CN115390086B - Fusion positioning method and device for automatic driving, electronic equipment and storage medium - Google Patents

Fusion positioning method and device for automatic driving, electronic equipment and storage medium Download PDF

Info

Publication number
CN115390086B
CN115390086B CN202211341937.6A CN202211341937A CN115390086B CN 115390086 B CN115390086 B CN 115390086B CN 202211341937 A CN202211341937 A CN 202211341937A CN 115390086 B CN115390086 B CN 115390086B
Authority
CN
China
Prior art keywords
error
positioning
laser
laser positioning
longitudinal
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
CN202211341937.6A
Other languages
Chinese (zh)
Other versions
CN115390086A (en
Inventor
李岩
费再慧
张海强
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.)
Zhidao Network Technology Beijing Co Ltd
Original Assignee
Zhidao Network Technology Beijing 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 Zhidao Network Technology Beijing Co Ltd filed Critical Zhidao Network Technology Beijing Co Ltd
Priority to CN202211341937.6A priority Critical patent/CN115390086B/en
Publication of CN115390086A publication Critical patent/CN115390086A/en
Application granted granted Critical
Publication of CN115390086B publication Critical patent/CN115390086B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/86—Combinations of lidar systems with systems other than lidar, radar or sonar, e.g. with direction finders
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S17/00—Systems using the reflection or reradiation of electromagnetic waves other than radio waves, e.g. lidar systems
    • G01S17/88—Lidar systems specially adapted for specific applications
    • G01S17/89—Lidar systems specially adapted for specific applications for mapping or imaging
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42—Determining position
    • G01S19/45—Determining position by combining measurements of signals from the satellite radio beacon positioning system with a supplementary measurement

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • General Physics & Mathematics (AREA)
  • Electromagnetism (AREA)
  • Optical Radar Systems And Details Thereof (AREA)

Abstract

The application discloses a fusion positioning method and device for automatic driving, electronic equipment and a storage medium, wherein the method comprises the steps of collecting laser data of a preset area in advance and establishing a target point cloud map; according to the target point cloud map, when the GNSS signals of the vehicle are available, a laser radar positioning error mode is adopted for self-learning, and a self-learning result of the laser radar positioning error mode is obtained; when laser positioning observation is needed, the positioning error generated when the laser radar is used for positioning is corrected in a self-adaption mode through the self-learning result of the laser radar positioning error mode, and a final positioning result is obtained. Through the method and the device, the positioning error is reduced, and the laser radar error self-adaption based on combination of multiple factors is realized. The scheme of the application can be used for the fusion and positioning of ROBOTAXI and ROBOBUS.

Description

Fusion positioning method and device for automatic driving, electronic equipment and storage medium
Technical Field
The present disclosure relates to the field of automatic driving positioning technologies, and in particular, to a fusion positioning method and device for automatic driving, an electronic device, and a storage medium.
Background
The popularity of autopilot technology has led to an increasing landing speed of ROBOTAXI or ROBOBUS. Correspondingly, the requirements on the stability and accuracy of the positioning function of the automatic driving vehicle are higher and higher, and the traditional combined navigation (IMU + GNSS/RTK) positioning technology cannot meet the requirements of full-scene centimeter-level positioning.
Lidar-based laser SLAM techniques are also being used step by step as additional observations to assist/replace GNSS/RTK. Compared with the SLAM technology in the traditional technology, the laser positioning of automatic driving needs to establish a point cloud map of a specific area, perform global coordinate assignment on the point cloud map, and then perform absolute positioning of the vehicle according to the established point cloud map in order to achieve a more stable effect.
Under ideal conditions among the correlation technique, the precision of point cloud matching location can reach centimetre level (within 10 cm), but receives the influence of following multifactor, and positioning accuracy can receive the influence, and the error can enlarge to the decimetre level, the meter level even:
case 1: the construction of various vehicle types such as ROBOTAXI and ROBOBUS is inconsistent, so that the model and the installation position of the laser radar are greatly different.
Case 2: and due to the influence of calibration errors, errors exist when the positioning of the laser radar is converted into the self-vehicle positioning.
Case 3: the time synchronization is inaccurate, so that the longitudinal positioning precision of the laser radar is increased along with the increase of the speed.
Disclosure of Invention
The embodiment of the application provides a fusion positioning method and device for automatic driving, electronic equipment and a storage medium, so as to provide a laser radar self-adaptive scheme and reduce positioning errors in automatic driving.
The embodiment of the application adopts the following technical scheme:
in a first aspect, an embodiment of the present application provides a fusion positioning method for automatic driving, where the method includes:
collecting laser data of a preset area in advance and establishing to obtain a target point cloud map;
according to the target point cloud map, when the GNSS signals of the vehicle are available, a laser radar positioning error mode is adopted for self-learning, and a self-learning result of the laser radar positioning error mode is obtained;
when laser positioning observation is needed, the positioning error generated when the laser radar is used for positioning is corrected in a self-adaption mode through the self-learning result of the laser radar positioning error mode, and a final positioning result is obtained.
When laser positioning observation is needed, the positioning error generated when the laser radar is used for positioning is corrected in a self-learning result self-adaptive mode through the laser radar positioning error mode, and a final positioning result is obtained, wherein the method comprises the following steps:
calculating the proportional coefficients of the transverse error and the longitudinal error of laser positioning;
correcting a laser positioning result meeting a preset condition according to the laser positioning transverse error and/or the laser positioning longitudinal error proportional coefficient;
when laser positioning observation is needed, fusing a positioning result of positioning by using a laser radar and the corrected laser positioning result, and updating an observation value of a Kalman filter based on the fusion result;
and taking the estimated value of the Kalman filter as a final positioning result.
In some embodiments, obtaining the laser positioning result meeting the preset condition includes:
whether the speed of the autonomous vehicle is greater than a preset speed threshold;
whether the confidence degrees of the laser positioning results are all larger than a preset threshold value or not;
the distance between the two frames of laser positioning and the displacement calculated by the speed of the vehicle body are within a preset error range.
In some embodiments, before calculating the laser positioning lateral error and the laser positioning longitudinal error proportionality coefficient, the method further includes:
the method comprises the steps of synchronizing the GNSS position, the laser positioning position information, the course angle information, the vehicle body speed information and the radar positioning confidence coefficient when GNSS signals with the same preset window size are available, and establishing an error self-adaptive data set, wherein the error self-adaptive data set is obtained by decomposing the GNSS position and the laser positioning position information when the GNSS signals are available into a transverse position set and a longitudinal position set under a vehicle coordinate system according to the course angle information, and the preset window size is set according to the laser positioning frequency.
In some embodiments, the laser positioning lateral error is calculated as follows:
and counting errors in the transverse position set, and if the errors conform to normal distribution, judging the mean value of the current laser positioning transverse errors which are normally distributed as the laser positioning transverse errors in the self-learning result of the laser radar positioning error mode.
In some embodiments, the laser positioning longitudinal error scaling factor is calculated as follows:
counting errors in the longitudinal position set, and fitting vehicle speed and laser positioning longitudinal errors according to the vehicle body speed information;
calculating an error proportional coefficient according to the vehicle speed and the laser positioning longitudinal error, and using the error fitting normal distribution corrected by the error proportional coefficient as the laser positioning longitudinal error proportional coefficient in the self-learning result of the laser radar positioning error mode;
or, determining whether to correct the longitudinal error according to a longitudinal positioning error judgment threshold value counted by the laser radar off-line, if the error mean value in the longitudinal position set is smaller than the judgment threshold value, not correcting the longitudinal error, and only correcting the transverse error by using the laser positioning transverse error.
In some embodiments, the method further comprises:
updating the positioning result in real time according to the laser positioning transverse error or the laser positioning longitudinal error proportional coefficient in the self-learning result of the laser radar positioning error mode, wherein the latest laser positioning transverse error or laser positioning longitudinal error proportional coefficient is adopted in the updating process,
or, the updating process adopts the average value of the laser positioning transverse error or the laser positioning longitudinal error proportionality coefficient and the previous laser positioning transverse error or the laser positioning longitudinal error proportionality coefficient.
In a second aspect, an embodiment of the present application further provides a fusion positioning apparatus for automatic driving, where the apparatus includes:
the point cloud map building module is used for collecting laser data of a preset area in advance and building to obtain a target point cloud map;
the error self-learning module is used for carrying out self-learning by adopting a laser radar positioning error mode when the GNSS signal of the vehicle is available according to the target point cloud map to obtain a self-learning result of the laser radar positioning error mode;
and the correcting module is used for adaptively correcting the positioning error generated when the laser radar is used for positioning through the self-learning result of the laser radar positioning error mode when the laser positioning observation is needed, so as to obtain a final positioning result.
In a third aspect, an embodiment of the present application further provides an electronic device, including: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform the above method.
In a fourth aspect, embodiments of the present application also provide a computer-readable storage medium storing one or more programs that, when executed by an electronic device including a plurality of application programs, cause the electronic device to perform the above-described method.
The embodiment of the application adopts at least one technical scheme which can achieve the following beneficial effects: the target point cloud map is obtained through the laser data of the preset area collected in advance and establishment, and the precondition of the point cloud map collected by the same data collection vehicle can be met. In the actual fusion positioning process, firstly, self-learning is carried out by adopting a laser radar positioning error mode when GNSS signals of a vehicle are available according to the target point cloud map, and a self-learning result of the laser radar positioning error mode is obtained; and then when laser positioning observation is needed, self-adaptively correcting the positioning error generated when the laser radar is used for positioning according to the self-learning result of the laser radar positioning error mode to obtain a final positioning result. The point cloud map established by the laser radar of the same vehicle type can be applied to laser positioning algorithms of various different vehicle types, so that errors generated in the positioning process caused by calibration, installation, time synchronization and the like are reduced to the minimum.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic flow diagram of a fusion positioning method for autonomous driving;
FIG. 2 is a schematic diagram of errors in a fusion positioning method for autonomous driving;
FIG. 3 is a schematic diagram (raw) of error statistics in the fusion localization method for autonomous driving;
FIG. 4 is a schematic diagram of error statistics in the fusion positioning method for automatic driving (after correction);
FIG. 5 is a schematic diagram of a fusion positioning device for autopilot;
fig. 6 is a schematic structural diagram of an electronic device in an embodiment of the present application.
Detailed Description
To make the objects, technical solutions and advantages of the present application more clear, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments of the present application and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
The embodiment of the present application provides a fusion positioning method for automatic driving, and as shown in fig. 1, provides a flow schematic diagram of the fusion positioning method for automatic driving in the embodiment of the present application, where the method at least includes the following steps S110 to S140:
step S110, collecting laser data of a preset area in advance and establishing to obtain a target point cloud map.
Because the structures of various vehicle types such as the ROBOTAXI and the ROBOBUS are inconsistent, the models and the installation positions of the laser radars are greatly different, and the ROBOTAXI and the ROBOBUS can use the same target point cloud map through the pre-established target point cloud map.
Illustratively, laser data in a preset ROBOTAXI or ROBOBUS operation area can be collected by a laser radar collection vehicle which is installed with time synchronization, calibration and truth value equipment, a point cloud map is established through post-processing positioning data and the point cloud data after distortion removal, and post-processing is carried out on the map through thinning, point cloud absolute position assignment and the like. And then, obtaining a target point cloud map.
The preset operation area refers to a fixed area where ROBOTAXI or ROBOBUS is to operate, such as a park, and the like. That is, both ROBOTAXI and ROBOBUS may be of different models, but serve the same operating area. Thus, the target point cloud map can be directly used when the ROBOTAXI or ROBOBUS is actually operated.
This has the advantages that:
(1) The map consistency is ensured, and the time for each vehicle to acquire, generate and update the map is reduced.
(2) The accuracy standard of operation car calibration is reduced, for example, high accuracy calibration needs to be carried out in a specific calibration space/field, and if the accuracy of the collection car needs to be calibrated, high labor and time costs are needed.
(3) Due to the fact that different vehicle types need to be configured with the laser radar of the continuous beam, errors caused by the laser radar types such as 16 lines, 32 lines and 80 lines are eliminated by the aid of the same target point cloud map.
(4) Based on the advantages of the above (1) - (3), the error caused by the point cloud inconsistency of different sensors is reduced.
And after the target point cloud map is obtained, deploying the generated map to ROBOTAXI or ROBOBUS in the operation area. It should be noted that ROBOTAXI or ROBOBUS in the operation area may be loaded in advance and obtain the target point cloud map.
And step S120, self-learning by adopting a laser radar positioning error mode when the GNSS signals of the vehicle are available according to the target point cloud map, and obtaining a self-learning result of the laser radar positioning error mode.
And acquiring and loading the target point cloud map during actual operation, and self-learning by adopting a laser radar positioning error mode when the GNSS signals of the vehicle are available, and acquiring a self-learning result of the laser radar positioning error mode through the self-learning.
It can be understood that the lidar positioning error mode can be operated as a node in an automatic driving program, and when the lidar positioning error mode is started for self-learning, namely the error is continuously corrected, namely a self-learning result of the lidar positioning error mode is obtained through self-learning.
Of course, if the GNSS signal is available and the intensity is good, the self-learning result of the lidar positioning error mode is not updated or the initial state is used, and if the GNSS signal is intermittent, the self-learning result of the lidar positioning error mode is updated continuously.
And S130, when laser positioning observation is needed, self-adaptively correcting the positioning error generated when the laser radar is used for positioning according to the self-learning result of the laser radar positioning error mode to obtain a final positioning result.
When trees are sheltered or pass through a bridge opening and a viaduct in an operation area, the GNSS signals are unavailable, the observation values need to be positioned by laser at the moment, the positioning errors generated when the laser radar is used for positioning are corrected in a self-adaption mode through the self-learning result of the laser radar positioning error mode, and the final positioning result is obtained. Meanwhile, the real-time property can be real-time correction or fixed time delay correction.
For ROBOTAXI or ROBOBUS, the positioning error caused by calibration, installation, time synchronization and the like can be reduced in the laser positioning algorithm of various vehicle types to the maximum extent. Meanwhile, a laser radar positioning error mode is learned under the condition of good GNSS signals, the laser radar positioning result is adaptively corrected when the GNSS signals are lost or influenced, the corrected result is input to a filter to complete filter observation updating instead of the GNSS, the positioning result can be updated in real time, and accurate positioning is realized.
In an embodiment of the present application, when a laser positioning observation is needed, adaptively correcting a positioning error generated when a laser radar is used for positioning according to a self-learning result of the laser radar positioning error mode to obtain a final positioning result, including: calculating the proportional coefficients of the transverse error and the longitudinal error of laser positioning; correcting a laser positioning result meeting a preset condition according to the laser positioning transverse error and/or the laser positioning longitudinal error proportional coefficient; when laser positioning observation is needed, fusing a positioning result of positioning by using a laser radar and the corrected laser positioning result, and updating an observation value of a Kalman filter based on the fusion result; and taking the estimated value of the Kalman filter as a final positioning result.
During specific implementation, the operation vehicle is positioned by using the laser radar in the running process, and the positioning error generated when the laser radar is used for positioning is corrected in a self-adaption mode through the self-learning result of the laser radar positioning error mode.
The laser positioning transverse error and the laser positioning longitudinal error proportionality coefficient are calculated and used as the key factors for error correction. For the laser positioning transverse error, the laser positioning transverse error is mainly influenced by the calibration of the laser radar, and the laser positioning transverse error needs to be calculated. The laser positioning longitudinal error proportion coefficient is mainly influenced by time synchronization and the current corresponding vehicle speed, and the laser positioning longitudinal error needs to be calculated.
It should be noted that if the positioning error of the laser radar within a certain time period does not exceed the preset threshold, it can be considered that the laser radar does not have the problems of time synchronization and the like, the transverse error can be corrected by using the transverse error of laser positioning, but the proportional coefficient of the longitudinal error of laser positioning still needs to be calculated and determined.
Further, according to the laser positioning transverse error and/or the laser positioning longitudinal error proportional coefficient, correcting the laser positioning result meeting the preset condition, namely updating the self-adaptive error. That is, after the initial lateral error value and the longitudinal error scaling factor are available, the subsequent laser positioning result meeting the preset condition can be corrected. Fig. 2 is a schematic diagram of the longitudinal error before correction (laser positioning longitudinal error), after correction, showing the original longitudinal error of laser positioning, and the error corrected by the method in the embodiment of the present application. The original longitudinal error statistics for laser positioning on the left side is shown in fig. 3, and the corrected error statistics shown in fig. 4 remove the error in the initialization stage, so that the corrected error satisfies the normal distribution with the average value of 0, and more accurate position and error can be provided for the filter.
And then, the longitudinal positioning result with the error of normal distribution can be directly input into a Kalman filter for use. Meanwhile, when laser positioning observation is needed, the corrected laser positioning result is fused for observation and updating.
It should be noted that the positioning observation of lidar is needed when GNSS signals are weak or lost, or when any situation that has been used occurs.
In an embodiment of the present application, the obtaining the laser positioning result meeting the preset condition includes: whether the speed of the autonomous vehicle is greater than a preset speed threshold; whether the confidence degrees of the laser positioning results are all larger than a preset threshold value or not; the distance between the two frames of laser positioning and the displacement calculated by the speed of the vehicle body are within a preset error range.
In specific implementation, the laser positioning result is filtered by mainly considering the use of speed information and confidence coefficient information, so that the influence of an error position caused by point cloud matching is ensured. Further, the laser positioning data meeting the conditions needs to satisfy 3 conditions:
condition 1: whether the speed of the autonomous vehicle is greater than a preset speed threshold.
Illustratively, when the vehicle speed is greater than 3m/s: if the influence of time synchronization is received, the longitudinal error of laser positioning is increased along with the increase of the vehicle speed, but when the vehicle speed is reduced to 0, the influence of deceleration is also received, and the error is gradually reduced at the same static position, so the influence of low speed and parking is eliminated.
Condition 2: and whether the laser positioning results are all larger than a preset laser position reliability threshold value or not. Higher than a preset laser position reliability threshold value: because the laser positioning matching can output confidence coefficient according to the density and the like of the matched point cloud, when the confidence coefficient is actually set, the relation between the positioning error and the confidence coefficient can be calculated in a testing stage, and a threshold value is found to ensure that the laser positioning result higher than the threshold value is credible, namely, positioning jump cannot occur due to too few point clouds.
Condition 3: the distance between the two frames of laser positioning and the displacement calculated by the speed of the vehicle body are within a preset error range. In order to further ensure the influence of positioning jump, such as inaccurate confidence coefficient, the use speed is considered to be limited, that is, the distance between two frames of laser positioning and the displacement calculated by the vehicle body speed are within a preset error range, and the preset error range can be set according to a speed error coefficient and a laser positioning statistical error.
In an embodiment of the present application, before calculating the laser positioning lateral error and the laser positioning longitudinal error proportionality coefficient, the method further includes: the method comprises the steps of synchronizing the GNSS position, the laser positioning position information, the course angle information, the vehicle body speed information and the radar positioning confidence coefficient when GNSS signals with the same preset window size are available, and establishing an error self-adaptive data set, wherein the error self-adaptive data set is obtained by decomposing the GNSS position and the laser positioning position information when the GNSS signals are available into a transverse position set and a longitudinal position set under a vehicle coordinate system according to the course angle information, and the preset window size is set according to the laser positioning frequency.
In specific implementation, the laser positioning transverse error and the laser positioning longitudinal error proportionality coefficient need to be obtained from the transverse and longitudinal position sets of the vehicle coordinate system before calculation.
Further, a GNSS position, laser positioning position information, course angle information, body speed information, and radar positioning confidence may be employed when GNSS signals having the same preset window size are available in synchronization, and an error adaptive data set may be established. It will be appreciated that the preset window size may be set according to the frequency of laser positioning. The same preset window size, i.e. the same laser sampling frequency.
Illustratively, the error adaptive data set S is obtained by synchronizing the GNSS position loc _ GNSS, the position information of the laser positioning loc _ lidar, the heading angle information YAW, the vehicle speed information velocity, and the radar position confidence conf when the GNSS signal of the preset window size win _ size is good.
The window size is set to 1000 according to the frequency of laser positioning, that is, 1000 qualified laser positioning data and corresponding GNSS positioning data, and then { loc _ GNSS, loc _ identifier } is decomposed into a set S _ lat { loc _ GNSS _ lat, loc _ identifier _ lat } and a set S _ long { loc _ GNSS _ long, loc _ identifier _ long } of the own vehicle coordinate system according to the course angle information YAW.
In one embodiment of the present application, the laser positioning lateral error is calculated as follows: and counting errors in the transverse position set, and if the errors conform to normal distribution, judging that the average value of the current laser positioning transverse errors which are normally distributed is used as the laser positioning transverse errors in the self-learning result of the laser radar positioning error mode.
In specific implementation, considering that the laser positioning system is mainly influenced by calibration, the errors in the transverse position set S _ lat of the self-vehicle coordinate system are counted, and if the errors conform to normal distribution, the laser positioning transverse errors can be judged to be the average value of the normal distribution. The corrected errors satisfy the normal distribution with the mean value of 0, and more accurate positions and errors can be provided for the filter.
A KS test scheme can be used to detect if a normal distribution is met. For example, the error statistics after the correction shown in fig. 4 removes the error in the initialization stage, and the corrected error satisfies the normal distribution with the mean value of 0, so that a more accurate position and error can be provided for the filter.
In one embodiment of the present application, the laser positioning longitudinal error scaling factor is calculated as follows: counting errors in the longitudinal position set, and fitting vehicle speed and laser positioning longitudinal errors according to the vehicle body speed information; calculating an error proportional coefficient according to the vehicle speed and the laser positioning longitudinal error, and using the error fitting normal distribution corrected by the error proportional coefficient as the laser positioning longitudinal error proportional coefficient in the self-learning result of the laser radar positioning error mode; or, determining whether to correct the longitudinal error according to a longitudinal positioning error judgment threshold counted by the laser radar off-line, if the error mean value in the longitudinal position set is smaller than the judgment threshold, not performing longitudinal error correction, and only performing transverse error correction by using the laser positioning transverse error.
In specific implementation, the laser positioning longitudinal error proportional coefficient is mainly influenced by time synchronization and vehicle speed. The errors in the longitudinal position set S _ Long of the self-vehicle coordinate system can be counted, the vehicle speed and the longitudinal errors of laser positioning are fitted according to vehicle speed information, a proportional coefficient r is calculated, the following equation value is minimum, and the errors after r correction are used to accord with normal distribution.
Figure 806439DEST_PATH_IMAGE001
Wherein the content of the first and second substances,
Figure 317054DEST_PATH_IMAGE002
and the vertical error information of the ith laser radar in the window is shown.
Figure 565633DEST_PATH_IMAGE003
And represents the ith speed information in the window.
Or, determining whether to correct the longitudinal error according to a longitudinal positioning error judgment threshold value counted by the laser radar off-line, if the error mean value in the longitudinal position set is smaller than the judgment threshold value, not correcting the longitudinal error, and only correcting the transverse error by using the laser positioning transverse error.
Exemplarily, that is, according to the positioning statistical result of the laser radar, a positioning error of 2 σ is obtained, for example, 40cm, and if the error in the longitudinal position set is smaller than the determination threshold many times, it may be considered that the laser radar does not have the problem of time synchronization or the like, and only the lateral error correction may be performed, and the longitudinal error correction is required.
In one embodiment of the present application, the method further comprises: and updating the positioning result in real time according to the laser positioning transverse error or the laser positioning longitudinal error proportional coefficient in the self-learning result of the laser radar positioning error mode, wherein the updated process adopts the latest laser positioning transverse error or laser positioning longitudinal error proportional coefficient, or the updated process adopts the average value of the laser positioning transverse error or laser positioning longitudinal error proportional coefficient and the previous laser positioning transverse error or laser positioning longitudinal error proportional coefficient.
In specific implementation, in order to reduce the influence of time synchronization error change and the like caused by network signals and the like, the initial calculated error or error proportionality coefficient can be obtained and then updated in real time, and the latest laser positioning transverse error or laser positioning longitudinal error proportionality coefficient can be selected and adopted in the updating method; or, the laser positioning transverse error or laser positioning longitudinal error proportionality coefficient and the average value of the laser positioning transverse error or laser positioning longitudinal error proportionality coefficient are adopted.
The embodiment of the present application further provides a fusion positioning device 500 for automatic driving, and as shown in fig. 5, a schematic structural diagram of the fusion positioning device 500 for automatic driving in the embodiment of the present application is provided, where the device 500 at least includes: a point cloud map building module 510, an error self-learning module 520, and a correction module 530, wherein:
in an embodiment of the present application, the point cloud map building module 510 is specifically configured to: the method comprises the steps of collecting laser data of a preset area in advance and establishing to obtain a target point cloud map.
Because the structures of various vehicle types such as the ROBOTAXI and the ROBOBUS are inconsistent, the models and the installation positions of the laser radars are greatly different, and the ROBOTAXI and the ROBOBUS can use the same target point cloud map through the pre-established target point cloud map.
Illustratively, laser data in a preset ROBOTAXI or ROBOBUS operation area can be collected by a laser radar collection vehicle which is provided with time synchronization equipment, calibration equipment and truth value equipment, a point cloud map is established through post-processed positioning data and the point cloud data after distortion removal, and the map is post-processed through rarefaction, point cloud absolute position assignment and the like. And then, obtaining a target point cloud map.
The preset operation area refers to a fixed area where ROBOTAXI or ROBOBUS is to operate, such as a park, and the like. That is, both ROBOTAXI and ROBOBUS models may be different, but serve the same operating area. Thus, the target point cloud map can be directly used when the ROBOTAXI or ROBOBUS is actually operated.
This has the advantages that:
(1) The map consistency is ensured, and the time for each vehicle to acquire, generate and update the map is reduced.
(2) The accuracy standard of operation car calibration is reduced, for example, high accuracy calibration needs to be carried out in a specific calibration space/field, and if the accuracy of the collection car needs to be calibrated, high labor and time costs are needed.
(3) Due to the fact that different vehicle types need to be configured with laser radars with non-stop beams, errors caused by the laser radars in types such as 16 lines, 32 lines and 80 lines are eliminated by the aid of the same target point cloud map.
(4) Based on the advantages of the above (1) - (3), the error caused by inconsistent errors of different sensor point clouds is reduced.
And after the target point cloud map is obtained, deploying the generated map to ROBOTAXI or ROBOBUS in the operation area. It should be noted that ROBOTAXI or ROBOBUS in the operation area may be loaded in advance and obtain the target point cloud map.
In an embodiment of the present application, the error self-learning module 520 is specifically configured to: and self-learning by adopting a laser radar positioning error mode when the GNSS signal of the vehicle is available according to the target point cloud map to obtain a self-learning result of the laser radar positioning error mode.
And acquiring and loading the target point cloud map during actual operation, and self-learning by adopting a laser radar positioning error mode when the GNSS signals of the vehicle are available, and acquiring a self-learning result of the laser radar positioning error mode through the self-learning.
It can be understood that the lidar positioning error mode can be operated as a node in an automatic driving program, and when the lidar positioning error mode is started for self-learning, namely the error is continuously corrected, namely a self-learning result of the lidar positioning error mode is obtained through self-learning.
Of course, if the GNSS signal is available and the intensity is good, the self-learning result of the lidar positioning error mode is not updated or the initial state is used, and if the GNSS signal is intermittent, the self-learning result of the lidar positioning error mode is updated continuously.
In an embodiment of the present application, the correcting module 530 is specifically configured to: when laser positioning observation is needed, the positioning error generated when the laser radar is used for positioning is corrected in a self-adaption mode through the self-learning result of the laser radar positioning error mode, and a final positioning result is obtained.
When trees are shielded in an operation area or pass through a bridge opening and a viaduct, the GNSS signal is unavailable, and a positioning error generated when the laser radar is used for positioning is corrected in a self-learning result self-adaption mode of the laser radar positioning error mode to obtain a final positioning result. Meanwhile, in order to ensure real-time performance, real-time correction or fixed delay correction can be carried out.
For ROBOTAXI or ROBOBUS, the positioning error caused by the problems of calibration, installation, time synchronization and the like of different laser radars of different vehicle types can be reduced to the greatest extent. Meanwhile, a laser radar positioning error mode is learned under the condition of good GNSS signals, the laser radar positioning result is adaptively corrected when the GNSS signals are lost or influenced, the corrected result is input to a filter to complete filter observation updating instead of the GNSS, the positioning result can be updated in real time, and accurate positioning is realized.
It can be understood that the fusion positioning device for automatic driving can implement the steps of the fusion positioning method for automatic driving provided in the foregoing embodiment, and the relevant explanations regarding the fusion positioning method for automatic driving are applicable to the fusion positioning device for automatic driving, and are not described herein again.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application. Referring to fig. 6, at a hardware level, the electronic device includes a processor, and optionally further includes an internal bus, a network interface, and a memory. The Memory may include a Memory, such as a Random-Access Memory (RAM), and may further include a non-volatile Memory, such as at least 1 disk Memory. Of course, the electronic device may also include hardware required for other services.
The processor, the network interface, and the memory may be connected to each other via an internal bus, which may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one double-headed arrow is shown in FIG. 6, but this does not indicate only one bus or one type of bus.
And the memory is used for storing programs. In particular, the program may include program code comprising computer operating instructions. The memory may include both memory and non-volatile storage and provides instructions and data to the processor.
The processor reads a corresponding computer program from the nonvolatile memory into the memory and then runs the computer program to form the fusion positioning device for automatic driving on a logic level. The processor is used for executing the program stored in the memory and is specifically used for executing the following operations:
collecting laser data of a preset area in advance and establishing to obtain a target point cloud map;
according to the target point cloud map, when the GNSS signals of the vehicle are available, a laser radar positioning error mode is adopted for self-learning, and a self-learning result of the laser radar positioning error mode is obtained;
when laser positioning observation is needed, the positioning error generated when the laser radar is used for positioning is corrected in a self-adaptive mode through the self-learning result of the laser radar positioning error mode, and a final positioning result is obtained.
The method executed by the fusion positioning device for automatic driving disclosed in the embodiment of fig. 1 of the present application can be applied to or implemented by a processor. The processor may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the above method may be performed by integrated logic circuits of hardware in a processor or instructions in the form of software. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic blocks disclosed in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module may be located in ram, flash memory, rom, prom, or eprom, registers, etc. storage media as is well known in the art. The storage medium is located in a memory, and a processor reads information in the memory and completes the steps of the method in combination with hardware of the processor.
The electronic device may further execute the method executed by the fusion positioning device for automatic driving in fig. 1, and implement the functions of the fusion positioning device for automatic driving in the embodiment shown in fig. 1, which are not described herein again in this application embodiment.
An embodiment of the present application further provides a computer-readable storage medium storing one or more programs, where the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to perform the method performed by the fusion positioning apparatus for automatic driving in the embodiment shown in fig. 1, and are specifically configured to perform:
collecting laser data of a preset area in advance and establishing to obtain a target point cloud map;
according to the target point cloud map, when the GNSS signals of the vehicle are available, a laser radar positioning error mode is adopted for self-learning, and a self-learning result of the laser radar positioning error mode is obtained;
when laser positioning observation is needed, the positioning error generated when the laser radar is used for positioning is corrected in a self-adaption mode through the self-learning result of the laser radar positioning error mode, and a final positioning result is obtained.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising a … …" does not exclude the presence of another identical element in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement or the like made within the spirit and principle of the present application shall be included in the scope of the claims of the present application.

Claims (7)

1. A fusion localization method for autonomous driving, wherein the method comprises:
the method comprises the steps of collecting laser data of a preset area in advance and establishing a target point cloud map, wherein the preset area comprises the same operation area where vehicles of different vehicle types are planned to operate;
according to the target point cloud map, when the GNSS signals of the vehicle are available, a laser radar positioning error mode is adopted for self-learning, and a self-learning result of the laser radar positioning error mode is obtained;
decomposing the GNSS position when the GNSS signal is available and the position information of the laser positioning into a transverse position set and a longitudinal position set under a self-vehicle coordinate system according to course angle information, and establishing an error self-adaptive data set;
calculating a laser positioning transverse error and a laser positioning longitudinal error proportional coefficient;
correcting a laser positioning result meeting preset conditions according to the laser positioning transverse error and/or the laser positioning longitudinal error proportional coefficient;
when laser positioning observation is needed, fusing a positioning result of positioning by using a laser radar and the corrected laser positioning result, and updating an observation value of a Kalman filter based on the fusion result;
taking the estimated value of the Kalman filter as a final positioning result;
wherein the content of the first and second substances,
the laser positioning lateral error is calculated as follows:
counting errors in the transverse position set, and if the errors conform to normal distribution, judging the average value of the normal distribution of the current laser positioning transverse errors as the laser positioning transverse errors in the self-learning result of the laser radar positioning error mode;
the laser positioning longitudinal error proportional coefficient is calculated according to the following mode:
counting errors in the longitudinal position set, and fitting the vehicle speed and the laser positioning longitudinal errors according to vehicle body speed information;
calculating an error proportional coefficient according to the vehicle speed and the laser positioning longitudinal error, and enabling the error corrected by the error proportional coefficient to be in accordance with normal distribution;
or, determining whether to correct the longitudinal error according to a longitudinal positioning error judgment threshold value counted by the laser radar off-line, if the error mean value in the longitudinal position set is smaller than the judgment threshold value, not correcting the longitudinal error, and only correcting the transverse error by using the laser positioning transverse error.
2. The method of claim 1, wherein the preset conditions include:
whether the speed of the autonomous vehicle is greater than a preset speed threshold;
whether the confidence coefficient of the laser positioning result is greater than a preset threshold value or not;
the distance between the two frames of laser positioning and the displacement calculated by the speed of the vehicle body are within a preset error range.
3. The method of claim 1, wherein before calculating the laser positioning lateral error and the laser positioning longitudinal error scaling factor, the method further comprises:
the method comprises the steps of synchronizing the GNSS position, the laser positioning position information, the course angle information, the vehicle body speed information and the radar positioning confidence coefficient when GNSS signals with the same preset window size are available, and establishing an error self-adaptive data set, wherein the error self-adaptive data set is obtained by decomposing the GNSS position and the laser positioning position information when the GNSS signals are available into a transverse position set and a longitudinal position set under a vehicle coordinate system according to the course angle information, and the preset window size is set according to the laser positioning frequency.
4. The method of claim 1, wherein the method further comprises:
updating the positioning result in real time according to the laser positioning transverse error or the laser positioning longitudinal error proportional coefficient in the self-learning result of the laser radar positioning error mode;
the updating process adopts the latest laser positioning transverse error or laser positioning longitudinal error proportionality coefficient,
or, the updating process adopts the average value of the laser positioning transverse error or laser positioning longitudinal error proportionality coefficient and the previous laser positioning transverse error or laser positioning longitudinal error proportionality coefficient.
5. A fusion positioning apparatus for autopilot, wherein the apparatus comprises:
the system comprises a point cloud map establishing module, a point cloud map generating module and a point cloud map generating module, wherein the point cloud map establishing module is used for acquiring laser data of a preset area in advance and establishing to obtain a target point cloud map, and the preset area comprises the same operation area for vehicles of different vehicle types to operate;
the error self-learning module is used for carrying out self-learning by adopting a laser radar positioning error mode when the GNSS signals of the vehicle are available according to the target point cloud map so as to obtain a self-learning result of the laser radar positioning error mode;
the correction module is used for decomposing the GNSS position when the GNSS signal is available and the laser positioning position information into a transverse position set and a longitudinal position set under a self-vehicle coordinate system according to course angle information, and establishing an error self-adaptive data set;
calculating the proportional coefficients of the transverse error and the longitudinal error of laser positioning;
correcting a laser positioning result meeting a preset condition according to the laser positioning transverse error and/or the laser positioning longitudinal error proportional coefficient;
when laser positioning observation is needed, fusing a positioning result of positioning by using a laser radar and the corrected laser positioning result, and updating an observation value of a Kalman filter based on the fusion result;
taking the estimated value of the Kalman filter as a final positioning result;
wherein the content of the first and second substances,
the laser positioning lateral error is calculated as follows:
counting errors in the transverse position set, and if the errors conform to normal distribution, judging the average value of the normal distribution of the current laser positioning transverse errors as the laser positioning transverse errors in the self-learning result of the laser radar positioning error mode;
the laser positioning longitudinal error proportional coefficient is calculated according to the following mode:
counting errors in the longitudinal position set, and fitting the vehicle speed and the laser positioning longitudinal errors according to vehicle body speed information;
calculating an error proportional coefficient according to the vehicle speed and the laser positioning longitudinal error, and enabling the error corrected by the error proportional coefficient to be in accordance with normal distribution;
or, determining whether to correct the longitudinal error according to a longitudinal positioning error judgment threshold value counted by the laser radar off-line, if the error mean value in the longitudinal position set is smaller than the judgment threshold value, not correcting the longitudinal error, and only correcting the transverse error by using the laser positioning transverse error.
6. An electronic device, comprising:
a processor; and
a memory arranged to store computer executable instructions that when executed cause the processor to perform the method of any of claims 1~4.
7. A computer readable storage medium storing one or more programs which, when executed by an electronic device that includes a plurality of application programs, cause the electronic device to perform the method of any of claims 1~4.
CN202211341937.6A 2022-10-31 2022-10-31 Fusion positioning method and device for automatic driving, electronic equipment and storage medium Active CN115390086B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211341937.6A CN115390086B (en) 2022-10-31 2022-10-31 Fusion positioning method and device for automatic driving, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211341937.6A CN115390086B (en) 2022-10-31 2022-10-31 Fusion positioning method and device for automatic driving, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN115390086A CN115390086A (en) 2022-11-25
CN115390086B true CN115390086B (en) 2023-03-31

Family

ID=84115116

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211341937.6A Active CN115390086B (en) 2022-10-31 2022-10-31 Fusion positioning method and device for automatic driving, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115390086B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115856979B (en) * 2023-02-16 2023-06-02 智道网联科技(北京)有限公司 Positioning method and device for automatic driving vehicle, electronic equipment and storage medium
CN115950441B (en) * 2023-03-08 2023-07-07 智道网联科技(北京)有限公司 Fusion positioning method and device for automatic driving vehicle and electronic equipment

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11651244B2 (en) * 2018-10-04 2023-05-16 Here Global B.V. Method and apparatus for predicting sensor error
CN111708043B (en) * 2020-05-13 2023-09-26 阿波罗智能技术(北京)有限公司 Positioning method and device
CN113935904A (en) * 2021-08-27 2022-01-14 清华大学 Laser odometer error correction method, system, storage medium and computing equipment
CN113759364A (en) * 2021-09-06 2021-12-07 浙江大学 Millimeter wave radar continuous positioning method and device based on laser map
CN114089365B (en) * 2022-01-20 2022-05-17 智道网联科技(北京)有限公司 Automatic driving vehicle positioning method and device, electronic equipment and storage medium
CN114545454A (en) * 2022-02-15 2022-05-27 南京航空航天大学 Fusion navigation system integrity monitoring method for automatic driving
CN115031755A (en) * 2022-06-13 2022-09-09 智道网联科技(北京)有限公司 Automatic driving vehicle positioning method and device, electronic equipment and storage medium
CN114894214A (en) * 2022-06-13 2022-08-12 智道网联科技(北京)有限公司 Fusion positioning method and device for automatic driving vehicle and electronic equipment
CN114877900A (en) * 2022-06-20 2022-08-09 智道网联科技(北京)有限公司 Automatic driving vehicle fusion positioning method for tunnel and related device

Also Published As

Publication number Publication date
CN115390086A (en) 2022-11-25

Similar Documents

Publication Publication Date Title
CN115390086B (en) Fusion positioning method and device for automatic driving, electronic equipment and storage medium
CN111947671B (en) Method, apparatus, computing device and computer-readable storage medium for positioning
CN114279453B (en) Automatic driving vehicle positioning method and device based on vehicle-road cooperation and electronic equipment
CN113791435B (en) GNSS signal abnormal value detection method and device, electronic equipment and storage medium
CN114777814A (en) Fusion positioning precision evaluation method, device and system based on vehicle road cloud
CN114894214A (en) Fusion positioning method and device for automatic driving vehicle and electronic equipment
CN115507862A (en) Lane line positioning method and device, electronic device and storage medium
CN115056801A (en) Multipath recognition method and device for automatic driving, electronic equipment and storage medium
CN115390103A (en) Satellite positioning signal abnormity detection method and device and electronic equipment
CN115962774A (en) Point cloud map updating method and device, electronic equipment and storage medium
CN114966632A (en) Laser radar calibration method and device, electronic equipment and storage medium
CN115856979B (en) Positioning method and device for automatic driving vehicle, electronic equipment and storage medium
CN115950441B (en) Fusion positioning method and device for automatic driving vehicle and electronic equipment
CN116295490A (en) Vehicle positioning method and device, electronic equipment and storage medium
CN116148821A (en) Laser radar external parameter correction method and device, electronic equipment and storage medium
CN116546424A (en) Laser mapping method and device, laser positioning method and device
CN116222586A (en) Fusion positioning method and device for automatic driving vehicle and electronic equipment
CN116164763A (en) Target course angle determining method and device, electronic equipment and storage medium
CN115183786A (en) Training method and device of sensor error prediction model for automatic driving
CN115031755A (en) Automatic driving vehicle positioning method and device, electronic equipment and storage medium
CN115014395A (en) Real-time calibration method and device for vehicle course angle for automatic driving
CN117572335B (en) Updating method and device for laser positioning confidence coefficient and electronic equipment
CN116518986B (en) Positioning method and device for automatic driving vehicle, electronic equipment and storage medium
CN116559899B (en) Fusion positioning method and device for automatic driving vehicle and electronic equipment
CN115014333B (en) Signal map construction method and device, electronic equipment and storage 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