属性组合中的参数属性集合的重 合度，并基于所述重合度进行数据融合以得到第一数据融合列表。
其中，所述第一数据融合列表可以包括每一个属性组合的重合度以及与每一个属性组合的重合度对应的参数属性集合。
本发明实施例中，重合度是指属性组合中对应于同一目标的参数属性集合的数量。简单举例来讲，如果包括参数属性集合A1、B1和C1的属性组合中参数属性集合A1和B1对应于同一目标，则可以确定该属性组合的重合度为2。则所得到的第一数据融合列表中可以包括重合度2和与该重合度2对应的参数属性集合A1和B1。
对于一个属性组合，也可能会确定出多个重合度，则该多个重合度及与该多个重合度对应的每一个重合度对应的参数属性集合都可以被包括在第一数据融合列表中。
通过对与同一目标对应的参数属性集合进行融合来生成并输出第一数据融合列表，使得后续决策系统更方便的使用目标的参数属性，从而简化了决策系统的判断逻辑。
在一些实施例中，传感器可能没有探测到目标，相应地也不会输出目标的参数属性集合，即，不能从该传感器读取到目标的参数属性集合。为了便于后续对重合度的计算，在根据所读取的每一个传感器探测的每一个目标的参数属性集合生成属性组合时，可以首先分别针对每一个传感器增加一个空的目标参数属性集合，相当于给每一个传感器虚拟了一个探测目标。例如，如果传感器实际探测到了10个目标并获得这10个目标的参数属性集合，则在添加空的目标的参数属性集合之后，与该传感器对应的是11个目标的参数属性集合。在添 加空的目标的参数属性集合之后，可以使用添加后的参数属性集合来生成属性组合。可以理解，所生成属性组合中将会有一个包括全部空的目标的参数属性集合的属性组合，该属性组合为没有实际意义的无效的属性组合，在实际运行过程中可以删除该无效的属性组合。
假设车辆前侧方布置5个传感器，这5个传感器探测到的目标的数量分别是N1、N2、N3、N4和N5，则对应从这5个传感器读取到的参数属性集合的数量分别是N1、N2、N3、N4和N5。针对每一个传感器添加一个空的目标的参数属性集合，则与这5个传感器对应的参数属性集合的数量变为N1+1、N2+1、N3+1、N4+1和N5+1。生成属性组合时，可以依次分别获取与每一个传感器对应的一个目标的参数属性集合，所生成的属性组合的数量为N1+1、N2+1、N3+1、N4+1和N5+1的乘积，删除无效的属性组合之后，剩余属性组合的数量为N1+1、N2+1、N3+1、N4+1和N5+1的乘积减去1。这里，N1、N2、N3、N4和N5均为大于或等于0的整数。
通过添加空的目标的参数属性集合，可以保证属性组合内参数属性集合的数量与对应的传感器的数量相同，简化了后续重合度计算的复杂性，提高了程序运行效率。
图2示出了根据本发明一实施例的属性组合中的参数属性集合的重合度确定流程示意图。如图2所示，基于上述任意实施例，针对每一个属性组合可以执行步骤S202至步骤S208来确定重合度。
在步骤S202，分别计算属性组合中的n个参数属性集合中的每一个相同类型的n个参数属性的离散度。
本发明实施例中的离散度可以是标准差、方差或平均差等，优选可以使用标准差，但是本发明实施例并不限制于此，可以使用任何可以表征离散度的数据。本发明实施例中，所述n为正整数，n的取值为大于或等于2且小于或等于所述属性组合中目标的参数属性集合的数量。
具体地，可以针对属性组合中的任意n个参数属性集合计算离散度，即可以针对指示纵向距离的n个参数属性进行离散度计算、针对指示横向距离的n个参数属性进行离散度计算、针对指向纵向距离的n个参数属性的进行离散度计算。
在步骤S204，判断每一个相同类型的n个参数属性的离散度是否均处于各自对应的预定范围内。
不同类型的参数属性对应的预定范围可以是固定值。或者，不同类型的参数属性对应的预定范围可以不同，和/或对于同一类型的参数属性，如果参数属性的取值范围不同，则对应的预定范围也可以不同。
可选地，可以预先存储有预定范围列表，该预定范围列表可以包括特定传感器探测的参数属性的范围及与特定传感器探测的每一参数属性的范围对应的预定范围。也就是说，选择一个特定传感器探测的参数属性的范围为基准，来确定预定范围。针对不同类型的参数属性所选择的特定传感器可以不同。可选地，可以使用准确率较高的传感器作为特定传感器。例如，针对纵向距离，可以使用激光雷达作为特定传感器，激光雷达探测不同纵向距离范围对应存储有不同的预定 范围。在执行步骤S204时，可以从预先存储的预定范围列表中选取n个参数属性中特定传感器探测的参数属性所对应的预定范围，然后基于该预定范围进行判断。
如果在步骤S204中判断出每一个相同类型的n个参数属性的离散度均处于各自对应的预定范围内，则执行步骤S206。如果在步骤S202中判断出每一个相同类型的n个参数属性的离散度不满足均处于各自对应的预定范围内，则执行步骤S208。
在步骤S206，可以确定属性组合中的参数属性集合的重合度为n，也就是说，这n个参数属性集合对应于同一探测目标，可以对这n个参数属性集合进行融合。可选地，所确定出的重合度可能为多个数值，则可以选择这多个数值中的最大值作为属性组合中的参数属性集合的重合度。可选地，在确定出的重合度中可能存在多个最大值，这种情况下，该多个最大值的每一个最大值及其所对应的参数属性集合都可以被包括在第一数据融合列表中。
在步骤S208，可以确定属性组合中的参数属性集合的重合度为1，也就是说，这n个参数属性集合分别对应于不同的探测目标，不能对这n个参数属性集合进行融合，这种情况下，可以将这n个参数属性集合中的每一个参数属性集合及其重合度均包括在第一数据融合列表中。
可选地，针对每一个属性组合，可以从n的值为最大值开始依次递减n的值来执行重合度的确定，直到确定出所述属性组合中的参数属性集合的重合度。
以5个传感器为例进行说明，这5个传感器对应的参数属性集合的数量分别为E1、E2、E3、E4和E5，根据这5个传感器对应的参数属性集合生成属性组合，生成的属性组合的数量记为F，本发明实施例中，E1、E2、E3、E4、E5和F均为正数。F的值为E1、E2、E3、E4和E5的乘积，或者F的值为E1、E2、E3、E4和E5的乘积减去1，每个属性组合中具有5个参数属性集合，且这5个属性集合分别对应于不同的传感器。这里，n的取值为2至5。
在计算每一个属性组合中参数属性集合的重合度时，针对每一个属性组合，首先选取n为最大值5，也就是说，首先使用属性组合中5个参数属性集合确定重合度。如果这5个参数属性集合中每一类型的参数属性的5个参数属性的离散度均处于各自对应的预定范围，即，5个纵向速度的离散度处于对应的第一预定范围，5个纵向距离的离散度处于对应的第二预定范围，5个横向距离的离散度处于对应的第三预定范围，则可以确定该属性组合中的参数属性集合的重合度为5。如果这5个参数属性集合中每一类型的参数属性的5个参数属性的离散度不满足均处于对应的预定范围，则继续使用属性组合中任意4个参数属性集合确定重合度。在任意4个参数属性集合中，如果存在4个参数属性集合中的每一类型的参数属性的4个参数属性的离散度均处于各自对应的预定范围，则可以确定该属性组合中的参数属性集合的重合度为4。如果任意4个参数属性集合均不满足条件‘4个参数属性集合中的每一类型的参数属性的4个参数属性的离散度均处于各自对应的预定范围’，则继续使用属性组合中任意3个参数属性 集合确定重合度。在任意3个参数属性集合中，如果存在3个参数属性集合中的每一类型的参数属性的3个参数属性的离散度均处于各自对应的预定范围，则可以确定该属性组合中的参数属性集合的重合度为3。如果任意3个参数属性集合均不满足条件‘3个参数属性集合中的每一类型的参数属性的3个参数属性的离散度均处于各自对应的预定范围’，则继续使用属性组合中任意2个参数属性集合确定重合度。在任意2个参数属性集合中，如果存在2个参数属性集合中的每一类型的参数属性的2个参数属性的离散度均处于各自对应的预定范围，则可以确定该属性组合中的参数属性集合的重合度为2。如果任意2个参数属性集合均不满足条件‘2个参数属性集合中的每一类型的参数属性的2个参数属性的离散度均处于各自对应的预定范围’，则可以参数属性集合的确定重合度为1。
在确定出重合度之后，可以进行数据融合，以使得第一数据融合列表中包括每一个属性组合中的每一个重合度及与每一个重合度对应的每一个参数属性集合。在所得到的第一数据融合列表中，可能存在一些重复融合的数据，也就是说可能针对同一目标存储了多次参数属性集合，如果直接将第一数据融合列表输出值后续的决策阶段，则可能造成虚假目标的产生。
进一步地，基于上述任意实施例，本发明实施例提供的用于车辆传感器的数据融合方法还可以包括从第一数据融合列表中删除重复融合的数据以得到第二数据融合列表。
本发明实施例中的参数属性集合还可以包括目标ID。在第一数 据融合列表中，可以判断与任意单个重合度p对应的目标ID的集合是否被包含在与任意单个重合度q对应的目标ID的集合内，其中p和q均为正整数，p的取值为大于或等于1且小于重合度的最大值，q的取值为大于1且小于或等于重合度的最大值，并且其中q的取值大于p的取值。如果单个重合度p对应的目标ID的集合被包含在单个重合度q对应的目标ID的集合内，则说明重合度p对应的参数属性集合为重复融合的数据，可以进行删除，否则可以不对重合度p进行对应的参数属性集合进行删除。例如，如果在第一数据融合列表中具有以下目标ID的集合：与重合度5对应的目标ID的集合ID1/ID2/ID3/ID4/ID5；与重合度4对应的目标ID的集合ID1/ID2/ID3/ID4；与重合度2对应的目标ID的集合ID1/ID2。则可以确定这些目标ID的集合均对应同一目标，则可以将目标ID的集合ID1/ID2/ID3/ID4对应的参数属性集合和与目标ID的集合ID1/ID2对应的参数属性集合从第一数据融合列表中删除。
根据目标ID删除第一数据融合列表中所有重复融合的数据就可以得到第二数据融合列表。可以理解，对重复融合数据的确定不限于使用目标ID，也可以使用与单个重合度p对应参数属性的集合是否被包含在与一个重合度q对应的参数属性集合中来确定重复融合的数据，如果与单个重合度p对应的参数属性的集合包含在与单个重合度q对应的参数属性集合中，则可以确定与该单个重合度p对应的参数属性集合为重复融合的数据，可以进行删除。
通过删除第一数据融合列表中重复融合的数据来得到精简的第 二数据融合列表，可以使得后续决策阶段使用第二数据融合列表时，不会造成虚假目标的产生，提高了后续决策阶段执行决策的准确度。
相应地，本发明实施例还提供一种机器可读存储介质，该机器可读存储介质上存储有指令，所述指令用于使得机器能够执行根据本发明任意实施例的用于车辆传感器的数据融合方法。所述机器可读介质可以包括以下任意一者或多者：能够携带所述计算机程序代码的任何实体或装置、记录介质、U盘、移动硬盘、磁碟、光盘、计算机存储器、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、电载波信号、电信信号以及软件分发介质等。
图3示出了根据本发明一实施例的用于车辆传感器的数据融合装置的结构框图。如图3所示，本发明实施例还提供一种用于车辆传感器的数据融合装置，所述装置可以包括存储器310和处理器320，存储器310中可以存储有指令，该指令使得处理器320能够执行根据本发明任意实施例的用于车辆传感器的数据融合方法。
处理器320可以是中央处理单元(Central Processing Unit，CPU)，还可以是其他通用处理器、数字信号处理器(Digital Signal Processor，DSP)、专用集成电路(Application Specific Integrated Circuit，ASIC)、现成可编程门阵列(Field-Programmable Gate Array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件等。
存储器310可用于存储所述计算机程序指令，所述处理器通过运行或执行存储在所述存储器内的计算机程序指令，以及调用存储在存 储器内的数据，实现所述用于车辆传感器的数据融合装置的各种功能。存储器310可以包括高速随机存取存储器，还可以包括非易失性存储器，例如硬盘、内存、插接式硬盘，智能存储卡(Smart Media Card,SMC)，安全数字(Secure Digital,SD)卡，闪存卡(Flash Card)、至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
本发明实施例提供的用于车辆传感器的数据融合装置的具体工作原理及益处与上述本发明实施例提供的用于车辆传感器的数据融合方法的具体工作原理及益处相类似，这里将不再赘述。
以上结合附图详细描述了本发明实施例的可选实施方式，但是，本发明实施例并不限于上述实施方式中的具体细节，在本发明实施例的技术构思范围内，可以对本发明实施例的技术方案进行多种简单变型，这些简单变型均属于本发明实施例的保护范围。
另外需要说明的是，在上述具体实施方式中所描述的各个具体技术特征，在不矛盾的情况下，可以通过任何合适的方式进行组合。为了避免不必要的重复，本发明实施例对各种可能的组合方式不再另行说明。
本领域技术人员可以理解实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序存储在一个存储介质中，包括若干指令用以使得单片机、芯片或处理器(processor)执行本申请各个实施例所述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(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘 等各种可以存储程序代码的介质。
此外，本发明实施例的各种不同的实施方式之间也可以进行任意组合，只要其不违背本发明实施例的思想，其同样应当视为本发明实施例所公开的内容。

Claims (10)

  1. 一种用于车辆传感器的数据融合方法，其特征在于，所述方法包括：
    读取布置在车辆上的传感器探测的每一个目标的参数属性集合，所述参数属性集合至少包括以下一者或多者：纵向速度、纵向距离和横向距离；
    根据所读取的每一个所述传感器探测的每一个目标的参数属性集合生成属性组合，其中每一所述属性组合包括分别从所述每一个所述传感器探测的目标的参数属性集合中选择的一个目标的参数属性集合；以及
    确定每一个所述属性组合中的参数属性集合的重合度，并基于所述重合度进行数据融合以得到第一数据融合列表，其中所述第一数据融合列表包括每一个所述属性组合的重合度及与所述每一个所述属性组合的重合度对应的参数属性集合，其中，所述重合度是指所述属性组合中对应于同一目标的参数属性集合的数量。
  2. 根据权利要求1所述的方法，其特征在于，所述确定每一个所述属性组合中的参数属性集合的重合度包括针对每一个所述属性组合执行以下步骤：
    分别计算n个参数属性集合中的每一个相同类型的n个参数属性的离散度；
    判断所述每一个相同类型的n个参数属性的离散度是否均处于各自对应的预定范围内；
    如果所述每一个相同类型的n个参数属性的离散度均处于各自对应的预定范围内，则确定所述属性组合中的参数属性集合的重合度为n；以及
    如果所述每一个相同类型的n个参数属性的离散度不满足均处于各自对应的预定范围内，则确定所述属性组合中的参数属性集合的重合度为1，
    其中，所述n为正整数，所述n的取值为大于或等于2且小于或等于所述属性组合中目标的参数属性集合的数量。
  3. 根据权利要求2所述的方法，其特征在于，在确定出的所述属性组合中的参数属性集合的重合度为多个数值时，选择这多个数值中的最大值作为所述属性组合中的参数属性集合的重合度。
  4. 根据权利要求2所述的方法，其特征在于，所述确定每一个所述属性组合中的参数属性集合的重合度包括：
    针对每一个所述属性组合，从所述n的值为最大值开始依次递减所述n的值，直到确定出所述属性组合中的参数属性集合的重合度。
  5. 根据权利要求2所述的方法，其特征在于，根据以下步骤确定所述预定范围：
    从预先存储的预定范围列表中选取所述n个参数属性中特定传感器探测的参数属性所对应的预定范围，其中所述预定范围列表包括特定传感器探测的参数属性的范围及与所述特定传感器探测的每一参数属性的范围对应的预定范围。
  6. 根据权利要求2所述的方法，其特征在于，所述离散度为标准差、方差或平均差。
  7. 根据权利要求1至6中任一项所述的方法，其特征在于，所述方法还包括：
    从所述第一数据融合列表中删除重复融合的数据以得到第二数据融合列表。
  8. 根据权利要求7所述的方法，其特征在于，所述参数属性集合还包括目标ID，所述方法包括根据以下步骤删除重复融合的数据：
    判断与重合度p对应的目标ID的集合是否被包含在与重合度对应的q的目标ID的集合内，其中q的取值大于p的取值；
    如果与重合度p对应的目标ID的集合被包含在与重合度对应的q的目标ID的集合内，则从所述第一数据融合列表中删除与所述重合度p对应的数据，
    其中p和q均为正整数，p的取值为大于或等于1且小于重合度的最大值，q的取值为大于1且小于或等于重合度的最大值。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，所述根据所读取的每一个传感器探测的每一个目标的参数属性集合生成属性组合包括：
    分别针对所述每一个传感器探测的目标的参数属性集合增加一个空的目标的参数属性集合；以及
    基于增加空的目标的参数属性集合后的参数属性集合来生成所述属性组合。
  10. 一种用于车辆传感器的数据融合装置，其特征在于，所述装置包括存储器和处理器，所述存储器中存储有指令，所述指令用于使得所述处理器能够执行根据权利要求1至9中任一项所述的用于车辆传感器的数据融合方法。
PCT/CN2019/108400 2018-09-30 2019-09-27 用于车辆传感器的数据融合方法及装置 WO2020063814A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
US17/281,557 US20210362734A1 (en) 2018-09-30 2019-09-27 Data fusion method and apparatus for vehicle sensor
EP19866352.8A EP3859385A4 (en) 2018-09-30 2019-09-27 METHOD AND DEVICE FOR DATA FUSION FOR A VEHICLE SENSOR
KR1020217013023A KR102473269B1 (ko) 2018-09-30 2019-09-27 차량 센서용 데이터 융합 방법 및 장치
JP2021517842A JP7174150B2 (ja) 2018-09-30 2019-09-27 車両センサ用のデータ融合方法及び装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811154323.0A CN110376583B (zh) 2018-09-30 2018-09-30 用于车辆传感器的数据融合方法及装置
CN201811154323.0 2018-09-30

Publications (1)

Publication Number Publication Date
WO2020063814A1 true WO2020063814A1 (zh) 2020-04-02

Family

ID=68243473

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/108400 WO2020063814A1 (zh) 2018-09-30 2019-09-27 用于车辆传感器的数据融合方法及装置

Country Status (6)

Country Link
US (1) US20210362734A1 (zh)
EP (1) EP3859385A4 (zh)
JP (1) JP7174150B2 (zh)
KR (1) KR102473269B1 (zh)
CN (1) CN110376583B (zh)
WO (1) WO2020063814A1 (zh)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112712717B (zh) * 2019-10-26 2022-09-23 华为技术有限公司 一种信息融合的方法、装置和设备
CN112597122A (zh) * 2020-09-03 2021-04-02 禾多科技（北京）有限公司 自动驾驶车辆的车载数据处理方法、装置和电子设备

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030179084A1 (en) * 2002-03-21 2003-09-25 Ford Global Technologies, Inc. Sensor fusion system architecture
CN101395492A (zh) * 2006-03-01 2009-03-25 丰田自动车株式会社 物体检测装置
CN103852762A (zh) * 2012-11-28 2014-06-11 富士通天株式会社 雷达设备和信号处理方法
CN106030336A (zh) * 2014-02-17 2016-10-12 丰田自动车株式会社 车辆周围状况识别设备和车辆控制设备
CN106842188A (zh) * 2016-12-27 2017-06-13 上海思致汽车工程技术有限公司 一种基于多传感器的目标物探测融合装置及方法

Family Cites Families (22)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH1019614A (ja) * 1996-06-28 1998-01-23 Omron Corp マルチセンサシステムの診断方法及び装置
DE10133945A1 (de) * 2001-07-17 2003-02-06 Bosch Gmbh Robert Verfahren und Vorrichtung zum Austausch und zur Verarbeitung von Daten
US8539359B2 (en) * 2009-02-11 2013-09-17 Jeffrey A. Rapaport Social network driven indexing system for instantly clustering people with concurrent focus on same topic into on-topic chat rooms and/or for generating on-topic search results tailored to user preferences regarding topic
US9429650B2 (en) * 2012-08-01 2016-08-30 Gm Global Technology Operations Fusion of obstacle detection using radar and camera
US9274525B1 (en) * 2012-09-28 2016-03-01 Google Inc. Detecting sensor degradation by actively controlling an autonomous vehicle
US9255988B2 (en) * 2014-01-16 2016-02-09 GM Global Technology Operations LLC Object fusion system of multiple radar imaging sensors
FR3020616B1 (fr) * 2014-04-30 2017-10-27 Renault Sas Dispositif de signalisation d'objets a un module de navigation de vehicule equipe de ce dispositif
US9563808B2 (en) * 2015-01-14 2017-02-07 GM Global Technology Operations LLC Target grouping techniques for object fusion
JP6169146B2 (ja) * 2015-10-16 2017-07-26 三菱電機株式会社 物体認識統合装置および物体認識統合方法
CN105372654B (zh) * 2015-12-14 2017-12-12 财团法人车辆研究测试中心 障碍物分类可靠度量化的方法
CN105740802A (zh) * 2016-01-28 2016-07-06 北京中科慧眼科技有限公司 基于视差图的障碍物检测方法和装置及汽车驾驶辅助系统
WO2017210901A1 (zh) * 2016-06-08 2017-12-14 驭势科技（北京）有限公司 车辆自动驾驶的速度规划方法、装置及计算装置
CN109844839A (zh) * 2016-06-10 2019-06-04 大陆汽车系统公司 用于自主车道变换操纵的状况分析的系统和方法
JPWO2018155142A1 (ja) * 2017-02-21 2019-07-11 日立オートモティブシステムズ株式会社 車両制御装置
US10466361B2 (en) * 2017-03-14 2019-11-05 Toyota Research Institute, Inc. Systems and methods for multi-sensor fusion using permutation matrix track association
CN107562890B (zh) * 2017-09-05 2020-11-06 成都中星世通电子科技有限公司 一种基于ais、雷达、电磁的目标信息融合方法
CN109521757B (zh) * 2017-09-18 2021-12-31 阿波罗智能技术(北京)有限公司 静态障碍物识别方法和装置
CN107918386B (zh) * 2017-10-25 2021-01-01 北京汽车集团有限公司 用于车辆的多传感器数据融合方法、装置及车辆
CN109541634B (zh) * 2018-12-28 2023-01-17 歌尔股份有限公司 一种路径规划方法、装置和移动设备
CN109658740A (zh) * 2019-02-19 2019-04-19 百度在线网络技术（北京）有限公司 车辆间的交互方法和装置
KR20200113915A (ko) * 2019-03-27 2020-10-07 주식회사 만도 차량 제어 장치 및 방법
US11548511B2 (en) * 2019-06-14 2023-01-10 GM Global Technology Operations LLC Method to control vehicle speed to center of a lane change gap

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030179084A1 (en) * 2002-03-21 2003-09-25 Ford Global Technologies, Inc. Sensor fusion system architecture
CN101395492A (zh) * 2006-03-01 2009-03-25 丰田自动车株式会社 物体检测装置
CN103852762A (zh) * 2012-11-28 2014-06-11 富士通天株式会社 雷达设备和信号处理方法
CN106030336A (zh) * 2014-02-17 2016-10-12 丰田自动车株式会社 车辆周围状况识别设备和车辆控制设备
CN106842188A (zh) * 2016-12-27 2017-06-13 上海思致汽车工程技术有限公司 一种基于多传感器的目标物探测融合装置及方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3859385A4 *

Also Published As

Publication number Publication date
JP2022502780A (ja) 2022-01-11
CN110376583B (zh) 2021-11-19
EP3859385A1 (en) 2021-08-04
US20210362734A1 (en) 2021-11-25
JP7174150B2 (ja) 2022-11-17
KR20210066890A (ko) 2021-06-07
KR102473269B1 (ko) 2022-12-05
EP3859385A4 (en) 2021-11-24
CN110376583A (zh) 2019-10-25

Similar Documents

Publication Publication Date Title
KR102175226B1 (ko) 데이터 위험을 제어하기 위한 방법 및 디바이스
CN111158365B (zh) 一种路径规划方法、装置、机器人及存储介质
US11295144B2 (en) Obstacle classification method and apparatus based on unmanned vehicle, device, and storage medium
CN108876024B (zh) 路径规划、路径实时优化方法及装置、存储介质
WO2020063814A1 (zh) 用于车辆传感器的数据融合方法及装置
KR102316960B1 (ko) 무인 항공기 영상 내 실시간 객체 검출 방법 및 장치
JP2020038622A (ja) 車線追跡方法及び装置
WO2021013227A1 (zh) 用于目标检测的图像处理方法及装置
Benoudnine et al. Real time Hough transform based track initiators in clutter
CN111319614B (zh) 一种自动泊车路径规划方法、装置和存储介质
CN111382315B (zh) 子图同构匹配结果的合并方法、电子设备及存储介质
KR102473272B1 (ko) 목표 추적 방법 및 장치
CN107305688B (zh) 检测道路消失点的方法、装置和系统
CN112558035A (zh) 用于估计地面的方法和装置
EP4209854A1 (en) Overtaking planning method and apparatus, and electronic device and storage medium
CN116360417A (zh) 一种机器人的路径规划方法、装置及设备
CN111045026B (zh) 一种识别充电桩位姿的方法及装置
CN109738908B (zh) 基于激光雷达的报警方法、装置及系统
CN110363834B (zh) 一种点云数据的分割方法和装置
CN108764899B (zh) 基于云计算网络的数字资产管理方法、装置和存储设备
WO2020094023A1 (zh) 一种道路抽稀的算法
CN109828894A (zh) 设备状态数据的采集方法、装置、存储介质和电子设备
WO2024183825A1 (zh) 一种目标关联匹配方法、装置、车机及存储介质
CN117125057B (zh) 一种基于车辆变道的碰撞检测方法、装置、设备及存储介质
CN115845381B (zh) 一种基于包围盒的快速寻路方法、装置、设备及介质

Legal Events

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

Ref document number: 19866352

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021517842

Country of ref document: JP

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2101001899

Country of ref document: TH

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 20217013023

Country of ref document: KR

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2019866352

Country of ref document: EP