CN113619600B - Obstacle data diagnosis method, obstacle data diagnosis device, movable carrier, and storage medium - Google Patents

Obstacle data diagnosis method, obstacle data diagnosis device, movable carrier, and storage medium Download PDF

Info

Publication number
CN113619600B
CN113619600B CN202110946926.XA CN202110946926A CN113619600B CN 113619600 B CN113619600 B CN 113619600B CN 202110946926 A CN202110946926 A CN 202110946926A CN 113619600 B CN113619600 B CN 113619600B
Authority
CN
China
Prior art keywords
obstacle
data
theoretical
preset
barrier
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN202110946926.XA
Other languages
Chinese (zh)
Other versions
CN113619600A (en
Inventor
林晓生
刘振亚
韩旭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wenyuan Jingxing Beijing Technology Co ltd
Original Assignee
Guangzhou Weride Technology Co Ltd
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 Guangzhou Weride Technology Co Ltd filed Critical Guangzhou Weride Technology Co Ltd
Priority to CN202110946926.XA priority Critical patent/CN113619600B/en
Publication of CN113619600A publication Critical patent/CN113619600A/en
Application granted granted Critical
Publication of CN113619600B publication Critical patent/CN113619600B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • 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
    • 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
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • 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
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4041—Position
    • 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
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4042—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
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics
    • B60W2554/4044—Direction of movement, e.g. backwards

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Human Computer Interaction (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention belongs to the technical field of automatic driving, and discloses a method and a device for diagnosing barrier data, a movable carrier and a storage medium. The method comprises the following steps: acquiring automatic driving data corresponding to the movable carrier; carrying out data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical obstacle; determining position information and stay time length corresponding to each theoretical obstacle according to the data to be identified, and calculating brake acceleration corresponding to each theoretical obstacle according to the data to be identified; diagnosing the theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain actual obstacles; and displaying the data to be identified corresponding to the actual barrier, so that the barrier data in the automatic driving data can be accurately and efficiently automatically diagnosed, the real barrier can be obtained, the efficiency and objectivity of the barrier diagnosis are ensured, and the cost of the data diagnosis is also saved.

Description

Obstacle data diagnosis method, obstacle data diagnosis apparatus, removable carrier, and storage medium
Technical Field
The invention relates to the technical field of automatic driving, in particular to a method and a device for diagnosing barrier data, a movable carrier and a storage medium.
Background
When the automatic driving vehicle is in drive test, the system can sense surrounding obstacles and generate a large amount of obstacle data. These obstacles do not necessarily exist in reality and need to be diagnosed to be discovered. However, manual diagnosis of these data can be costly, inefficient, and subject to subjective differences, and some relatively subtle problems can be missed.
The above is only for the purpose of assisting understanding of the technical aspects of the present invention, and does not represent an admission that the above is prior art.
Disclosure of Invention
The invention mainly aims to provide a method and a device for diagnosing barrier data, a movable carrier and a storage medium, and aims to solve the technical problems of low efficiency and high cost and no objectivity when the barrier data is artificially diagnosed in the prior art.
To achieve the above object, the present invention provides an obstacle data diagnosis method, including the steps of:
acquiring automatic driving data corresponding to a movable carrier;
performing data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical barrier;
determining position information and stay time length corresponding to each theoretical obstacle according to the data to be identified, and calculating brake acceleration corresponding to each theoretical obstacle according to the data to be identified;
diagnosing the theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain actual obstacles;
and displaying the data to be identified corresponding to the actual barrier.
Optionally, before performing data separation on the automatic driving data and obtaining to-be-identified data corresponding to each theoretical obstacle, the method further includes:
acquiring frequency and time information corresponding to each information source in automatic driving data;
performing data alignment based on the time information corresponding to each information source;
judging whether the frequency corresponding to each information source exceeds a preset information source frequency threshold value or not;
when the frequency corresponding to each information source does not exceed the preset information source frequency threshold, performing frame interpolation on the information sources which do not exceed the information source frequency threshold;
and when the frequency corresponding to each information source exceeds the preset information source frequency threshold, performing frame extraction on the information sources exceeding the information source frequency threshold according to preset selection conditions.
Optionally, the diagnosing the theoretical obstacle based on the position information, the staying time and the braking acceleration corresponding to each theoretical obstacle to obtain the actual obstacle includes:
acquiring position information of a movable carrier;
obtaining the relative position between the corresponding movable carrier and each theoretical obstacle based on the position information of the movable carrier and the position information corresponding to each theoretical obstacle;
diagnosing based on the relative position relation and the residence time corresponding to each theoretical barrier to obtain the barrier to be selected;
and diagnosing the barrier to be selected based on the brake acceleration corresponding to the barrier to be selected to obtain the actual barrier.
Optionally, the diagnosing based on the relative position relationship and the residence time corresponding to each theoretical obstacle to obtain the obstacle to be selected includes:
acquiring a preset position relation and a preset time threshold;
judging whether the relative position relation is equal to a preset position relation or not, and acquiring a first theoretical obstacle corresponding to the relative position relation equal to the preset position relation in each theoretical obstacle;
judging whether the stay time corresponding to the first theoretical barrier exceeds the preset time threshold or not, and obtaining the to-be-selected barrier corresponding to the stay time exceeding the preset time threshold in the first theoretical barrier.
Optionally, the diagnosing the obstacle to be selected based on the braking acceleration corresponding to the obstacle to be selected to obtain the actual obstacle includes:
acquiring a preset acceleration threshold;
judging whether the brake acceleration corresponding to the barrier to be selected exceeds the preset acceleration threshold value or not;
obtaining an obstacle with a brake acceleration not exceeding the preset acceleration threshold in the obstacles to be selected;
and taking the obstacle with the brake acceleration not exceeding the preset acceleration threshold value in the obstacles to be selected as an actual obstacle.
Optionally, the calculating, according to the data to be identified, the brake acceleration corresponding to each theoretical obstacle includes:
acquiring a target moving track and a moving speed of a movable carrier;
obtaining target marking points and distances between the movable carrier and each theoretical obstacle according to the data to be identified;
acquiring the driving speed and the driving direction corresponding to each theoretical barrier according to the data to be identified based on the target mark points;
decomposing the driving speed and the position corresponding to each theoretical obstacle based on the driving direction and the distance corresponding to each theoretical obstacle to obtain a decomposition speed and a projection distance corresponding to each theoretical obstacle;
and obtaining the braking acceleration corresponding to each theoretical barrier respectively based on the moving speed, the distance, the decomposition speed and the projection distance.
Optionally, before determining the position information and the stay time corresponding to each theoretical obstacle according to the data to be identified and calculating the brake acceleration corresponding to each theoretical obstacle according to the data to be identified, the method further includes:
classifying each theoretical obstacle in the data to be identified to obtain an initial obstacle type corresponding to each theoretical obstacle;
acquiring a preset theoretical barrier type;
screening each theoretical obstacle based on the preset theoretical obstacle type and the initial obstacle type;
and updating the obstacle corresponding to the initial obstacle type meeting the preset theoretical obstacle type into the theoretical obstacle.
Optionally, the diagnosing the theoretical obstacle based on the position information, the dwell time, and the braking acceleration corresponding to each theoretical obstacle, and after obtaining the actual obstacle, further includes:
acquiring an automatic driving judgment parameter;
performing confidence calculation on the actual obstacles based on the automatic driving judgment parameters to obtain confidence results corresponding to the actual obstacles respectively;
and obtaining the obstacle corresponding to the high confidence coefficient in the confidence coefficient result, and updating the obstacle corresponding to the high confidence coefficient in the confidence coefficient result into an actual obstacle.
In order to achieve the above object, the present invention also provides an obstacle data diagnosis apparatus including:
the data acquisition module is used for acquiring the automatic driving data corresponding to the movable carrier;
the data separation module is used for carrying out data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical barrier;
the data calculation module is used for calculating the position information, the stay time and the brake acceleration which correspond to each theoretical barrier according to the data to be identified;
the data diagnosis module is used for diagnosing theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain actual obstacles;
and the data display module is used for displaying the data to be identified corresponding to the actual barrier.
In addition, to achieve the above object, the present invention further provides a server, comprising: a memory, a processor and an obstacle data diagnostic program stored on the memory and executable on the processor, the obstacle data diagnostic program being configured to implement the steps of the obstacle data diagnostic method as described above.
Further, to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon an obstacle data diagnosis program which, when executed by a processor, implements the steps of the obstacle data diagnosis method as described above.
The automatic driving data corresponding to the movable carrier is obtained; carrying out data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical obstacle; determining position information and dwell time corresponding to each theoretical obstacle according to the data to be identified, and calculating brake acceleration corresponding to each theoretical obstacle according to the data to be identified; diagnosing the theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain actual obstacles; the data to be identified corresponding to the actual barrier are displayed, so that the barrier data in the automatic driving data can be accurately and efficiently diagnosed, the real barrier can be obtained, the efficiency and objectivity of the barrier diagnosis are ensured, the cost of the data diagnosis is saved, and meanwhile, the obtained barrier diagnosis result can also provide support for subsequent data statistics and further provide an objective data statistics result.
Drawings
FIG. 1 is a schematic flow chart of a first embodiment of the obstacle data diagnosis method according to the present invention;
fig. 2 is a flowchart illustrating step S40 of the obstacle data diagnosing method according to the second embodiment of the present invention;
FIG. 3 is a schematic diagram of the relative position between the movable carrier and the theoretical obstacle according to the embodiment of the present invention;
fig. 4 is a flowchart illustrating a step S30 of the obstacle data diagnosis method according to the third embodiment of the present invention;
fig. 5 is a block diagram of an obstacle data diagnosis apparatus according to an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a movable carrier of a hardware operating environment according to an embodiment of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a flowchart illustrating a first embodiment of the obstacle data diagnosis method according to the present invention.
In a first embodiment, the obstacle data diagnosis method includes the steps of:
step S10: and acquiring automatic driving data corresponding to the movable carrier.
It should be noted that the execution subject of the present embodiment is a movable carrier, and the movable carrier may have various expressions, such as a carrier with a moving capability, such as an automobile, a robot, an aircraft, and the like, which is not limited in this embodiment.
It can be understood that, the data acquisition is performed by a camera and a sensor which are arranged on the movable carrier, and a controller of the movable carrier, so as to obtain automatic driving data corresponding to the movable carrier, where the automatic driving data includes, but is not limited to, driving movement data of the movable carrier itself and environment information around the movable carrier, such as obstacle information around the movable carrier, which is obtained.
Step S20: and carrying out data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical barrier.
It should be noted that, the automatic driving data includes, in addition to the data to be identified corresponding to each theoretical obstacle, other data, such as peripheral signal light information data, peripheral road information data, driving movement data of the movable carrier itself, and other data, which is not exemplified in this embodiment.
It can be understood that after the automatic driving data is obtained, data separation needs to be performed on the automatic driving data to obtain an original data structure corresponding to the automatic driving data, an independent data structure is constructed for each theoretical obstacle, all information of each theoretical obstacle needs to be obtained from the automatic driving data structure when the independent data structure is constructed for each theoretical obstacle, then alignment sequencing is performed by using timestamps to generate data structures of a plurality of theoretical obstacles, and finally obtained data structures of the plurality of theoretical obstacles are to-be-identified data corresponding to each theoretical obstacle.
In a specific implementation, because the acquired automatic driving data includes a plurality of types of data, each information source has a certain delay, and the frequencies of the information sources are not necessarily the same, in order to make the subsequent automatic diagnosis process more smooth and accurate, the data cleaning and alignment of the acquired automatic driving data are required, and therefore, in this embodiment, before step S20, the method further includes:
acquiring frequency and time information corresponding to each information source in the automatic driving data; performing data alignment based on the time information corresponding to each information source; judging whether the frequency corresponding to each information source exceeds a preset information source frequency threshold value or not; when the frequency corresponding to each information source does not exceed the preset information source frequency threshold, performing frame interpolation on the information sources which do not exceed the information source frequency threshold; and when the frequency corresponding to each information source exceeds the preset information source frequency threshold, performing frame extraction on the information sources exceeding the information source frequency threshold according to preset selection conditions.
It should be noted that, the data alignment adopts a timestamp alignment manner, acquires time information of each information source in the automatic driving data, and performs data alignment based on the time information of each information source, for example, the currently acquired sensor data of the movable carrier includes 12:03-12:30, but acquiring data related to obstacles around the movable carrier from 12:06-12:30, so sensor data and movable carrier surrounding obstacle related data need to be updated from 12:06, time stamp matching and alignment are carried out, and finally, the data of the two are aligned.
It is to be understood that the preset source frequency threshold refers to a source frequency for data cleansing preset by a mobile carrier administrator or a user, and the preset source frequency threshold set in this embodiment is 10Hz, and may also be other values, which is not limited in this embodiment, and this embodiment is explained by using the preset source frequency threshold as 10Hz.
It should be understood that the preset selection condition refers to a mobile carrier administrator or a condition for performing frame extraction in a preset data washing process, and in this embodiment, the preset selection condition is to select a frame with a closest current timestamp from an information source to be reserved, and extract and remove other redundant frames.
It can be understood that the frequency corresponding to each information source in the automatic driving data is obtained, the data is cleaned according to a preset information source frequency threshold of 10Hz, whether the frequency corresponding to each information source exceeds 10Hz is judged, when the frequency corresponding to the information source is lower than 10Hz, the information source corresponding to the information source lower than 10Hz is subjected to frame interpolation, so that the frequency corresponding to the information source is equal to 10Hz, when the frequency corresponding to the information source exceeds 10Hz, the information source corresponding to the information source higher than 10Hz is subjected to frame extraction according to a preset selection condition, namely, a frame with the closest timestamp in the information source corresponding to the information source higher than 10Hz is selected, and other redundant frames are removed, so that the frequency corresponding to the information source is equal to 10Hz.
Step S30: and determining the position information and the stay time length corresponding to each theoretical obstacle according to the data to be identified, and calculating the braking acceleration corresponding to each theoretical obstacle according to the data to be identified.
It should be noted that the position information refers to geographical position information corresponding to each theoretical obstacle, the stay time length refers to a time length for each theoretical obstacle to stay around the movable carrier, and the brake acceleration corresponding to each theoretical obstacle refers to a brake acceleration a required by the movable carrier to avoid colliding with each theoretical obstacle r 。
It can be understood that the data to be recognized includes, but is not limited to, position information, dwell time, driving speed, driving direction, and type of the obstacle corresponding to each theoretical obstacle, and various information in the data to be recognized is classified and recognized, so that the position information and dwell time corresponding to each theoretical obstacle at present can be determined.
It can be understood that the driving movement data of the movable carrier itself included in the automatic driving data is acquired, and calculation is performed based on the driving movement data of the movable carrier itself and the driving data and the position information of the obstacle, so that the braking acceleration a corresponding to each theoretical obstacle can be obtained r 。
In a specific implementation, because the types of obstacles sensed by the automatic driving are many, some types of obstacles do not need to be tracked and diagnosed, and before actual diagnosis is performed, preliminary screening and filtering are performed on data to be recognized according to the types of the obstacles, so that in this embodiment, before step S30, the method further includes:
classifying each theoretical obstacle in the data to be identified to obtain an initial obstacle type corresponding to each theoretical obstacle; acquiring a preset theoretical barrier type; screening each theoretical obstacle based on the preset theoretical obstacle type and the initial obstacle type; and updating the obstacle of which the initial obstacle type meets the preset theoretical obstacle type into a theoretical obstacle.
It should be noted that the preset theoretical obstacle type refers to a movable carrier administrator or a type for screening theoretical obstacles preset, and the preset theoretical obstacle type includes, but is not limited to, a vehicle, a moving object, and a pedestrian, and may also include other obstacle types having a large influence on automatic driving of the movable carrier, which is not exemplified by the present embodiment.
It can be understood that each theoretical obstacle is classified according to the data to be identified to obtain the obstacle type corresponding to each theoretical obstacle, namely the initial obstacle type, the initial obstacle type is compared with the preset theoretical obstacle to filter the obstacles of which the initial obstacle type does not belong to the preset theoretical obstacle type, and the obstacles left after filtering are updated to the theoretical obstacles.
For example, classifying each theoretical barrier according to data to be identified to obtain initial barrier types of each theoretical barrier, including trees, flowers and plants, fences, running vehicles and pedestrians, screening according to preset theoretical barrier types, filtering out barriers corresponding to the trees, the flowers and the fences, and updating the barriers corresponding to the running vehicles and the pedestrians into the theoretical barriers.
Step S40: and diagnosing the theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain the actual obstacles.
It should be noted that after the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle are obtained, each current theoretical obstacle is automatically diagnosed, and an actual obstacle existing in the data to be identified is obtained.
It can be understood that after the position information and the stay time corresponding to each theoretical obstacle are obtained, the theoretical obstacle of which the position information is not in front of the movable carrier is filtered, after the obstacle of which the position is in front of the movable carrier is obtained, the theoretical obstacle of which the stay time is less than a certain time threshold is filtered according to the condition that the stay time is less than the certain threshold, the rest theoretical obstacles are filtered for three times according to the condition that the brake acceleration is greater than the certain threshold, the theoretical obstacle of which the brake acceleration is greater than the certain speed threshold is filtered, and the finally obtained theoretical obstacle is the actual obstacle.
For example, the preset time threshold is 5 minutes, and the brake acceleration threshold is 5m/s 2 The position of existence of A in each theoretical barrier is the left side of the movable carrier, the stay time is 5 minutes, and the braking acceleration required by the movable carrier to avoid colliding the barrier A is 5m/s 2 The theoretical obstacle B is present in front of the mobile carrier for a dwell time of 2 minutes, the braking acceleration of the mobile carrier required to avoid a collision with the obstacle B being 5m/s 2 The theoretical obstacle C is present in front of the mobile carrier for a dwell time of 5 minutes, the braking acceleration of the mobile carrier required to avoid a collision with the obstacle C being 6m/s 2 The theoretical obstacle D is present in front of the mobile carrier, the dwell time being 5 minutes, the braking acceleration of the mobile carrier required to avoid a collision with the obstacle D being 5m/s 2 According to the actual obstacle existence condition, the movable carrier is positioned in front of the movable carrier and exists for more than 5 minutes, and the braking acceleration is less than 5m/s 2 If the theoretical obstacles a, B, C and D are false detections of automatic driving, the obstacle D is an actual obstacle.
It can be understood that, since many sensed obstacles do not actually affect the automatic driving of the movable carrier, after the obstacle data is diagnosed, it is necessary to perform confidence calculation according to the result, and output the result with high confidence, which is the actual obstacle, so in this embodiment, after step S40, the method further includes:
acquiring an automatic driving judgment parameter; performing confidence calculation on the actual obstacles based on the automatic driving judgment parameters to obtain confidence results corresponding to the actual obstacles respectively; and acquiring the obstacle corresponding to the high confidence degree in the confidence degree result, and updating the obstacle corresponding to the high confidence degree in the confidence degree result into an actual obstacle.
It should be noted that the automatic driving determination parameter refers to a determination parameter that needs to be referred to when performing confidence calculation, and the automatic driving determination parameter includes, but is not limited to, whether an obstacle is in an automatic driving state, whether the obstacle affects a path plan when the movable carrier is automatically driven, and whether a distance between the obstacle and the movable carrier is within a certain distance range.
It can be understood that after the automatic driving judgment parameters are obtained, the confidence degrees corresponding to the actual obstacles are calculated based on the judgment parameters, the result with higher confidence degree is output, the obstacle corresponding to the higher confidence degree is obtained, and the obstacle corresponding to the higher confidence degree in the confidence degree result is updated to be the actual obstacle.
Step S50: and displaying the data to be identified corresponding to the actual barrier.
It should be noted that after the actual obstacle is obtained, the data to be identified corresponding to the actual obstacle is displayed.
The embodiment obtains the automatic driving data corresponding to the movable carrier; carrying out data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical obstacle; determining position information and dwell time corresponding to each theoretical obstacle according to the data to be identified, and calculating brake acceleration corresponding to each theoretical obstacle according to the data to be identified; diagnosing the theoretical obstacles based on the position information, the stay time and the braking acceleration corresponding to each theoretical obstacle to obtain actual obstacles; and displaying the data to be identified corresponding to the actual barrier. According to the method, the obtained automatic driving data are subjected to data separation, the data to be identified corresponding to each theoretical barrier are obtained, the position information, the stay time and the brake acceleration corresponding to each theoretical barrier are obtained based on the data to be identified, the barrier data are diagnosed according to the position information, the stay time and the brake acceleration corresponding to each theoretical barrier, the actual barrier is finally obtained, and the data to be identified corresponding to the actual barrier are displayed, so that the barrier data in the automatic driving data can be accurately and efficiently diagnosed, the real barrier is obtained, the efficiency and the objectivity of the barrier diagnosis are guaranteed, the cost of the data diagnosis is saved, and meanwhile, the obtained barrier diagnosis result can provide support for subsequent data statistics and further provide objective data statistics results.
Referring to fig. 2, fig. 2 is a flowchart illustrating a method for diagnosing obstacle data according to a second embodiment of the present invention.
Based on the above embodiment, the obstacle data diagnosis method in this embodiment specifically includes, in step S40:
s41: position information of the movable carrier is acquired.
It should be noted that the location information of the movable carrier refers to a current location where the movable carrier is located by the movable carrier controller.
S42: and obtaining the relative position between the corresponding movable carrier and each theoretical obstacle based on the position information of the movable carrier and the position information corresponding to each theoretical obstacle.
After obtaining the position information corresponding to each theoretical obstacle, the relative position information between the movable carrier and each obstacle can be obtained based on the position information of the movable carrier. For example, as shown in fig. 3, the relative position of the theoretical obstacle E and the movable carrier is such that the theoretical obstacle E is located in front of the movable carrier, and the relative position between the theoretical obstacle F and the movable carrier is such that the theoretical obstacle F is located on the right side of the movable carrier.
S43: and diagnosing based on the relative position relation and the residence time corresponding to each theoretical obstacle to obtain the obstacle to be selected.
The candidate obstacles refer to theoretical obstacles left after preliminary screening according to the residence time and the relative position in each theoretical obstacle.
It can be understood that, since the obstacle located in front of the movable carrier has the largest influence on the automatic driving of the movable carrier, and meanwhile, if the obstacle does not really exist, the existence time of the obstacle is usually short, after the relative position relationship and the stay time corresponding to each theoretical obstacle are obtained, each theoretical obstacle is screened according to the condition that the relative position is located in front of the movable carrier and the existence time is greater than the preset time threshold, so as to obtain the obstacle to be selected, in this embodiment, step S43 may specifically include:
acquiring a preset position relation and a preset time threshold; judging whether the relative position relation is equal to a preset position relation or not, and acquiring a first theoretical obstacle corresponding to the relative position relation equal to the preset position relation in each theoretical obstacle; judging whether the stay time corresponding to the first theoretical barrier exceeds the preset time threshold or not, and obtaining the to-be-selected barrier corresponding to the stay time exceeding the preset time threshold in the first theoretical barrier.
It should be noted that the preset position and preset duration threshold relationship refers to a mobile carrier administrator or a preset position and duration condition for screening a candidate obstacle, and in this embodiment, the preset position relationship refers to that a theoretical obstacle is located in front of the mobile carrier. The preset time threshold is adjusted according to the sensitivity of different automatic driving sensing systems, when the automatic driving sensing systems are sensitive to the detection of the obstacles, the preset time threshold is smaller, and when the automatic driving sensing systems are less sensitive to the detection of the obstacles, the preset time threshold is larger.
It can be understood that after the relative position relationship between each theoretical obstacle and the movable carrier and the stay time corresponding to each theoretical obstacle are obtained, each theoretical obstacle is primarily screened based on the preset position relationship and the relative position relationship to obtain a first theoretical obstacle meeting the condition that the relative position relationship is equal to the preset position relationship among the theoretical obstacles, and then the first theoretical obstacle is secondarily screened based on the stay time corresponding to each obstacle and the preset time threshold to obtain an obstacle to be selected, wherein the stay time of the obstacle to be selected is greater than the preset time threshold, and the obstacle to be selected is selected.
For example, the preset positional relationship is that a theoretical obstacle is located in front of the movable carrier, the preset time threshold is 2 minutes, the relative positional relationship between the theoretical obstacle G and the movable carrier in the theoretical obstacle is that the theoretical obstacle G is located in front of the movable carrier, the dwell time of the theoretical obstacle G is 5 minutes, the relative positional relationship between the theoretical obstacle H and the movable carrier is that the theoretical obstacle H is located on the right side of the movable carrier, the dwell time of the theoretical obstacle H is 5 minutes, the relative positional relationship between the theoretical obstacle I and the movable carrier is that the theoretical obstacle I is located on the left side of the movable carrier, the dwell time of the theoretical obstacle I is 5 minutes, the relative positional relationship between the theoretical obstacle J and the movable carrier is that the theoretical obstacle J is located in front of the movable carrier, the dwell time of the theoretical obstacle J is 1 minute, the relative positional relationship between the theoretical obstacle K and the movable carrier is that the theoretical obstacle K is located in front of the movable carrier, the theoretical obstacle K is 3 minutes, the theoretical obstacle K and the theoretical obstacle K is screened based on the preset positional relationship, the theoretical obstacle K is obtained on the theoretical obstacle G, the theoretical obstacle K is greater than the preset positional relationship, the theoretical obstacle K, the theoretical obstacle G, the theoretical obstacle is obtained on the first theoretical obstacle.
S44: and diagnosing the barrier to be selected based on the brake acceleration corresponding to the barrier to be selected to obtain the actual barrier.
It should be noted that after the obstacle to be selected is obtained, the braking acceleration corresponding to the obstacle to be selected is obtained, and the obstacle to be selected is diagnosed based on the braking acceleration corresponding to the obstacle to be selected, so as to obtain the actual obstacle.
It can be understood that, when an obstacle really exists, the braking acceleration corresponding to the candidate obstacle should not exceed the preset acceleration threshold, and when diagnosing the candidate obstacle based on the braking acceleration corresponding to the candidate obstacle, an accurate result needs to be obtained according to the preset acceleration threshold, and therefore, in this embodiment, step S44 may specifically include:
acquiring a preset acceleration threshold; judging whether the brake acceleration corresponding to the barrier to be selected exceeds the preset acceleration threshold value or not; obtaining an obstacle with a brake acceleration not exceeding the preset acceleration threshold in the obstacles to be selected; and taking the obstacle with the brake acceleration not exceeding the preset acceleration threshold value in the obstacles to be selected as an actual obstacle.
It should be noted that the preset acceleration threshold refers to a mobile carrier administrator or a preset vehicle acceleration condition for screening actual obstacles, the setting of the acceleration threshold is adjusted according to a large number of positive examples and negative examples, and the braking acceleration threshold is generally located at 1m/s 2 ～5m/s 2 In the embodiment, the preset acceleration threshold value is 5m/s 2 The description is given.
It can be understood that after the preset acceleration threshold is obtained, the obstacle to be selected is diagnosed and screened according to the preset acceleration threshold and the brake acceleration corresponding to each theoretical obstacle, and an actual obstacle with the brake acceleration smaller than the preset acceleration threshold in the obstacle to be selected is obtained.
For example, the brake acceleration corresponding to the candidate obstacle L in the candidate obstacles is 7m/s 2 The brake acceleration corresponding to the barrier M to be selected is 4M/s 2 The brake acceleration corresponding to the candidate barrier N is 5m/s 2 And diagnosing and screening the obstacles to be selected based on the preset acceleration threshold and the brake acceleration corresponding to each theoretical obstacle to obtain the actual obstacles M and N which meet the condition that the brake acceleration does not exceed the preset acceleration threshold in the theoretical obstacles.
The embodiment obtains the position information of the movable carrier; obtaining the relative position between the corresponding movable carrier and each theoretical obstacle based on the position information of the movable carrier and the position information corresponding to each theoretical obstacle; diagnosing based on the relative position relation and the residence time corresponding to each theoretical barrier to obtain the barrier to be selected; and diagnosing the barrier to be selected based on the brake acceleration corresponding to the barrier to be selected to obtain the actual barrier. The method comprises the steps of obtaining the relative position relation between a movable carrier and each theoretical barrier and the residence time corresponding to each theoretical barrier, conducting preliminary diagnosis on each theoretical barrier to obtain a barrier to be selected, conducting secondary diagnosis on the barrier to be selected based on the brake acceleration corresponding to the barrier to be selected to obtain an actual barrier, and guaranteeing the accuracy and objectivity of a diagnosis result through multiple barrier data diagnosis conditions.
Referring to fig. 4, fig. 4 is a flowchart illustrating a method for diagnosing obstacle data according to a third embodiment of the present invention.
Based on the above embodiment, the obstacle data diagnosis method in this embodiment specifically includes, in step S30:
s31: and determining the position information and the stay time corresponding to each theoretical obstacle according to the data to be identified, and acquiring the target moving track and the moving speed of the movable carrier.
It should be noted that the target movement track refers to a target planned path of the movable carrier, and the movement speed refers to a current driving speed v of the movable carrier e 。
S32: and obtaining target marking points and distances between the movable carrier and each theoretical obstacle according to the data to be identified.
The target mark points refer to a point np closest to each theoretical obstacle in the target planned path of the movable carrier and a direction ori of the target mark point np, and the distance refers to a distance d from a starting point of the target planned path of the movable carrier to the target mark point np p 。
It can be understood that the target mark points and distances between the movable carrier and each theoretical obstacle can be obtained according to the position information of each theoretical obstacle in the data to be identified.
S33: and acquiring the driving speed and the driving direction corresponding to each theoretical obstacle according to the data to be identified based on the target mark points.
It should be noted that, according to the driving data of each theoretical obstacle in the data to be identified, the driving speed and the driving direction corresponding to each theoretical obstacle can be obtained, and the vector data of each theoretical obstacle during driving can be obtained.
S34: and decomposing the driving speed and the position corresponding to each theoretical obstacle based on the driving direction and the distance corresponding to each theoretical obstacle to obtain the decomposition speed and the projection distance corresponding to each theoretical obstacle.
The decomposition speed corresponding to each theoretical obstacle is a speed obtained by decomposing the travel speed of each theoretical obstacle based on the direction ori and the travel direction of the target mark point, and the projection distance corresponding to each theoretical obstacle is a projection distance obtained by projecting the position of each theoretical obstacle based on the direction ori of the target mark point.
It can be understood that the velocity of each theoretical obstacle is decomposed in the direction ori of the target mark point to obtain a decomposition velocity v in the x direction ox (front end of movable carrier facing direction), and the decomposition speed in y direction is v oy (movable carrier front vertical direction). Projecting the position of each theoretical barrier on the orientation ori of the target mark point to obtain the projection distance d of each theoretical barrier in the y direction (the direction vertical to the front end of the movable carrier) y 。
S35: and obtaining the braking acceleration corresponding to each theoretical barrier respectively based on the moving speed, the distance, the decomposition speed and the projection distance.
In addition, the moving speed v is obtained e Distance d p And the decomposition velocity v ox 、v oy And a projection distance d y Then based on the moving speed v e Distance d p Decomposition velocity v ox 、v oy And a projection distance d y The brake acceleration a corresponding to each theoretical barrier can be obtained r 。
It will be appreciated that the movable carrier is targetedDistance d from starting point of planned path to target mark point np p Adding to the x direction (direction toward which the front end of the movable carrier faces) to obtain d x Finally, the brake acceleration a corresponding to each theoretical obstacle is obtained r Comprises the following steps:
Figure BDA0003216042380000141
the embodiment obtains the target moving track and the moving speed of the movable carrier; obtaining target mark points and distances between the movable carrier and each theoretical obstacle according to the data to be identified; acquiring the driving speed and the driving direction corresponding to each theoretical obstacle according to the data to be identified based on the target mark points; decomposing the driving speed and the position corresponding to each theoretical obstacle based on the driving direction and the distance corresponding to each theoretical obstacle to obtain the decomposition speed and the projection distance corresponding to each theoretical obstacle; and obtaining the brake acceleration corresponding to each theoretical barrier based on the moving speed, the distance, the decomposition speed and the projection distance, and obtaining the accurate brake acceleration corresponding to each theoretical barrier, so that the subsequent barrier data diagnosis process is more accurate and objective.
Further, referring to fig. 5, an obstacle data diagnosis apparatus according to an embodiment of the present invention includes:
the data acquisition module 10 is used for acquiring the automatic driving data corresponding to the movable carrier;
the data separation module 20 is configured to perform data separation on the automatic driving data to obtain to-be-identified data corresponding to each theoretical obstacle;
the data calculation module 30 is configured to calculate, according to the data to be identified, position information, a dwell time, and a brake acceleration that correspond to each theoretical obstacle;
the data diagnosis module 40 is used for diagnosing theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain actual obstacles;
and the data display module 50 is configured to display the data to be identified corresponding to the actual obstacle.
The embodiment obtains the automatic driving data corresponding to the movable carrier; performing data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical barrier; determining position information and stay time length corresponding to each theoretical obstacle according to the data to be identified, and calculating brake acceleration corresponding to each theoretical obstacle according to the data to be identified; diagnosing the theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain actual obstacles; and displaying the data to be identified corresponding to the actual barrier. According to the method, the obtained automatic driving data are subjected to data separation to obtain the data to be identified corresponding to each theoretical obstacle, the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle are obtained based on the data to be identified, obstacle data diagnosis is carried out according to the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle, the actual obstacle is finally obtained, and the data to be identified corresponding to the actual obstacle is displayed, so that the obstacle data in the automatic driving data can be accurately and efficiently diagnosed, the real obstacle is obtained, the efficiency and the objectivity of obstacle diagnosis are guaranteed, the cost of data diagnosis is saved, meanwhile, the obtained obstacle diagnosis result can also provide support for subsequent data statistics, and objective data statistics results are provided.
Referring to fig. 6, fig. 6 is a schematic diagram of a movable carrier structure of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 6, the movable carrier may include: a processor 1001, such as a CPU, a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to implement connection communication among these components. The user interface 1003 may include a Display (Display), an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., a WI-FI interface). The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a storage device separate from the processor 1001.
Those skilled in the art will appreciate that the configuration shown in fig. 6 does not constitute a limitation of the movable carrier, and may include more or fewer components than those shown, or some components in combination, or a different arrangement of components.
As shown in fig. 6, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and an obstacle data diagnosis program.
In the removable carrier shown in fig. 6, the network interface 1004 is mainly used for data communication with an external network; the user interface 1003 is mainly used for receiving an input instruction of a user; the removable carrier calls the obstacle data diagnosis program stored in the memory 1005 by the processor 1001, and performs the following operations:
acquiring automatic driving data corresponding to the movable carrier;
carrying out data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical obstacle;
determining position information and stay time length corresponding to each theoretical obstacle according to the data to be identified, and calculating brake acceleration corresponding to each theoretical obstacle according to the data to be identified;
diagnosing the theoretical obstacles based on the position information, the stay time and the braking acceleration corresponding to each theoretical obstacle to obtain actual obstacles;
and displaying the data to be identified corresponding to the actual barrier.
Further, the processor 1001 may call the obstacle data diagnosis program stored in the memory 1005, and also perform the following operations:
acquiring frequency and time information corresponding to each information source in the automatic driving data;
performing data alignment based on the time information corresponding to each information source;
judging whether the frequency corresponding to each information source exceeds a preset information source frequency threshold value or not;
when the frequency corresponding to each information source does not exceed the preset information source frequency threshold, performing frame interpolation on the information sources which do not exceed the information source frequency threshold;
and when the frequency corresponding to each information source exceeds the preset information source frequency threshold, performing frame extraction on the information sources exceeding the information source frequency threshold according to preset selection conditions.
Further, the processor 1001 may call the obstacle data diagnosis program stored in the memory 1005, and also perform the following operations:
acquiring position information of a movable carrier;
obtaining the relative position between the corresponding movable carrier and each theoretical obstacle based on the position information of the movable carrier and the position information corresponding to each theoretical obstacle;
diagnosing based on the relative position relation and the residence time corresponding to each theoretical obstacle to obtain the obstacle to be selected;
and diagnosing the barrier to be selected based on the brake acceleration corresponding to the barrier to be selected to obtain the actual barrier.
Further, the processor 1001 may call the obstacle data diagnosis program stored in the memory 1005, and also perform the following operations:
acquiring a preset position relation and a preset time threshold;
judging whether the relative position relation is equal to a preset position relation or not, and acquiring a first theoretical obstacle corresponding to the relative position relation equal to the preset position relation in each theoretical obstacle;
judging whether the stay time corresponding to the first theoretical barrier exceeds the preset time threshold or not, and obtaining the to-be-selected barrier corresponding to the stay time exceeding the preset time threshold in the first theoretical barrier.
Further, the processor 1001 may call the obstacle data diagnosis program stored in the memory 1005, and also perform the following operations:
acquiring a preset acceleration threshold;
judging whether the brake acceleration corresponding to the barrier to be selected exceeds the preset acceleration threshold value or not;
obtaining an obstacle with a brake acceleration not exceeding the preset acceleration threshold in the obstacles to be selected;
and taking the obstacle with the brake acceleration not exceeding the preset acceleration threshold value in the obstacles to be selected as an actual obstacle.
Further, the processor 1001 may call the obstacle data diagnosis program stored in the memory 1005, and also perform the following operations:
acquiring a target moving track and a moving speed of a movable carrier;
obtaining target marking points and distances between the movable carrier and each theoretical obstacle according to the data to be identified;
acquiring the driving speed and the driving direction corresponding to each theoretical obstacle according to the data to be identified based on the target mark points;
decomposing the driving speed and the position corresponding to each theoretical obstacle based on the driving direction and the distance corresponding to each theoretical obstacle to obtain a decomposition speed and a projection distance corresponding to each theoretical obstacle;
and obtaining the braking acceleration corresponding to each theoretical obstacle based on the moving speed, the distance, the decomposition speed and the projection distance.
Further, the processor 1001 may call the obstacle data diagnosis program stored in the memory 1005, and also perform the following operations:
classifying each theoretical obstacle in the data to be identified to obtain an initial obstacle type corresponding to each theoretical obstacle;
acquiring a preset theoretical barrier type;
screening each theoretical obstacle based on the preset theoretical obstacle type and the initial obstacle type;
and updating the obstacle corresponding to the initial obstacle type meeting the preset theoretical obstacle type into the theoretical obstacle.
Further, the processor 1001 may call the obstacle data diagnosis program stored in the memory 1005, and also perform the following operations:
acquiring an automatic driving judgment parameter;
performing confidence calculation on the actual obstacles based on the automatic driving judgment parameters to obtain confidence results corresponding to the actual obstacles respectively;
and obtaining the obstacle corresponding to the high confidence coefficient in the confidence coefficient result, and updating the obstacle corresponding to the high confidence coefficient in the confidence coefficient result into an actual obstacle.
According to the method, the acquired automatic driving data are subjected to data separation to obtain the data to be identified corresponding to each theoretical obstacle, the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle are obtained based on the data to be identified, obstacle data diagnosis is performed according to the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle, the actual obstacle is finally obtained, and the data to be identified corresponding to the actual obstacle is displayed, so that the obstacle data in the automatic driving data can be accurately and efficiently diagnosed, the real obstacle is obtained, the efficiency and the objectivity of the obstacle diagnosis are guaranteed, the cost of the data diagnosis is saved, and meanwhile, the obtained obstacle diagnosis result can provide support for subsequent data statistics and further provide objective data statistics results.
Furthermore, an embodiment of the present invention further provides a computer-readable storage medium, where an obstacle data diagnosis program is stored, and when executed by a processor, the obstacle data diagnosis program implements the following operations:
acquiring automatic driving data corresponding to the movable carrier;
performing data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical barrier;
determining position information and stay time length corresponding to each theoretical obstacle according to the data to be identified, and calculating brake acceleration corresponding to each theoretical obstacle according to the data to be identified;
diagnosing the theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain actual obstacles;
and displaying the data to be identified corresponding to the actual barrier.
According to the method, the acquired automatic driving data are subjected to data separation to obtain the data to be identified corresponding to each theoretical obstacle, the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle are obtained based on the data to be identified, obstacle data diagnosis is performed according to the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle, the actual obstacle is finally obtained, and the data to be identified corresponding to the actual obstacle is displayed, so that the obstacle data in the automatic driving data can be accurately and efficiently diagnosed, the real obstacle is obtained, the efficiency and the objectivity of the obstacle diagnosis are guaranteed, the cost of the data diagnosis is saved, and meanwhile, the obtained obstacle diagnosis result can provide support for subsequent data statistics and further provide objective data statistics results.
It should be noted that, when being executed by a processor, the computer-readable storage medium may also implement the steps in the method, and achieve the corresponding technical effects, which is not described herein again.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are only for description, and do not represent the advantages and disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) as described above and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.

Claims (10)

1. An obstacle data diagnosis method characterized by comprising:
acquiring automatic driving data corresponding to the movable carrier;
carrying out data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical obstacle;
determining position information and stay time length corresponding to each theoretical obstacle according to the data to be identified, and calculating brake acceleration corresponding to each theoretical obstacle according to the data to be identified;
diagnosing the theoretical obstacles based on the position information, the stay time and the braking acceleration corresponding to each theoretical obstacle to obtain actual obstacles;
displaying the data to be identified corresponding to the actual barrier;
the method for diagnosing the theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain the actual obstacle comprises the following steps:
acquiring position information of a movable carrier;
obtaining the relative position between the corresponding movable carrier and each theoretical obstacle based on the position information of the movable carrier and the position information corresponding to each theoretical obstacle;
diagnosing based on the relative position and the residence time corresponding to each theoretical obstacle to obtain the obstacle to be selected;
and diagnosing the barrier to be selected based on the brake acceleration corresponding to the barrier to be selected to obtain the actual barrier.
2. The obstacle data diagnosis method according to claim 1, wherein before the data separation of the automatic driving data and the acquisition of the data to be recognized corresponding to each theoretical obstacle, the method further comprises:
acquiring frequency and time information corresponding to each information source in the automatic driving data;
performing data alignment based on the time information corresponding to each information source;
judging whether the frequency corresponding to each information source exceeds a preset information source frequency threshold value or not;
when the frequency corresponding to each information source does not exceed the preset information source frequency threshold, performing frame interpolation on the information sources which do not exceed the information source frequency threshold;
and when the frequency corresponding to each information source exceeds the preset information source frequency threshold, performing frame extraction on the information sources exceeding the information source frequency threshold according to preset selection conditions.
3. The obstacle data diagnosis method according to claim 1, wherein the diagnosing based on the relative position and the stay time corresponding to each theoretical obstacle to obtain the obstacle to be selected includes:
acquiring a preset position and a preset time threshold;
judging whether the relative position is equal to a preset position or not, and acquiring a first theoretical obstacle corresponding to the relative position equal to the preset position in each theoretical obstacle;
judging whether the stay time corresponding to the first theoretical barrier exceeds the preset time threshold or not, and obtaining the to-be-selected barrier corresponding to the stay time exceeding the preset time threshold in the first theoretical barrier.
4. The obstacle data diagnosis method according to claim 3, wherein the diagnosing the obstacle to be selected based on the brake acceleration corresponding to the obstacle to be selected to obtain the actual obstacle comprises:
acquiring a preset acceleration threshold;
judging whether the brake acceleration corresponding to the barrier to be selected exceeds the preset acceleration threshold value or not;
obtaining an obstacle with a brake acceleration not exceeding the preset acceleration threshold in the obstacles to be selected;
and taking the obstacle with the brake acceleration not exceeding the preset acceleration threshold value in the obstacles to be selected as an actual obstacle.
5. The obstacle data diagnosis method according to claim 1, wherein the calculating of the braking acceleration corresponding to each theoretical obstacle from the data to be recognized includes:
acquiring a target moving track and a moving speed of a movable carrier;
obtaining target marking points and distances between the movable carrier and each theoretical obstacle according to the data to be identified;
acquiring the driving speed and the driving direction corresponding to each theoretical obstacle according to the data to be identified based on the target mark points;
decomposing the driving speed and the position corresponding to each theoretical obstacle based on the driving direction and the distance corresponding to each theoretical obstacle to obtain the decomposition speed and the projection distance corresponding to each theoretical obstacle;
and obtaining the braking acceleration corresponding to each theoretical obstacle based on the moving speed, the distance, the decomposition speed and the projection distance.
6. The obstacle data diagnosis method according to claim 1, wherein before determining the position information and the stay time length corresponding to each theoretical obstacle according to the data to be identified and calculating the brake acceleration corresponding to each theoretical obstacle according to the data to be identified, the method further comprises:
classifying each theoretical obstacle in the data to be identified to obtain an initial obstacle type corresponding to each theoretical obstacle;
acquiring a preset theoretical obstacle type;
screening each theoretical obstacle based on the preset theoretical obstacle type and the initial obstacle type;
and updating the obstacle of which the initial obstacle type meets the preset theoretical obstacle type into a theoretical obstacle.
7. The obstacle data diagnosis method according to claim 1, wherein the diagnosing theoretical obstacles based on the position information, the stay time, and the braking acceleration corresponding to each theoretical obstacle, after obtaining the actual obstacle, further comprises:
acquiring an automatic driving judgment parameter;
performing confidence calculation on the actual obstacles based on the automatic driving judgment parameters to obtain confidence results corresponding to the actual obstacles respectively;
and obtaining the obstacle corresponding to the high confidence coefficient in the confidence coefficient result, and updating the obstacle corresponding to the high confidence coefficient in the confidence coefficient result into an actual obstacle.
8. An obstacle data diagnosis apparatus characterized by comprising:
the data acquisition module is used for acquiring the automatic driving data corresponding to the movable carrier;
the data separation module is used for carrying out data separation on the automatic driving data to obtain data to be identified corresponding to each theoretical obstacle;
the data calculation module is used for calculating the position information, the stay time and the brake acceleration which correspond to each theoretical obstacle according to the data to be identified;
the data diagnosis module is used for diagnosing theoretical obstacles based on the position information, the stay time and the brake acceleration corresponding to each theoretical obstacle to obtain actual obstacles;
the data display module is used for displaying the data to be identified corresponding to the actual barrier;
the data diagnosis module is used for acquiring the position information of the movable carrier;
obtaining the relative position between the corresponding movable carrier and each theoretical obstacle based on the position information of the movable carrier and the position information corresponding to each theoretical obstacle;
diagnosing based on the relative position and the residence time corresponding to each theoretical obstacle to obtain the obstacle to be selected;
and diagnosing the barrier to be selected based on the brake acceleration corresponding to the barrier to be selected to obtain the actual barrier.
9. A movable carrier, characterized in that the movable carrier comprises: a memory, a processor, and an obstacle data diagnostic program stored on the memory and executable on the processor, the obstacle data diagnostic program configured to implement the obstacle data diagnostic method of any one of claims 1 to 7.
10. A storage medium, characterized in that the storage medium has stored thereon an obstacle data diagnosis program which, when executed by a processor, realizes the obstacle data diagnosis method according to any one of claims 1 to 7.
CN202110946926.XA 2021-08-17 2021-08-17 Obstacle data diagnosis method, obstacle data diagnosis device, movable carrier, and storage medium Active CN113619600B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110946926.XA CN113619600B (en) 2021-08-17 2021-08-17 Obstacle data diagnosis method, obstacle data diagnosis device, movable carrier, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110946926.XA CN113619600B (en) 2021-08-17 2021-08-17 Obstacle data diagnosis method, obstacle data diagnosis device, movable carrier, and storage medium

Publications (2)

Publication Number Publication Date
CN113619600A CN113619600A (en) 2021-11-09
CN113619600B true CN113619600B (en) 2022-11-15

Family

ID=78386263

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110946926.XA Active CN113619600B (en) 2021-08-17 2021-08-17 Obstacle data diagnosis method, obstacle data diagnosis device, movable carrier, and storage medium

Country Status (1)

Country Link
CN (1) CN113619600B (en)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20180072139A (en) * 2016-12-21 2018-06-29 현대자동차주식회사 Vehicle and method for controlling thereof
CN108733060A (en) * 2018-06-05 2018-11-02 北京智行者科技有限公司 A kind of processing method of operation cartographic information
CN111619560B (en) * 2020-07-29 2020-11-03 北京三快在线科技有限公司 Vehicle control method and device
CN112329552B (en) * 2020-10-16 2023-07-14 爱驰汽车（上海）有限公司 Obstacle detection method and device based on automobile
CN112462368B (en) * 2020-11-25 2022-07-12 中国第一汽车股份有限公司 Obstacle detection method and device, vehicle and storage medium

Also Published As

Publication number Publication date
CN113619600A (en) 2021-11-09

Similar Documents

Publication Publication Date Title
KR102198724B1 (en) Method and apparatus for processing point cloud data
CN111753612B (en) Method and device for detecting casting object and storage medium
CN111780987B (en) Test method and device for automatic driving vehicle, computer equipment and storage medium
CN110751012B (en) Target detection evaluation method and device, electronic equipment and storage medium
CN105702152A (en) Map generation method and device
DE112018004953T5 (en) INFORMATION PROCESSING DEVICE, INFORMATION PROCESSING PROCESS, PROGRAM AND MOVING BODY
CN110341621B (en) Obstacle detection method and device
CN113433548B (en) Data monitoring method, device, equipment and storage medium
CN113189989B (en) Vehicle intention prediction method, device, equipment and storage medium
CN114639085A (en) Traffic signal lamp identification method and device, computer equipment and storage medium
CN113255444A (en) Training method of image recognition model, image recognition method and device
CN112784817B (en) Method, device and equipment for detecting lane where vehicle is located and storage medium
WO2024098992A1 (en) Vehicle reversing detection method and apparatus
CN113762079A (en) Environment data processing method, device, equipment and storage medium
CN113619600B (en) Obstacle data diagnosis method, obstacle data diagnosis device, movable carrier, and storage medium
CN113435350A (en) Traffic marking detection method, device, equipment and medium
CN113536867B (en) Object identification method, device and system
CN113361299A (en) Abnormal parking detection method and device, storage medium and electronic equipment
CN115019508B (en) Road monitoring traffic flow simulation method, device, equipment and medium based on machine learning
CN108399357B (en) Face positioning method and device
CN115249407A (en) Indicating lamp state identification method and device, electronic equipment, storage medium and product
CN108363985B (en) Target object perception system testing method and device and computer readable storage medium
CN114821553A (en) Welt control method and device for working machine, working machine and electronic equipment
US12125222B1 (en) Systems for determining and reporting vehicle following distance
US20230025579A1 (en) High-definition mapping

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20231121

Address after: Building 1801, Building 1, No. 2 South Ronghua Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing, 100176

Patentee after: Wenyuan Jingxing (Beijing) Technology Co.,Ltd.

Address before: Room 687, No. 333, jiufo Jianshe Road, Zhongxin Guangzhou Knowledge City, Guangzhou, Guangdong 510000

Patentee before: Guangzhou WeRide Technology Limited Company