CN116513175B - Correction method, device, equipment and medium for driving deviation in automatic driving - Google Patents

Correction method, device, equipment and medium for driving deviation in automatic driving Download PDF

Info

Publication number
CN116513175B
CN116513175B CN202310797707.9A CN202310797707A CN116513175B CN 116513175 B CN116513175 B CN 116513175B CN 202310797707 A CN202310797707 A CN 202310797707A CN 116513175 B CN116513175 B CN 116513175B
Authority
CN
China
Prior art keywords
deviation
dimension
lane line
vehicle
real
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
CN202310797707.9A
Other languages
Chinese (zh)
Other versions
CN116513175A (en
Inventor
刘羿
何贝
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.)
Beijing Sinian Zhijia Technology Co ltd
Original Assignee
Beijing Sinian Zhijia 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 Beijing Sinian Zhijia Technology Co ltd filed Critical Beijing Sinian Zhijia Technology Co ltd
Priority to CN202310797707.9A priority Critical patent/CN116513175B/en
Publication of CN116513175A publication Critical patent/CN116513175A/en
Application granted granted Critical
Publication of CN116513175B publication Critical patent/CN116513175B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/10—Path keeping
    • B60W30/12—Lane keeping
    • 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
    • B60W60/0025—Planning or execution of driving tasks specially adapted for specific operations
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
    • G01M17/00—Testing of vehicles
    • G01M17/007—Wheeled or endless-tracked vehicles

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Steering Control In Accordance With Driving Conditions (AREA)

Abstract

The application provides a method, a device, equipment and a medium for correcting driving deviation in automatic driving, which comprise the following steps: performing real vehicle testing on the automatic driving system aiming at the deviation dimension related to the driving deviation of the lane line in the automatic driving to control the tested vehicle to keep steady-state driving along the target lane line in the high-precision map; according to the real vehicle test data in steady-state driving, determining whether lane line driving deviation in the real vehicle test process is required to be corrected in a deviation dimension; if so, determining a correction parameter under the deviation dimension according to the real vehicle test data, and correcting the automatic driving system according to the correction parameter under the deviation dimension. Therefore, the error of driving deviating from the lane line caused by deviation dimensions including steering zero deviation, vehicle positioning angle deviation, high-precision map lane line deviation and vehicle positioning transverse deviation can be effectively eliminated, so that the lane line keeping precision is improved, and the requirement of driving strictly along a specific lane line is met.

Description

Correction method, device, equipment and medium for driving deviation in automatic driving
Technical Field
The application relates to the technical field of automatic driving, in particular to a method, a device, equipment and a medium for correcting driving deviation in automatic driving.
Background
Under certain application scenes, the automatic driving vehicle based on the high-precision map has a severe requirement for running on a specific lane line, for example, a road on a wharf is narrow, the left and right distance between the automatic driving vehicle and the lane boundary is only about 10-15 cm when the automatic driving vehicle runs along the lane center line, and at the moment, slight deviation from the lane center line is obvious, and even line pressing occurs. In the automatic driving process, the vehicles calibrated in the prior art often have a certain deviation from the lane center line, cannot strictly run along the lane center line, and cannot meet the requirement of running along the specific lane line in the application scenes.
Disclosure of Invention
Accordingly, the present application is directed to a method, apparatus, device and medium for correcting driving deviation in automatic driving, which can effectively eliminate driving deviation errors caused by deviation dimensions including steering zero deviation, vehicle positioning angle deviation, high-precision map lane line deviation and vehicle positioning transverse deviation, thereby improving lane line keeping accuracy and meeting the requirement of driving strictly along specific lane lines.
The embodiment of the application provides a correction method of driving deviation in automatic driving, which comprises the following steps:
performing real vehicle testing on the automatic driving system aiming at the deviation dimension related to the driving deviation of the lane line in the automatic driving to control the tested vehicle to keep steady-state driving along the target lane line in the high-precision map; wherein the deviation dimension comprises at least one of: steering zero offset dimension, vehicle positioning angle offset dimension, high-precision map lane line deviation dimension and vehicle positioning transverse offset dimension;
according to the real vehicle test data in steady-state driving, determining whether lane line driving deviation in the real vehicle test process is required to be corrected in the deviation dimension;
and if so, determining a correction parameter under the deviation dimension according to the real vehicle test data, and correcting the automatic driving system according to the correction parameter under the deviation dimension.
Further, when the deviation dimension includes the steering zero deviation dimension, the real vehicle test data includes a steering instruction value issued by the automatic driving system;
according to the real vehicle test data during steady-state driving, determining whether the lane line driving deviation occurring in the real vehicle test process needs to be corrected under the deviation dimension comprises the following steps:
When the steering instruction value issued by the automatic driving system is not zero, determining that the lane line driving deviation occurring in the real vehicle testing process needs to be corrected in the steering zero deviation dimension;
the method for determining the correction parameters in the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters in the deviation dimension comprises the following steps:
determining an average value of steering command values within a predetermined interval as a correction parameter in the steering zero offset dimension;
and inverting the correction parameter under the steering zero-offset dimension and compensating the correction parameter to a steering instruction value issued by the automatic driving system.
Further, when the deviation dimension includes the vehicle localization angle deviation dimension, the real vehicle test data includes a travel track recorded in the automatic driving system;
according to the real vehicle test data during steady-state driving, determining whether the lane line driving deviation occurring in the real vehicle test process needs to be corrected under the deviation dimension comprises the following steps:
determining a deviation angle between a driving track recorded in the automatic driving system and the target lane line;
when the deviation angle is not zero, determining that lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the vehicle positioning angle deviation dimension;
The method for determining the correction parameters in the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters in the deviation dimension comprises the following steps:
determining an average value of the deviation angles within a predetermined section as a correction parameter in the vehicle localization angle deviation dimension;
and compensating the correction parameters under the deviation dimension of the vehicle positioning angle to the orientation feedback value of the vehicle positioning in the automatic driving system after inverting the correction parameters.
Further, when the deviation dimension includes the high-precision map lane line deviation dimension, the real vehicle test data includes a real lane position corresponding to the real physical world of the target lane line, a forward running track generated by the test vehicle in the real physical world during forward running, and a reverse running track generated by the test vehicle in the real physical world during reverse running;
according to the real vehicle test data during steady-state driving, determining whether the lane line driving deviation occurring in the real vehicle test process needs to be corrected under the deviation dimension comprises the following steps:
determining an average forward lateral deviation between the forward travel trajectory and the real lane position, and an average reverse lateral deviation between the reverse travel trajectory and the real lane position;
When the sum of the average forward transverse deviation and the average reverse transverse deviation is not zero, determining that lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the lane line deviation dimension of the high-precision map;
the method for determining the correction parameters in the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters in the deviation dimension comprises the following steps:
determining half of the sum of the average forward lateral deviation and the average reverse lateral deviation as a correction parameter in the high-precision map lane line deviation dimension;
and inverting the correction parameters under the lane line deviation dimension of the high-precision map and compensating the correction parameters to the target lane line in the high-precision map used by the automatic driving system.
Further, when the deviation dimension includes the vehicle positioning lateral deviation dimension, the real vehicle test data during steady-state driving includes a real lane position corresponding to the target lane line in the real physical world and a driving track generated by the test vehicle in the real physical world;
according to the real vehicle test data during steady-state driving, determining whether the lane line driving deviation occurring in the real vehicle test process needs to be corrected under the deviation dimension comprises the following steps:
Determining an average lateral deviation between the travel track and the real lane position;
when the sum of the average transverse deviations is not zero, determining that lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the vehicle positioning transverse deviation dimension;
the method for determining the correction parameters in the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters in the deviation dimension comprises the following steps:
determining the average lateral deviation as a correction parameter in the vehicle positioning lateral deviation dimension;
and compensating the correction parameters under the transverse deviation dimension of the vehicle positioning to the transverse position feedback value of the vehicle positioning in the automatic driving system after inverting the correction parameters.
Further, when the deviation dimension further includes the vehicle positioning lateral deviation dimension, the correction method further includes:
and if the average forward lateral deviation and the average reverse lateral deviation obtained by the real vehicle test conducted on the lane line deviation dimension of the high-precision map are both zero, determining that the lane line driving deviation in the real vehicle test process does not need to be corrected under the vehicle positioning lateral deviation dimension.
Further, the correction method further includes:
before performing a real vehicle test on the deviation dimension, determining whether correction in any deviation dimension having a higher priority than the deviation dimension is completed; the priority of the steering zero deviation dimension, the vehicle positioning angle deviation dimension, the high-precision map lane line deviation dimension and the vehicle positioning transverse deviation dimension is sequentially decreased;
and if so, performing real vehicle testing on the deviation dimension.
The embodiment of the application also provides a correction device for the driving deviation in the automatic driving, which comprises:
the test module is used for carrying out real vehicle test on the automatic driving system aiming at the deviation dimension related to the driving deviation of the lane line in the automatic driving so as to control the test vehicle to keep steady-state driving along the target lane line in the high-precision map; wherein the deviation dimension comprises at least one of: steering zero offset dimension, vehicle positioning angle offset dimension, high-precision map lane line deviation dimension and vehicle positioning transverse offset dimension;
the determining module is used for determining whether lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the deviation dimension according to real vehicle testing data in steady driving;
And the correction module is used for determining correction parameters under the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters under the deviation dimension if required.
The embodiment of the application also provides electronic equipment, which comprises: the system comprises a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, the processor and the memory are communicated through the bus when the electronic device is running, and the machine-readable instructions are executed by the processor to perform the steps of the method for correcting the driving deviation in the automatic driving.
The embodiment of the present application also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of a method for correcting a driving deviation in automatic driving as described above.
According to the correction method, device, equipment and medium for the driving deviation in the automatic driving, the deviation dimension causing the lane line driving deviation in the automatic driving is determined through analysis, and the automatic driving system is corrected according to the real vehicle test data, so that the error of lane line driving deviation caused by the deviation dimension including steering zero deviation, vehicle positioning angle deviation, high-precision map lane line deviation and vehicle positioning transverse deviation can be effectively eliminated, lane line keeping accuracy is improved, and the requirement of driving strictly along a specific lane line is met.
In order to make the above objects, features and advantages of the present application more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for correcting a driving deviation in automatic driving according to an embodiment of the present application;
FIG. 2 is a schematic diagram of lane departure in a steering zero-offset dimension according to an embodiment of the present application;
FIG. 3 is a schematic diagram showing lane line driving deviation in a vehicle positioning angle deviation dimension according to an embodiment of the present application;
fig. 4 (a) and fig. 4 (b) are schematic diagrams showing lane line driving deviation in a lane line deviation dimension of a high-precision map according to an embodiment of the present application;
FIG. 5 is a schematic diagram showing lane line driving deviation in a vehicle positioning lateral deviation dimension according to an embodiment of the present application;
Fig. 6 is a schematic structural diagram of a correction device for driving deviation in automatic driving according to an embodiment of the present application;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. The components of the embodiments of the present application generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. Based on the embodiments of the present application, every other embodiment obtained by a person skilled in the art without making any inventive effort falls within the scope of protection of the present application.
According to the research, under certain application scenes, the high-precision map-based automatic driving vehicle has a severe requirement on running on a specific lane line, for example, a certain dock is narrow in road, and when the automatic driving vehicle keeps running along the lane center line, the distance between the left and right sides of the automatic driving vehicle and the lane boundary is only about 10-15 cm, and at the moment, the automatic driving vehicle slightly deviates from the lane center line, so that even the line pressing occurs. In the automatic driving process, the vehicles calibrated in the prior art often have a certain deviation from the lane center line, cannot strictly run along the lane center line, and cannot meet the requirement of running along the specific lane line in the application scenes.
Based on the above, the embodiment of the application provides a correction method, a device, equipment and a medium for driving deviation in automatic driving, which are used for determining the deviation dimension causing the driving deviation of a lane line in automatic driving through analysis and correcting an automatic driving system according to real vehicle test data, so that the driving deviation error caused by the deviation dimension including steering zero deviation, vehicle positioning angle deviation, high-precision map lane line deviation and vehicle positioning transverse deviation can be effectively eliminated, the lane line keeping precision is improved, and the driving requirement strictly along a specific lane line is met.
Referring to fig. 1, fig. 1 is a flowchart of a method for correcting driving deviation in automatic driving according to an embodiment of the application. As shown in fig. 1, the correction method provided by the embodiment of the application includes:
and S101, performing real vehicle testing on the automatic driving system aiming at the deviation dimension related to the driving deviation of the lane line in the automatic driving so as to control the tested vehicle to keep steady-state driving along the target lane line in the high-precision map.
It should be noted that, the test vehicle used in the embodiment of the present application is an automatic driving vehicle that has completed preliminary calibration, that is, under the condition of closing the planning control dynamic planning, certain position accuracy and control accuracy can be ensured to perform automatic driving, but it cannot strictly ensure that the test vehicle runs along the target lane line, and the running route always has a certain deviation from the target lane line. The target lane line can be a road center line in general, and can be set according to driving conditions; for example, if there is a break to the left of a road, the target lane may be set with the road centerline offset a distance to the right. The following description will be made with the target lane line as the road center line.
The embodiment of the application discovers the source of the error of driving away from the lane line in automatic driving through research, namely the dimension of the error comprises at least one of the following: steering zero offset dimension, vehicle positioning angle offset dimension, high-precision map lane line deviation dimension and vehicle positioning transverse offset dimension. Wherein, the steering zero offset means that when the steering wheel angle is 0, the front wheel steering angle of the vehicle is not 0; the vehicle positioning angular deviation refers to angular deviation generated when positioning equipment installed in a vehicle positions the vehicle, namely, the vehicle gesture fed back by the positioning equipment deviates from the vehicle gesture in the real physical world; the high-precision map lane line deviation refers to deviation of position data about a target lane line in a high-precision map on which an automatic driving vehicle depends, namely, the target lane line in the high-precision map is deviated from a target lane line in the real physical world; the vehicle positioning lateral deviation refers to lateral position deviation generated when a positioning device installed in a vehicle positions the vehicle, namely, the vehicle position fed back by the positioning device deviates from the real physical vehicle position.
In the step, for each deviation dimension, a real vehicle test is carried out on the automatic driving system, and the test vehicle which is subjected to preliminary calibration is controlled to reach steady-state running along a target lane line in a high-precision map and keep. During real vehicle testing, a section of straight road on the map is selected for testing, and the length of the straight road is enough, for example, the test vehicle can be accelerated to the maximum speed in an application scene, and a period of time, for example, at least 10 seconds, is prolonged, so that accurate and sufficient experimental data can be collected; in addition, for correction under the lane line deviation dimension of the high-precision map, the straight road is required to be capable of driving forward and backward, and lane related data in the high-precision map only changes direction and does not change coordinates during forward and backward driving.
It should be noted that, since the lane line driving deviation is difficult to distinguish due to different deviation dimensions, it is preferable that when the source of the lane line driving deviation is a plurality of deviation dimensions, the plurality of deviation dimensions can be corrected one by one following a certain sequence. Thus, in particular implementation, the correction method further comprises:
before performing a real vehicle test on the deviation dimension, determining whether correction in any deviation dimension having a higher priority than the deviation dimension is completed; the priority of the steering zero deviation dimension, the vehicle positioning angle deviation dimension, the high-precision map lane line deviation dimension and the vehicle positioning transverse deviation dimension is sequentially decreased; and if so, performing real vehicle testing on the deviation dimension.
That is, such a correction sequence corrects from one deviation dimension to another in accordance with the steering zero deviation dimension, the vehicle positioning angle deviation dimension, the high-precision map lane line deviation dimension, and the vehicle positioning lateral deviation dimension.
S102, determining whether lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the deviation dimension according to real vehicle testing data in steady driving.
In the step, in the real vehicle test process for each deviation dimension, real vehicle test data after the vehicle reaches steady state running is collected to determine whether lane line running deviation occurring in the real vehicle test process needs to be corrected under the deviation dimension.
If not, it is determined that correction for the deviation dimension is completed, the next deviation dimension may be corrected continuously, or lane line driving deviation correction for the entire autopilot system may be completed.
Specifically, for the steering zero offset dimension, the vehicle positioning angle offset dimension and the vehicle positioning transverse offset dimension, when the real vehicle is tested, the test vehicle which is subjected to preliminary calibration is required to be placed on a straight road to finish the automatic driving which reaches a preset speed (such as the highest speed, 80% of the highest speed and the like) once and keeps steady running for a period of time after reaching the preset speed; for the lane line deviation dimension of the high-precision map, the test vehicle which completes the primary calibration is required to be placed on a straight road to complete forward and reverse directions once to reach a preset speed in real vehicle test, and automatic driving of steady-state running is kept for a period of time after the preset speed is reached.
And S103, if necessary, determining a correction parameter under the deviation dimension according to the real vehicle test data, and correcting the automatic driving system according to the correction parameter under the deviation dimension.
The actual vehicle testing and calibration for different deviation dimensions will be described in detail below in connection with specific examples.
Referring to fig. 2, fig. 2 is a schematic diagram of a lane line driving deviation under a steering zero-deviation dimension according to an embodiment of the present application. As shown in fig. 2, 1 represents a high-precision map lane center line; 2 represents a rear axle center of the vehicle; 3 denotes a front wheel of the vehicle; 4 represents the rear wheels of the vehicle; the actual rotation angle of the front wheels 3 of the vehicle is 0, but the commanded rotation angle is not 0, and there is a certain deviation.
In the specific implementation, the test vehicle with the primary calibration of the vehicle is placed on a section of straight lane to finish one-time automatic driving to the highest speed, and after the highest speed is reached and the steady state is kept, the steering instruction issued by the automatic driving system is recorded. Analysis shows that when there is a steering zero bias, the vehicle state at steady state appears as: (1) when the steering wheel angle is 0, the front wheel angle is not 0; therefore, in order to ensure that the actual front wheel rotation angle is 0, the automatic control system needs to issue a steering command value which is not 0 to compensate, and the steering command issued in the automatic driving system is not 0. (2) Because a steering command value which is not zero is required to be issued to ensure that the real steering angle is zero in a steady state, and a feedback is required to ensure that the steering angle command which is not zero is required, a fixed lateral deviation is required, namely, the fixed lateral deviation exists between the running track in the automatic driving system and the middle line of a lane of a high-precision map I.e. the distance from the centre 2 of the rear axle of the vehicle to the centre line 1 of the lane of the high-precision map is +.>. Steering command value +.>The relationship with the vehicle state is shown in table 1 below:
table 1 steering command valueRelationship to vehicle state
Thus, in an implementation, when the deviation dimension includes the steering zero deviation dimension, the real vehicle test data includes a steering command value issued by the autopilot system.
Step S102 includes: and when the steering instruction value issued by the automatic driving system is not zero, determining that the lane line driving deviation occurring in the real vehicle testing process needs to be corrected in the steering zero deviation dimension.
Step S103 includes: determining an average value of steering command values within a predetermined interval as a correction parameter in the steering zero offset dimension; and inverting the correction parameter under the steering zero-offset dimension and compensating the correction parameter to a steering instruction value issued by the automatic driving system.
Here, the predetermined section may be a time section or a distance section, such as a period of time or a distance for which steady state running is maintained. Collecting the steering command value in a preset interval and averagingDetermining an average value c as a correction parameter; and then compensating the corrected parameter to a steering command value issued by the automatic driving system after inverting, and correcting the steering zero offset so as to eliminate the steering zero offset.
Referring to fig. 3, fig. 3 is a schematic diagram of a lane line driving deviation in a vehicle positioning angle deviation dimension according to an embodiment of the application. As shown in fig. 3, 1 represents a high-precision map lane center line; 2 represents a rear axle center of the vehicle; the feedback posture (dotted line) of the vehicle in the automatic driving system has angular deviation from the real posture of the physical world。
In the specific implementation, the test vehicle with the primary calibration and steering zero offset correction is placed on a section of straight lane to finish one-time automatic driving to the highest speed, and the angle deviation between the running track of the automatic driving system and the center line of the high-precision map is recorded after the highest speed is reached and the steady state is kept. Analysis shows that when there is a vehicle localization angle bias, the vehicle state at steady state appears as: (1) The feedback gesture of the vehicle and the real gesture of the physical world have angular deviationThe steering command issued in the autopilot system is substantially 0. (2) A fixed transverse deviation exists in a driving track and a high-precision map central line in an automatic driving system>Because the feedback positional angle deviation may result in a steering command that is not zero, a lateral deviation is required to counteract the non-zero steering command. Deviation angle->The relationship with the vehicle state is shown in table 2 below:
TABLE 2 relationship of deviation angle and vehicle state
Thus in practice, when the deviation dimension comprises the vehicle localization angle deviation dimension, the real vehicle test data comprises a travel track recorded in the autopilot system.
Step S102 includes: determining a deviation angle between a driving track recorded in the automatic driving system and the target lane line; and when the deviation angle is not zero, determining that the lane line driving deviation in the real vehicle testing process needs to be corrected under the vehicle positioning angle deviation dimension.
Step S103 includes: determining an average value of the deviation angles within a predetermined section as a correction parameter in the vehicle localization angle deviation dimension; and compensating the correction parameters under the deviation dimension of the vehicle positioning angle to the orientation feedback value of the vehicle positioning in the automatic driving system after inverting the correction parameters.
Similarly, the predetermined interval may be a time interval or a distance interval, such as a period of time or a distance to maintain steady state travel. Collecting the angular deviation in the preset interval and averagingAverage +.>Determining as a correction parameter; and then, compensating the corrected parameters to the orientation feedback value of the vehicle positioning in the automatic driving system after reversing so as to eliminate the positioning angle deviation.
Referring to fig. 4 (a) and fig. 4 (b), fig. 4 (a) and fig. 4 (b) are schematic diagrams of lane line driving deviation in a lane line deviation dimension of a high-precision map according to an embodiment of the present application. As shown in fig. 4 (a) and 4 (b), 1 represents a high-precision map lane center line; 2 represents a rear axle center of the vehicle; 5 denotes a real lane center line.
In the specific implementation, a test vehicle which completes the primary calibration, steering zero offset correction and positioning angle offset correction of the vehicle is placed on a section of straight-going lane to complete forward and reverse automatic driving once to the highest speed, after the highest speed is reached and the steady state is kept, the offset state of the vehicle and the lane in the real world is observed, and the average transverse deviation in the steady state during forward and reverse driving is recorded、/>. Analysis shows that, assuming that the left direction of forward travel is the forward direction, when there is a lane deviation of a high-definition map, the vehicle state at steady state is represented as: (1) The steering command issued in the autopilot system is substantially 0. (2) The angle deviation between the running track and the central line of the high-precision map in the automatic driving system and the transverse deviation are basically 0, namely the running trackThe trace is substantially coincident with the lane centerline 1 of the high-precision map in the figure. (3) When the vehicle is traveling forward and backward, there is a lateral deviation on the real road, which is offset to the lane side, for example, in the forward traveling, the lateral deviation from the real lane center line 5 is +. >The method comprises the steps of carrying out a first treatment on the surface of the In the reverse driving, the reverse driving trajectory in fig. 4 (b), i.e., the high-precision map lane center line 1, has a lateral deviation of +.>；。/>、/>The relationship with the vehicle state is shown in the following table 3:
TABLE 3 average forward and reverse lateral deviation、/>Relationship to vehicle state
Therefore, in implementation, when the deviation dimension includes the high-precision map lane line deviation dimension, the real vehicle test data includes a real lane position corresponding to the real physical world of the target lane line, a forward running track generated by the test vehicle in the real physical world during forward running, and a reverse running track generated by the test vehicle in the real physical world during reverse running.
Step S102 includes: determining an average forward lateral deviation between the forward travel trajectory and the real lane position, and an average reverse lateral deviation between the reverse travel trajectory and the real lane position; and when the sum of the average forward transverse deviation and the average reverse transverse deviation is not zero, determining that lane line driving deviation occurring in the real vehicle testing process needs to be corrected under the lane line deviation dimension of the high-precision map.
Step S103 includes: determining half of the sum of the average forward lateral deviation and the average reverse lateral deviation as a correction parameter in the high-precision map lane line deviation dimension; and inverting the correction parameters under the lane line deviation dimension of the high-precision map and compensating the correction parameters to the target lane line in the high-precision map used by the automatic driving system.
In the specific implementation, the driving track and the real lane position during forward and reverse driving are respectively collected, and the average forward transverse deviation between the forward driving track and the real lane position is obtainedAnd an average reverse lateral deviation between the reverse driving trajectory and the real lane position +.>And will->Determining as a correction parameter; and then, compensating the corrected parameters to target lane lines in a high-precision map used by the automatic driving system after reversing so as to eliminate lane line deviation of the high-precision map.
Referring to fig. 5, fig. 5 is a schematic diagram of a lane line driving deviation in a vehicle positioning lateral deviation dimension according to an embodiment of the present application. As shown in fig. 5, 1 represents a high-precision map lane center line; 2 represents a rear axle center of the vehicle; 5 denotes a real lane center line.
In the specific implementation, the automatic driving vehicle after the initial calibration, steering zero offset correction, positioning angle offset correction and map transverse offset correction of the vehicle is placed on a section of straight lane to finish one-time automatic driving to the highest speed, after the highest speed is reached and the steady state is kept, the offset state of the vehicle and the lane in the real world is observed, and the steady state is recordedAverage lateral deviation. Analysis shows that when there is a vehicle positioning yaw, the vehicle state at steady state is represented as: (1) The steering command issued in the autopilot system is substantially 0. (2) The angle deviation and the transverse deviation of the running track in the automatic driving system and the line of the high-precision map are basically 0, namely the running track is basically coincident with the line 1 of the lane of the high-precision map in the figure. (3) When the vehicle is traveling, there is a lateral deviation on the real road, which is offset to the lane side. Assuming that the left bias is positive and the right bias is negative, the average transverse deviation is set as Average lateral deviation>The relationship with the vehicle state is shown in the following table 4:
TABLE 4 average lateral deviationRelationship to vehicle state
Therefore, in a specific implementation, when the deviation dimension includes the vehicle positioning lateral deviation dimension, the real vehicle test data during steady-state driving includes a real lane position corresponding to the real physical world of the target lane line and a driving track generated by the test vehicle in the real physical world.
Step S102 includes: determining an average lateral deviation between the travel track and the real lane position; and when the sum of the average transverse deviations is not zero, determining that the lane line driving deviation occurring in the real vehicle testing process needs to be corrected under the vehicle positioning transverse deviation dimension.
Step S103 includes: determining the average lateral deviation as a correction parameter in the vehicle positioning lateral deviation dimension; and compensating the correction parameters under the transverse deviation dimension of the vehicle positioning to the transverse position feedback value of the vehicle positioning in the automatic driving system after inverting the correction parameters.
In specific implementation, the driving track and the real lane position are collected, and the average lateral deviation is obtainedAnd is determined as a correction parameter; and then compensating the corrected parameters to the lateral position feedback value of the vehicle positioning in the automatic driving system of the automatic driving system after reversing, so as to eliminate the lateral deviation of the vehicle positioning.
Further, when the deviation dimension includes a high-precision map lane line deviation dimension and a vehicle positioning lateral deviation dimension, the correction method further includes:
and if the average forward lateral deviation and the average reverse lateral deviation obtained by the real vehicle test conducted on the lane line deviation dimension of the high-precision map are both zero, determining that the lane line driving deviation in the real vehicle test process does not need to be corrected under the vehicle positioning lateral deviation dimension.
Here, in the real vehicle test for the lane line deviation dimension of the high-precision map, the average forward lateral deviationDeviation from the average reverse transverse direction->And if the vehicle positioning deviation is zero, the fact that the lane line deviation of the high-precision map does not exist can be determined, and then the vehicle positioning deviation correction should be carried out in the next step. While the average forward lateral deviation +.>Deviation from the average reverse transverse direction->The vehicle positioning lateral deviation is proved to be absent when the vehicle positioning lateral deviation is zero, so that the real vehicle test for the vehicle positioning lateral deviation dimension is not needed, the test process can be reduced, and the correction efficiency is improved.
Experiments prove that the vehicle corrected by the correction method provided by the embodiment of the application can basically run on the central line of the lane on a section of straight road, the deviation is not more than +/-2 cm, the deviation between the running track and the central line of the high-precision map in an automatic driving system is not more than +/-2 cm, the angle deviation is not more than +/-0.1 degrees, and the correction of the running deviation of the lane line of the vehicle can be considered to be finished. And then the corrected vehicle can be used for driving on all maps, and other deviation items can be corrected by testing the deviation of the actual driving.
The method for correcting the driving deviation in the automatic driving, provided by the embodiment of the application, comprises the following steps: performing real vehicle testing on the automatic driving system aiming at the deviation dimension related to the driving deviation of the lane line in the automatic driving to control the tested vehicle to keep steady-state driving along the target lane line in the high-precision map; wherein the deviation dimension comprises at least one of: steering zero offset dimension, vehicle positioning angle offset dimension, high-precision map lane line deviation dimension and vehicle positioning transverse offset dimension; according to the real vehicle test data in steady-state driving, determining whether lane line driving deviation in the real vehicle test process is required to be corrected in the deviation dimension; and if so, determining a correction parameter under the deviation dimension according to the real vehicle test data, and correcting the automatic driving system according to the correction parameter under the deviation dimension.
The deviation dimension causing the lane line driving deviation in the automatic driving is determined through analysis, and the automatic driving system is corrected according to the real vehicle test data, so that the error of lane line driving deviation caused by the deviation dimension including steering zero deviation, vehicle positioning angle deviation, high-precision map lane line deviation and vehicle positioning transverse deviation can be effectively eliminated, the lane line keeping precision is improved, and the requirement of driving strictly along a specific lane line is met.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a device for correcting driving deviation in automatic driving according to an embodiment of the application. As shown in fig. 6, the correction device 600 includes:
the test module 610 is configured to perform a real vehicle test on the automatic driving system for a deviation dimension related to a lane line driving deviation in automatic driving, so as to control the test vehicle to keep a steady state driving along a target lane line in the high-precision map; wherein the deviation dimension comprises at least one of: steering zero offset dimension, vehicle positioning angle offset dimension, high-precision map lane line deviation dimension and vehicle positioning transverse offset dimension;
the determining module 620 is configured to determine whether a lane line driving deviation occurring in a real vehicle testing process needs to be corrected under the deviation dimension according to real vehicle testing data during steady driving;
the correction module 630 is configured to determine, if necessary, a correction parameter in the deviation dimension according to the real vehicle test data, and correct the autopilot system according to the correction parameter in the deviation dimension.
Further, when the deviation dimension includes the steering zero deviation dimension, the real vehicle test data includes a steering instruction value issued by the automatic driving system;
The determining module 620 determines whether the lane line driving deviation occurring in the real vehicle testing process needs to be corrected under the deviation dimension according to the real vehicle testing data during the steady driving, including:
when the steering instruction value issued by the automatic driving system is not zero, determining that the lane line driving deviation occurring in the real vehicle testing process needs to be corrected in the steering zero deviation dimension;
the correction module 630 determines a correction parameter in the deviation dimension according to the real vehicle test data, and corrects the autopilot system according to the correction parameter in the deviation dimension, including:
determining an average value of steering command values within a predetermined interval as a correction parameter in the steering zero offset dimension;
and inverting the correction parameter under the steering zero-offset dimension and compensating the correction parameter to a steering instruction value issued by the automatic driving system.
Further, when the deviation dimension includes the vehicle localization angle deviation dimension, the real vehicle test data includes a travel track recorded in the automatic driving system;
the determining module 620 determines whether the lane line driving deviation occurring in the real vehicle testing process needs to be corrected under the deviation dimension according to the real vehicle testing data during the steady driving, including:
Determining a deviation angle between a driving track recorded in the automatic driving system and the target lane line;
when the deviation angle is not zero, determining that lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the vehicle positioning angle deviation dimension;
the correction module 630 determines a correction parameter in the deviation dimension according to the real vehicle test data, and corrects the autopilot system according to the correction parameter in the deviation dimension, including:
determining an average value of the deviation angles within a predetermined section as a correction parameter in the vehicle localization angle deviation dimension;
and compensating the correction parameters under the deviation dimension of the vehicle positioning angle to the orientation feedback value of the vehicle positioning in the automatic driving system after inverting the correction parameters.
Further, when the deviation dimension includes the high-precision map lane line deviation dimension, the real vehicle test data includes a real lane position corresponding to the real physical world of the target lane line, a forward running track generated by the test vehicle in the real physical world during forward running, and a reverse running track generated by the test vehicle in the real physical world during reverse running;
The determining module 620 determines whether the lane line driving deviation occurring in the real vehicle testing process needs to be corrected under the deviation dimension according to the real vehicle testing data during the steady driving, including:
determining an average forward lateral deviation between the forward travel trajectory and the real lane position, and an average reverse lateral deviation between the reverse travel trajectory and the real lane position;
when the sum of the average forward transverse deviation and the average reverse transverse deviation is not zero, determining that lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the lane line deviation dimension of the high-precision map;
the correction module 630 determines a correction parameter in the deviation dimension according to the real vehicle test data, and corrects the autopilot system according to the correction parameter in the deviation dimension, including:
determining half of the sum of the average forward lateral deviation and the average reverse lateral deviation as a correction parameter in the high-precision map lane line deviation dimension;
and inverting the correction parameters under the lane line deviation dimension of the high-precision map and compensating the correction parameters to the target lane line in the high-precision map used by the automatic driving system.
Further, when the deviation dimension includes the vehicle positioning lateral deviation dimension, the real vehicle test data during steady-state driving includes a real lane position corresponding to the target lane line in the real physical world and a driving track generated by the test vehicle in the real physical world;
the determining module 620 determines whether the lane line driving deviation occurring in the real vehicle testing process needs to be corrected under the deviation dimension according to the real vehicle testing data during the steady driving, including:
determining an average lateral deviation between the travel track and the real lane position;
when the sum of the average transverse deviations is not zero, determining that lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the vehicle positioning transverse deviation dimension;
the correction module 630 determines a correction parameter in the deviation dimension according to the real vehicle test data, and corrects the autopilot system according to the correction parameter in the deviation dimension, including:
determining the average lateral deviation as a correction parameter in the vehicle positioning lateral deviation dimension;
and compensating the correction parameters under the transverse deviation dimension of the vehicle positioning to the transverse position feedback value of the vehicle positioning in the automatic driving system after inverting the correction parameters.
Further, when the deviation dimension further includes the vehicle positioning lateral deviation dimension, the determining module 620 is further configured to:
and if the average forward lateral deviation and the average reverse lateral deviation obtained by the real vehicle test conducted on the lane line deviation dimension of the high-precision map are both zero, determining that the lane line driving deviation in the real vehicle test process does not need to be corrected under the vehicle positioning lateral deviation dimension.
Further, the correction device 600 further includes a priority determining module (not shown in fig. 6); the priority determining module is used for:
before performing a real vehicle test on the deviation dimension, determining whether correction in any deviation dimension having a higher priority than the deviation dimension is completed; the priority of the steering zero deviation dimension, the vehicle positioning angle deviation dimension, the high-precision map lane line deviation dimension and the vehicle positioning transverse deviation dimension is sequentially decreased;
and if so, performing real vehicle testing on the deviation dimension.
Referring to fig. 7, fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the application. As shown in fig. 7, the electronic device 700 includes a processor 710, a memory 720, and a bus 730.
The memory 720 stores machine-readable instructions executable by the processor 710, when the electronic device 700 is running, the processor 710 communicates with the memory 720 through the bus 730, and when the machine-readable instructions are executed by the processor 710, the steps of a method for correcting driving deviation in automatic driving in the method embodiment shown in fig. 1 can be executed, and detailed description of the method embodiment will be omitted.
The embodiment of the present application further provides a computer readable storage medium, where a computer program is stored on the computer readable storage medium, and when the computer program is executed by a processor, the computer program may execute the steps of a method for correcting a driving deviation in automatic driving in the method embodiment shown in fig. 1, and a specific implementation manner may refer to the method embodiment and will not be described herein.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. The above-described apparatus embodiments are merely illustrative, for example, the division of the units is merely a logical function division, and there may be other manners of division in actual implementation, and for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be through some communication interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above examples are only specific embodiments of the present application, and are not intended to limit the scope of the present application, but it should be understood by those skilled in the art that the present application is not limited thereto, and that the present application is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application. Therefore, the protection scope of the application is subject to the protection scope of the claims.

Claims (9)

1. A correction method of a running deviation in automatic driving, characterized by comprising:
performing real vehicle testing on the automatic driving system aiming at the deviation dimension related to the driving deviation of the lane line in the automatic driving to control the tested vehicle to keep steady-state driving along the target lane line in the high-precision map; wherein,
The deviation dimension includes at least one of: steering zero offset dimension, vehicle positioning angle offset dimension, high-precision map lane line deviation dimension and vehicle positioning transverse offset dimension;
the priority of the steering zero deviation dimension, the vehicle positioning angle deviation dimension, the high-precision map lane line deviation dimension and the vehicle positioning transverse deviation dimension is sequentially decreased;
according to the real vehicle test data in steady-state driving, determining whether lane line driving deviation in the real vehicle test process is required to be corrected in the deviation dimension;
and if so, determining a correction parameter under the deviation dimension according to the real vehicle test data, and correcting the automatic driving system according to the correction parameter under the deviation dimension.
2. The correction method according to claim 1, wherein when the deviation dimension includes the steering zero deviation dimension, the real vehicle test data includes a steering command value issued by the automatic driving system;
according to the real vehicle test data during steady-state driving, determining whether the lane line driving deviation occurring in the real vehicle test process needs to be corrected under the deviation dimension comprises the following steps:
When the steering instruction value issued by the automatic driving system is not zero, determining that the lane line driving deviation occurring in the real vehicle testing process needs to be corrected in the steering zero deviation dimension;
the method for determining the correction parameters in the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters in the deviation dimension comprises the following steps:
determining an average value of steering command values within a predetermined interval as a correction parameter in the steering zero offset dimension;
and inverting the correction parameter under the steering zero-offset dimension and compensating the correction parameter to a steering instruction value issued by the automatic driving system.
3. The correction method according to claim 1, characterized in that when the deviation dimension includes the vehicle localization angle deviation dimension, the real vehicle test data includes a travel track recorded in the automatic driving system;
according to the real vehicle test data during steady-state driving, determining whether the lane line driving deviation occurring in the real vehicle test process needs to be corrected under the deviation dimension comprises the following steps:
determining a deviation angle between a driving track recorded in the automatic driving system and the target lane line;
When the deviation angle is not zero, determining that lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the vehicle positioning angle deviation dimension;
the method for determining the correction parameters in the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters in the deviation dimension comprises the following steps:
determining an average value of the deviation angles within a predetermined section as a correction parameter in the vehicle localization angle deviation dimension;
and compensating the correction parameters under the deviation dimension of the vehicle positioning angle to the orientation feedback value of the vehicle positioning in the automatic driving system after inverting the correction parameters.
4. The correction method according to claim 1, wherein when the deviation dimension includes the high-precision map lane line deviation dimension, the real vehicle test data includes a real lane position corresponding to the real physical world of the target lane line, a forward travel locus generated by the test vehicle in the real physical world during forward travel, and a reverse travel locus generated by the test vehicle in the real physical world during reverse travel;
according to the real vehicle test data during steady-state driving, determining whether the lane line driving deviation occurring in the real vehicle test process needs to be corrected under the deviation dimension comprises the following steps:
Determining an average forward lateral deviation between the forward travel trajectory and the real lane position, and an average reverse lateral deviation between the reverse travel trajectory and the real lane position;
when the sum of the average forward transverse deviation and the average reverse transverse deviation is not zero, determining that lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the lane line deviation dimension of the high-precision map;
the method for determining the correction parameters in the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters in the deviation dimension comprises the following steps:
determining half of the sum of the average forward lateral deviation and the average reverse lateral deviation as a correction parameter in the high-precision map lane line deviation dimension;
and inverting the correction parameters under the lane line deviation dimension of the high-precision map and compensating the correction parameters to the target lane line in the high-precision map used by the automatic driving system.
5. The correction method according to claim 1, wherein when the deviation dimension includes the vehicle positioning lateral deviation dimension, the real vehicle test data at the time of steady-state running includes a real lane position corresponding to the target lane line in the real physical world and a running track generated by the test vehicle in the real physical world;
According to the real vehicle test data during steady-state driving, determining whether the lane line driving deviation occurring in the real vehicle test process needs to be corrected under the deviation dimension comprises the following steps:
determining an average lateral deviation between the travel track and the real lane position;
when the sum of the average transverse deviations is not zero, determining that lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the vehicle positioning transverse deviation dimension;
the method for determining the correction parameters in the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters in the deviation dimension comprises the following steps:
determining the average lateral deviation as a correction parameter in the vehicle positioning lateral deviation dimension;
and compensating the correction parameters under the transverse deviation dimension of the vehicle positioning to the transverse position feedback value of the vehicle positioning in the automatic driving system after inverting the correction parameters.
6. The correction method as claimed in claim 4, wherein when the deviation dimension further includes the vehicle positioning lateral deviation dimension, the correction method further includes:
and if the average forward lateral deviation and the average reverse lateral deviation obtained by the real vehicle test conducted on the lane line deviation dimension of the high-precision map are both zero, determining that the lane line driving deviation in the real vehicle test process does not need to be corrected under the vehicle positioning lateral deviation dimension.
7. A correction device for a running deviation in automatic driving, characterized by comprising:
the test module is used for carrying out real vehicle test on the automatic driving system aiming at the deviation dimension related to the driving deviation of the lane line in the automatic driving so as to control the test vehicle to keep steady-state driving along the target lane line in the high-precision map; wherein,
the deviation dimension includes at least one of: steering zero offset dimension, vehicle positioning angle offset dimension, high-precision map lane line deviation dimension and vehicle positioning transverse offset dimension;
the priority of the steering zero deviation dimension, the vehicle positioning angle deviation dimension, the high-precision map lane line deviation dimension and the vehicle positioning transverse deviation dimension is sequentially decreased;
the determining module is used for determining whether lane line driving deviation occurring in the real vehicle testing process is required to be corrected under the deviation dimension according to real vehicle testing data in steady driving;
and the correction module is used for determining correction parameters under the deviation dimension according to the real vehicle test data and correcting the automatic driving system according to the correction parameters under the deviation dimension if required.
8. An electronic device, comprising: a processor, a memory and a bus, said memory storing machine readable instructions executable by said processor, said processor and said memory communicating via said bus when the electronic device is running, said machine readable instructions when executed by said processor performing the steps of a method of correcting for driving bias in an automatic driving as claimed in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, performs the steps of a method for correcting a driving deviation in automatic driving as claimed in any one of claims 1 to 6.
CN202310797707.9A 2023-07-03 2023-07-03 Correction method, device, equipment and medium for driving deviation in automatic driving Active CN116513175B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310797707.9A CN116513175B (en) 2023-07-03 2023-07-03 Correction method, device, equipment and medium for driving deviation in automatic driving

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310797707.9A CN116513175B (en) 2023-07-03 2023-07-03 Correction method, device, equipment and medium for driving deviation in automatic driving

Publications (2)

Publication Number Publication Date
CN116513175A CN116513175A (en) 2023-08-01
CN116513175B true CN116513175B (en) 2023-09-22

Family

ID=87403298

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310797707.9A Active CN116513175B (en) 2023-07-03 2023-07-03 Correction method, device, equipment and medium for driving deviation in automatic driving

Country Status (1)

Country Link
CN (1) CN116513175B (en)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109131325A (en) * 2018-08-15 2019-01-04 江苏大学 The three-dimensional of intelligent driving automobile can open up the pre- lane for taking aim at switching and keep control method
CN111717189A (en) * 2019-03-18 2020-09-29 长城汽车股份有限公司 Lane keeping control method, device and system
KR20210077833A (en) * 2019-12-17 2021-06-28 현대자동차주식회사 Apparatus and method for correcting offset of sensor for autonomous vehicle
CN113260544A (en) * 2018-12-28 2021-08-13 爱知制钢株式会社 Correction method of gyroscope sensor
CN113415276A (en) * 2021-07-30 2021-09-21 东风商用车有限公司 Intelligent driving pre-aiming control method and device and storage medium
CN114919641A (en) * 2022-06-02 2022-08-19 合众新能源汽车有限公司 Zero-offset compensation method and device for vehicle steering wheel
CN116118725A (en) * 2022-12-13 2023-05-16 桂林电子科技大学 Lane keeping control method based on multipoint pretightening

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109131325A (en) * 2018-08-15 2019-01-04 江苏大学 The three-dimensional of intelligent driving automobile can open up the pre- lane for taking aim at switching and keep control method
CN113260544A (en) * 2018-12-28 2021-08-13 爱知制钢株式会社 Correction method of gyroscope sensor
CN111717189A (en) * 2019-03-18 2020-09-29 长城汽车股份有限公司 Lane keeping control method, device and system
KR20210077833A (en) * 2019-12-17 2021-06-28 현대자동차주식회사 Apparatus and method for correcting offset of sensor for autonomous vehicle
CN113415276A (en) * 2021-07-30 2021-09-21 东风商用车有限公司 Intelligent driving pre-aiming control method and device and storage medium
CN114919641A (en) * 2022-06-02 2022-08-19 合众新能源汽车有限公司 Zero-offset compensation method and device for vehicle steering wheel
CN116118725A (en) * 2022-12-13 2023-05-16 桂林电子科技大学 Lane keeping control method based on multipoint pretightening

Also Published As

Publication number Publication date
CN116513175A (en) 2023-08-01

Similar Documents

Publication Publication Date Title
CN105774801B (en) Method and device for guiding a vehicle on a lane
CN110320917B (en) Unmanned vehicle curve tracking control method
US20130317698A1 (en) Lane keeping assist system and method
JP2020134528A (en) Removal method of stationary lateral direction deviation, device, storage medium and program
WO2022095460A1 (en) Vehicle lateral control method and apparatus, and vehicle and readable storage medium
CN112703539B (en) Travel route generation device and vehicle control device
CN110398963A (en) Deviation rectifying control method and device for trackless navigation, storage medium and controller
JP6419671B2 (en) Vehicle steering apparatus and vehicle steering method
CN111123950B (en) Driving control method and device and vehicle
CN113830174B (en) Steering angle correction method, device and equipment and readable storage medium
CN110316249A (en) Crosswise joint method and device
EP4345421A2 (en) Method for calibrating sensor parameters based on autonomous driving, apparatus, storage medium, and vehicle
JP2010117804A (en) Unmanned vehicle of traveling wheel independent steering and travel control method therefor
CN110221313B (en) Laser radar installation position correction method of AGV (automatic guided vehicle) and AGV
CN115635967A (en) Vehicle control method and device, vehicle-mounted terminal and storage medium
CN116513175B (en) Correction method, device, equipment and medium for driving deviation in automatic driving
CN111634331A (en) Steering control method, device and system for automatic driving vehicle
CN113311845B (en) Pure tracking control error compensation method and device based on path curvature
CN114740861A (en) AGV zero correction method and system and AGV
CN114839993A (en) Unmanned vehicle line patrol obstacle avoidance method, device, equipment and storage medium
CN114643980A (en) Parking path real-time adjustment method, device, equipment and storage medium
CN113581282A (en) Vehicle steering control method, device, equipment and storage medium
CN110682910B (en) Bend auxiliary driving method and device
CN110968082B (en) Automatic driving vehicle path tracking method and device
CN109823348B (en) Unmanned vehicle reverse model control method, device, equipment and computer readable medium

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