CN117572476B - Automatic driving vehicle positioning adjustment method and device based on driving track - Google Patents
Automatic driving vehicle positioning adjustment method and device based on driving track Download PDFInfo
- Publication number
- CN117572476B CN117572476B CN202410051504.XA CN202410051504A CN117572476B CN 117572476 B CN117572476 B CN 117572476B CN 202410051504 A CN202410051504 A CN 202410051504A CN 117572476 B CN117572476 B CN 117572476B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- target vehicle
- real
- positioning
- information
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 64
- 230000000007 visual effect Effects 0.000 claims abstract description 12
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000011084 recovery Methods 0.000 claims description 3
- 238000004590 computer program Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 9
- 238000012937 correction Methods 0.000 description 8
- 238000012512 characterization method Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000009877 rendering Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The application provides an automatic driving vehicle positioning adjustment method and device based on a driving track. The utility model relates to an autopilot vehicle positioning technology field solves under the high-speed tracking mode, the problem of vehicle left and right swing, and this method includes: under the condition that the RTK is in a non-differential state and the laser or visual sensor cannot provide a reliable position, acquiring real-time positioning information of a target vehicle in tracking running, and determining the transverse deviation between the real-time positioning information of the target vehicle and a navigation track according to the real-time positioning information; based on the comparison relation between the pre-calibrated vehicle speed and the vehicle transverse error, according to the vehicle speed information and the transverse deviation of the target vehicle, when the transverse deviation exceeds the corresponding maximum error allowable value, the real-time positioning of the target vehicle is adjusted within the time period of the available time period T. According to the method and the device, the driving route of the target vehicle is adjusted within a certain time, and the body feeling and the rationality of the driving of the vehicle are guaranteed to the greatest extent.
Description
Technical Field
The invention relates to the technical field of automatic driving vehicle positioning, in particular to an automatic driving vehicle positioning technology based on a driving track.
Background
Autonomous vehicles have been landed in more and more cities, due to the high complexity of urban environments, including urban canyons, urban tunnels, the influence of greening trees on both sides of roads, the stability of GNSS (Global Navigation Satellite System, global satellite navigation system)/RTK (Real-time kinematic) signals can be affected, and the combined navigation of conventional GNSS/rtk+imu (Inertial Measurement Unit, inertial measurement system) is limited by the signal stability of GNSS/RTK, which cannot provide centimeter level positioning accuracy in highly complex scenes.
Therefore, the visual or laser positioning technology is also an auxiliary positioning technology except for the GNSS/RTK, and based on a pre-established map, when the GNSS/RTK signal fails, the camera or the laser sensor can provide additional observation updating information so as to ensure the positioning stability of the automatic driving vehicle.
Ideally, the accuracy of the laser point cloud matching positioning can reach the centimeter level (within 10 cm), but is affected by the following factors:
1. the vehicle travels for a long time, and external parameters of the camera or the laser sensor are changed.
2. The vehicle is traveling fast, an error in time synchronization is generated, and the faster the vehicle traveling speed, the larger the error will be.
3. When the sensor is blocked, the optimal result cannot be obtained by calculation due to the limitation of the matching algorithm.
In summary, even though visual or laser positioning techniques may provide additional observation information, positioning accuracy may be affected for various reasons, and errors may be extended to decimeter level, even meter level; therefore, an error of 20cm or more is probabilistically brought about, and the fluctuation of the error causes the vehicle to swing left and right in a high-speed tracking mode, so that the passenger feel is poor.
Disclosure of Invention
In order to solve the technical defects, the embodiment of the application provides an automatic driving vehicle positioning adjustment method and device based on a driving track.
An embodiment of a first aspect of the present application provides a method for adjusting positioning of an automatic driving vehicle based on a driving track, including:
under the condition that the RTK is in a non-differential state and a laser or visual sensor cannot provide a reliable position, acquiring real-time positioning information of a target vehicle in tracking running, and determining the transverse deviation between the real-time positioning information of the target vehicle and a navigation track according to the real-time positioning information;
determining whether the lateral deviation exceeds a corresponding error maximum allowable value according to the vehicle speed information of the target vehicle and the lateral deviation based on a comparison relation between a pre-calibrated vehicle speed and a vehicle lateral error;
and when the transverse deviation exceeds the corresponding maximum allowable error value, adjusting the real-time positioning of the target vehicle in a period of time T when the vehicle is available.
In a possible implementation manner, the adjusting the real-time positioning of the target vehicle includes:
the lateral position in the set navigation track is used instead of the lateral position of the filter.
In a possible implementation manner, the usable time length T is a driving time length of the target vehicle without changing lanes and without stopping at an intersection;
the step of obtaining the usable time length T includes:
mapping the navigation track and the real-time positioning information to a pre-stored map;
calculating the straight distance of the target vehicle according to the map and the navigation track;
and calculating the usable time length T of the target vehicle according to the straight distance and the vehicle speed information.
In a possible implementation manner, adjusting the real-time positioning of the target vehicle further includes:
limiting obstacle avoidance operation of the target vehicle within a usable time length T; and correcting the transverse position of the target vehicle according to the result of the visual lane line matching calculation, so as to ensure the positioning of the lane level.
In a possible implementation manner, the obstacle avoidance operation includes at least one of the following operations: active obstacle avoidance, overtaking operation and lane changing operation.
In a possible implementation manner, the method further includes: calibrating the comparison relation between the vehicle speed and the vehicle transverse error, comprising:
and in the tracking mode, testing the vehicle vibration amplitude caused by the vehicle transverse error of the automatic driving vehicle with the same model as the target vehicle at different speeds, and determining the maximum allowable value of the transverse error at different speeds based on preset control parameters.
In one possible implementation manner, acquiring real-time positioning information of a target vehicle in tracking running and determining a lateral deviation between the real-time positioning information of the target vehicle and a navigation track according to the real-time positioning information includes:
position information of a central point of a vehicle rear axle of the target vehicle, which is acquired by using the RTK, auxiliary vision or laser positioning technology;
updating the position information of the center point by using a positioning filter to obtain real-time positioning information of the target vehicle;
determining the distance between the real-time positioning information and a track point closest to the central point of the rear axle of the vehicle in the navigation track;
and taking the distance as the transverse deviation of the target vehicle and the navigation track.
In a possible implementation manner, the method further includes:
and periodically updating the usable time length T, and reducing the speed of the target vehicle and waiting for the recovery of an RTK signal when no other vehicle is in the preset range of the target vehicle or the front speed of the target vehicle is lower than a preset speed threshold value.
In a possible implementation manner, the method further includes:
and if the RTK signal is recovered, eliminating the deviation according to the deviation of the recovered RTK positioning information of the target vehicle and the real-time positioning information of the target vehicle, and taking the RTK positioning information as the position information of the target vehicle to carry out tracking running.
In a second aspect, the present invention also provides an automatic driving vehicle positioning adjustment device based on a driving track, including:
the positioning module is used for acquiring real-time positioning information of a target vehicle in tracking running under the condition that the RTK is in a non-differential state and a laser or visual sensor cannot provide a reliable position, and determining the transverse deviation between the real-time positioning information of the target vehicle and a navigation track according to the real-time positioning information;
the comparison module is used for determining whether the transverse deviation exceeds the corresponding maximum error allowable value according to the speed information of the target vehicle and the transverse deviation based on the comparison relation between the pre-calibrated speed and the maximum vehicle transverse error allowable value;
and the adjusting module is used for adjusting the real-time positioning of the target vehicle in a period of time T when the transverse deviation exceeds the corresponding maximum allowable error value.
A third aspect of the embodiments of the present application further provides an electronic device, including:
a memory; a processor; a computer program;
wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method as described above.
A fourth aspect of the present embodiments also provides a computer-readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement the method as described above.
According to the automatic driving vehicle positioning adjustment method and device based on the driving track, under the condition that the RTK is in a non-differential state and the laser/vision cannot provide reliable position information, reasonable virtual positioning information is calculated according to the information such as the transverse deviation of the real-time positioning information and the preset navigation track, the speed, the perception, the high-precision map and the like, and is provided for the downstream; meanwhile, before the positioning signal is recovered, the behavior of the vehicle is limited by combining with the downstream, so that the normal running of the target vehicle (without deviating from a navigation track, without missing a station, an intersection and the like) is ensured, and the body feeling and the rationality of the running of the vehicle are ensured to the greatest extent.
Drawings
FIG. 1 is a flow chart of a method for automatically driving a vehicle positioning adjustment based on a driving trajectory according to one embodiment of the present invention;
FIG. 2 is a schematic view of the direction of travel of a straight intersection according to one embodiment of the present invention;
FIG. 3 is a schematic view of the direction of travel of an intersection according to one embodiment of the present invention;
FIG. 4 is a schematic view of a driving track-based automatic driving vehicle positioning adjustment device according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a computing device according to one embodiment of the invention;
fig. 6 is a schematic diagram of a computer-readable storage medium according to one embodiment of the invention.
Detailed Description
In order to make the technical solutions and advantages of the embodiments of the present application more apparent, the following detailed description of exemplary embodiments of the present application is given with reference to the accompanying drawings, and it is apparent that the described embodiments are only some of the embodiments of the present application and not exhaustive of all the embodiments. It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other.
Since the signal stability of GNSS/RTK is limited, an autonomous vehicle may cause a certain lateral error, if a sudden or rapid adjustment route may cause uncomfortable feeling to passengers and drivers, and may also cause a vehicle to swing left and right, in some cases, the sudden or rapid adjustment route may also affect other vehicles that normally travel on a road, so a method is needed to adjust the travel route of the autonomous vehicle based on a preset travel track in a tracking mode, and combine with navigation planning control to ensure the feeling of the vehicle traveling.
As shown in fig. 1, in an embodiment of the present invention, an automatic driving vehicle positioning adjustment method based on a travel track starts at step S110.
In step S110: under the condition that the RTK is in a non-differential state and the laser or visual sensor cannot provide a reliable position, acquiring real-time positioning information of a target vehicle in tracking running, and determining the transverse deviation of the real-time positioning information of the target vehicle and a navigation track according to the real-time positioning information.
In the embodiment of the invention, the global satellite navigation system and the ground receiving equipment calculate the distance between the global satellite navigation system and each satellite by receiving the signals (including time and satellite positions) of the navigation satellites so as to determine the position. The GNSS currently in use includes: GPS in the united states (Global Positioning System ), GLONASS in russia: (Global Navigation Satellite System, glonass system), BDS of china: (BeiDou Navigation Satellite System, beidou system), GALILEO (GALILEO satellite navigation system) in europe. The GNSS system utilizes the differential technology to improve the precision of civil positioning. The principle is that a GNSS receiver is matched with a known point with accurately measured position as a reference station, the GNSS observation is synchronously carried out with a user (mobile station), the obtained single-point positioning result is compared with the reference station coordinate, and the real-time differential correction value is solved. At present, the information modes sent by the differential base station can be divided into three types:
position difference: i.e. corrected by errors in the position of the reference station, which is the simplest one, any GNSS receiver can be adapted and composed to such a differential system, the base station sending out errors in the coordinates of the positioning and the known coordinates to be received and corrected by the user. A prerequisite for this difference is that the reference station and the subscriber station observe the same set of satellites, which is appropriate for the situation where the subscriber is within 100km of the base station.
Pseudo-range difference: i.e. corrected by the error of the reference station to the respective satellite. This is the most widely used difference, in which all satellites are observed at a reference station, and the true distance from each moment of each satellite to the reference station is determined from the known coordinates of the reference station and the coordinates of each satellite. And then the pseudo-range correction is compared with the measured pseudo-range, so that the pseudo-range correction is obtained and transmitted to a user receiver, and the positioning accuracy is improved. This difference can obtain the positioning accuracy of the meter level.
Phase difference: the Real-time dynamic carrier phase technique, also known as RTK (Real-time Kinematic), is a differential method that processes the observed quantity of the carrier phases of two stations in Real time. The carrier phase acquired by the reference station is sent to the user receiver to calculate the coordinate by difference. Since the carrier is much more accurate than its content (C/a code rate is 1.023MHz, one code length is 977.5ns, i.e. 293 meters, and carrier rate is 1575.42MHz, one carrier length is 635ps, i.e. 19 cm), carrier phase difference can bring the positioning accuracy to centimeter or even millimeter level. RTK technology is widely applied in the field of vehicle autopilot where highly accurate positioning is required.
In the embodiment of the invention, in a GNSS/RTK non-differential state, high-confidence observation positioning cannot be provided, and additional observation information provided by a camera or a laser sensor can be assisted, but as described above, the positioning accuracy of the camera or the laser sensor can be influenced by various factors and certain errors can exist; in the embodiment of the invention, the obtained position information is updated by using the positioning filter, so that the transverse deviation between the target vehicle and the navigation track is determined, and the process can be as follows:
in one implementation, the step S110 of obtaining real-time positioning information of the target vehicle during tracking, and determining the lateral deviation of the target vehicle from the navigation track according to the real-time positioning information includes:
position information of a central point of a vehicle rear axle of the target vehicle, which is acquired by using the RTK, auxiliary vision or laser positioning technology;
updating the position information of the center point by using a positioning filter to obtain real-time positioning information of the target vehicle;
determining the distance between the real-time positioning information and a track point closest to the central point of the rear axle of the vehicle in the navigation track;
and taking the distance as the transverse deviation of the target vehicle and the navigation track.
In the embodiment of the present invention, under the condition that the GNSS/RTK is in a non-differential state and the laser/vision cannot provide a reliable position, the position output by the positioning filter is used as the real-time positioning information, and the real-time positioning information obtained in the embodiment of the present invention is virtual positioning information, where the positioning filter predicts the state at the current time according to the state at the previous time, weights the predicted state and the measured value at the current time, and the weighted result is considered to be the current state, so that the measured value at the current time is not only adopted or listened to (as described above, both the RTK measured value at the current time and the laser/vision measured value have errors).
In the embodiment of the invention, when the distance between the real-time positioning information and the track point of the navigation track closest to the central point of the rear axle of the vehicle is determined, the real-time positioning information and the position of the track point are required to be unified under a coordinate system, the track point of the real-time positioning information and the navigation track closest to the central point of the rear axle of the vehicle can be converted into a vehicle body coordinate system, and the transverse deviation between the target vehicle and the preset navigation track is calculated. The real-time positioning information and the track point of the navigation track closest to the center point of the rear axle of the vehicle can be converted into a world coordinate system, and the transverse deviation between the target vehicle and the preset navigation track is calculated.
In step S120: and determining whether the lateral deviation exceeds a corresponding error maximum allowable value according to the speed information of the target vehicle and the lateral deviation based on the comparison relation between the pre-calibrated speed and the lateral error of the vehicle.
In one implementation manner, the embodiment of the invention needs to pre-calibrate the comparison relation between the vehicle speed and the vehicle transverse error, and comprises the following steps:
and in the tracking mode, testing the vehicle vibration amplitude caused by the vehicle transverse error of the automatic driving vehicle with the same model as the target vehicle at different speeds, and determining the maximum allowable value of the transverse error at different speeds based on preset control parameters.
According to the embodiment of the invention, the acceptable maximum value of the error under different vehicle speeds is calculated by testing the vehicle shaking amplitude of the automatic driving vehicle caused by the transverse error of the vehicle under different vehicle speeds, namely the maximum allowable value of the transverse error is calculated, for example, under the condition of 60km/h of speed per hour, the transverse error of the vehicle exceeds 20cm, and the vehicle can be caused to swing under the preset control parameters. The comparison relation between the specific calibrated vehicle speed and the maximum allowable value of the vehicle transverse error can be expressed in the form of a control learning table, namely, the server stores a table of the corresponding comparison relation between the vehicle speed and the maximum allowable value of the vehicle transverse error for each model of automatic driving vehicle, as shown in the table 1:
TABLE 1
The system comprises a vehicle body, a vehicle speed control system and a vehicle speed control system, wherein Aij represents an i-th model automatic driving vehicle, j-th vehicle speed, xij represents an i-th model automatic driving vehicle, the maximum value of i is the number of the automatic driving vehicle models under j vehicle speeds, the maximum value of i is increased along with the increase of the vehicle types, j is the number of divided vehicle speeds, and the maximum value of Aij is the highest speed limit of the current vehicle running on various road sections. For example, the highest speed limit of a highway is 120 km/h, the specified speed limit of an urban road is generally 40 to 60km/h (different cities and different road conditions), and the highest speed value is 120 km/h when the comparison relation between the vehicle speed and the maximum allowable value of the transverse error of the vehicle is calibrated in the embodiment of the invention.
As shown in fig. 2, for a straight crossing, a vehicle can only go straight when passing through the straight crossing, and a navigation track from north to south can be considered as a route, when a target vehicle passes through the straight crossing by taking the navigation route as an example from north to south, the route is shown in (1) in fig. 2, wherein the target vehicle is represented as a rounded rectangle, a center point of a rear axle of the target vehicle is represented as an asterisk, position information of the center point of the rear axle of the target vehicle is detected by using a positioning technology, and real-time positioning information (virtual positioning information) of the target vehicle is determined after optimization by using a positioning filter. And then determining the position of the nearest track point of the navigation track from the central point of the rear axle of the vehicle, wherein the distance L between the central point of the rear axle of the target vehicle and the nearest track point of the navigation track from the central point of the rear axle of the vehicle can be measured by utilizing an extension line, and the length of the L is the transverse deviation between the target vehicle and the navigation track.
As shown in fig. 3, for an intersection or a t-junction, a vehicle may go straight, turn left, or turn right when passing through the intersection (the t-junction is similar in case, and the driving direction is reduced according to the situation of the intersection compared with the intersection), for a vehicle driving from south to north, there are three possible driving directions at the intersection, taking a navigation route as an example, and when the target vehicle passes through the intersection, the route is shown in fig. 3 (2), wherein the target vehicle is represented as a rounded rectangle, the center point of the rear axle of the target vehicle is represented as an asterisk, the position information of the center point of the rear axle of the target vehicle is detected by using a positioning technique, and after optimization by using a positioning filter, real-time positioning information (virtual positioning information) of the target vehicle is determined. Then, the position of the track point of the navigation track closest to the center point of the rear axle of the vehicle is determined, and the navigation route in fig. 3 is a curve or an arc, so that the track point of the navigation track closest to the center point of the rear axle of the vehicle can be determined by the following method: the tangent line of the curve or the circular arc is perpendicular to the connecting line of the central point of the vehicle rear axle and the track point, the corresponding track point is the track point closest to the central point of the vehicle rear axle, therefore, the distance L between the central point of the rear axle of the target vehicle and the track point closest to the central point of the vehicle rear axle of the navigation track is the connecting line of the central point of the vehicle rear axle and the track point, and the length of L is the transverse deviation between the target vehicle and the navigation track.
In step S130: and when the transverse deviation exceeds the corresponding maximum allowable error value, adjusting the real-time positioning of the target vehicle in a period of time T when the vehicle is available.
In the embodiment of the invention, in order to avoid uncomfortable feeling and vehicle swing caused by suddenly or quickly adjusting the route to passengers and drivers, other vehicles which normally run on the road can be influenced by suddenly or quickly adjusting the route, the route can be adjusted within a certain time by utilizing the straight-going distance (the vehicles do not change lanes and stop at the intersections), the body feeling and rationality of the running of the vehicles are ensured to the greatest extent, and the transverse error is eliminated smoothly.
In one implementation, the adjusting the real-time positioning of the target vehicle in step S130 includes:
the lateral position in the set navigation track is used instead of the lateral position of the filter.
In the embodiment of the invention, the usable time length T is the driving time length of the target vehicle which does not change lanes and does not pass through an intersection for stopping.
The method for obtaining the usable time period T may include:
mapping the navigation track and the real-time positioning information to a pre-stored map;
calculating the straight distance of the target vehicle according to the map and the navigation track;
and calculating the usable time length T of the target vehicle according to the straight distance and the vehicle speed information.
In one implementation, adjusting the real-time positioning of the target vehicle further comprises:
limiting obstacle avoidance operation of the target vehicle within a usable time length T; and correcting the transverse position of the target vehicle according to the result of the visual lane line matching calculation, so as to ensure the positioning of the lane level.
In the embodiment of the invention, the pre-stored map adopts the high-precision map, the high-precision map provides map information with higher precision and richer content, the automatic driving can be served, the precision of the high-precision map can reach the centimeter level, and the high-precision map comprises information of elements such as street lamps, guardrails, traffic lights and the like besides information of roads, POIs (Point of interesting, points of interest such as shops, bars, gas stations, hospitals and stations) and the like. The road information can be provided with richer fine information of lanes and intersections.
In one implementation, the step of obtaining a pre-stored map includes:
establishing a characterization model suitable for computer representation and processing for objects in the road to describe geometric shape, position and texture information in the road;
and rendering objects in the road according to the characterization model to obtain a map of the road.
The map pre-stored in the embodiment of the invention is especially a high-precision map, and the obtained characterization model mainly comes from point cloud information acquired by a laser radar sensor; and a unique target or feature from the camera image acquisition.
In the embodiment of the invention, the straight distance of the target vehicle is determined from the pre-stored map, the straight distance refers to the distance of a road section which does not change lanes and stops at an intersection, the distance can be regarded as the longitudinal safe driving distance of the automatic driving vehicle, and the distance is suitable for safe and stable route adjustment. Calculating the usable time length T according to the straight distance and the vehicle speed information (except the case that the speed of a general vehicle is fixed and emergency obstacle avoidance or braking is needed in a tracking mode); the lateral movement of the target vehicle is gradually corrected during the period of time T when the vehicle is available. According to the embodiment of the invention, the current straight-going distance of the target vehicle is calculated according to the navigation track and the high-precision map, if the target vehicle is positioned on a straight-going road section, the straight-going distance is relatively large, but at certain inbound, outbound, crossing or turning positions, the straight-going distance is relatively small, so that the straight-going distance is the distance of the position with the furthest changeable transverse deviation. The method avoids abrupt or rapid adjustment of the route, ensures the comfort of passengers and drivers, and avoids uncomfortable feeling of the passengers and drivers caused by lateral swing of the vehicle.
In an embodiment of the present invention, the obstacle avoidance operation includes at least one of the following operations: active obstacle avoidance, overtaking operation and lane changing operation.
The embodiment of the invention can limit the dangerous operation of the vehicle in the time within the usable time length T, such as the operations of active obstacle avoidance, overtaking, lane changing and the like.
Based on the lateral deviation, correcting the lateral movement of the target vehicle according to the result of the visual lane line matching calculation includes:
calculating a corresponding correction factor of the target vehicle according to the transverse deviation and the usable time length T based on the yaw angle information of the target vehicle in the transverse motion control process;
and controlling the yaw angle of the target vehicle according to the correction factors, ensuring lane-level positioning of the target vehicle, and reducing the transverse deviation so that the target vehicle runs in the navigation track.
In the embodiment of the invention, the transverse deviation is corrected by generating the correction factor of the target vehicle in the transverse movement process, the transverse movement is controlled in a usable long T time period by considering the speed of the longitudinal movement in the steering process, so that a relatively stable deflection angle (yaw angle) is determined according to the yaw angle information in the transverse movement control process of the automatic driving vehicle of the corresponding model of the target vehicle, and therefore, the information such as the turning radius or the deflection angle is used as the correction factor, and the route of the target vehicle is adjusted according to the correction factor.
In one implementation, the method further comprises, after:
and periodically updating the usable time length T, and reducing the speed of the target vehicle and waiting for the recovery of an RTK signal when no other vehicle is in the preset range of the target vehicle or the front speed of the target vehicle is lower than a preset speed threshold value.
In one implementation, the method further comprises, after:
and according to the straight-going distance, when the target vehicle is determined not to change lanes within a preset time range and stops without passing through an intersection, restarting a positioning filter, and waiting for GNSS or RTK signals to recover.
In one implementation, the method further comprises:
and if the RTK signal is recovered, eliminating the deviation according to the deviation of the recovered RTK positioning information of the target vehicle and the real-time positioning information of the target vehicle, and taking the RTK positioning information as the position information of the target vehicle to carry out tracking running.
According to the embodiment of the invention, the positioning filter can be restarted under the condition that the road is not required to be changed and the road junction is not encountered to stop, and the problem that part of navigation cannot enter a differential state can be solved by restarting the positioning filter. In addition, since the speed of the vehicle varies with the road condition/other vehicle conditions, it is necessary to update the positioning information in real time, and when no other vehicles around the own vehicle are perceived or the speed of the preceding vehicle is slow, the speed can be reduced appropriately to improve the probability of recovering the GNSS or RTK signals. And after the signal is recovered, according to the position deviation between the recovered position and the virtual positioning, the vehicle positioning is converted from the virtual position to the real position, and the error is eliminated smoothly.
Embodiments of the present invention also provide a travel track-based automatic driving vehicle positioning adjustment device capable of performing the respective step processes of the travel track-based automatic driving vehicle positioning adjustment method as described above. Next, the above-described automatic driving vehicle positioning adjustment device based on the travel locus will be described with reference to fig. 4.
As shown in fig. 4, the automatic driving vehicle positioning adjustment device based on the driving track includes a positioning module 410, a comparing module 420, and an adjustment module 430.
The positioning module 410 is configured to obtain real-time positioning information of a tracking traveling target vehicle, and determine a lateral deviation between the real-time positioning information of the target vehicle and a navigation track according to the real-time positioning information, when the RTK is in a non-differential state and the laser or vision sensor cannot provide a reliable position;
a comparison module 420, configured to determine, based on a comparison between a pre-calibrated vehicle speed and a maximum allowable value of a vehicle lateral error, whether the lateral deviation exceeds the corresponding maximum allowable value of the error according to the vehicle speed information of the target vehicle and the lateral deviation;
an adjustment module 430 is configured to adjust the real-time positioning of the target vehicle during the long time period when the lateral deviation exceeds the corresponding maximum allowable error value.
The present embodiment also provides a computing device comprising a memory 1120, a processor 1110 and a computer program stored in said memory 1120 and executable by said processor 1110, which computer program is stored in a space 1130 for program code in the memory 1120, which computer program, when being executed by the processor 1110, implements a program 1131 for performing any of the method steps according to the invention.
Embodiments of the present application also provide a computer-readable storage medium. Referring to fig. 6, the computer-readable storage medium includes a storage unit for program code, the storage unit being provided with a program 1131' for performing the method steps according to the present invention, the program being executed by a processor.
Embodiments of the present application also provide a computer program product comprising instructions. The computer program product, when run on a computer, causes the computer to perform the method steps according to the invention.
The various techniques described herein may be implemented in connection with hardware or software or, alternatively, with a combination of both. Thus, the methods and apparatus of the present invention, or certain aspects or portions of the methods and apparatus of the present invention, may take the form of program code (i.e., instructions) embodied in tangible media, such as removable hard drives, U-drives, floppy diskettes, CD-ROMs, or any other machine-readable storage medium, wherein, when the program is loaded into and executed by a machine, such as a computer, the machine becomes an apparatus for practicing the invention.
In the case of program code execution on programmable computers, the electronic device will generally include a processor, a storage medium readable by the processor (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device. Wherein the memory is configured to store program code; the processor is configured to execute the object tracking processing method of the present invention in accordance with instructions in said program code stored in the memory.
By way of example, and not limitation, readable media comprise readable storage media and communication media. The readable storage medium stores information such as computer readable instructions, data structures, program modules, or other data. Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Combinations of any of the above are also included within the scope of readable media.
In the description provided herein, algorithms and displays are not inherently related to any particular computer, virtual system, or other apparatus. Various general-purpose systems may also be used with examples of the invention. The required structure for a construction of such a system is apparent from the description above. In addition, the present invention is not directed to any particular programming language. It should be appreciated that the teachings of the present invention as described herein may be implemented in a variety of programming languages and that the foregoing descriptions of specific languages are provided for disclosure of preferred embodiments of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Those skilled in the art will appreciate that the modules or units or components of the devices in the examples disclosed herein may be arranged in a device as described in this embodiment, or alternatively may be located in one or more devices different from the devices in this example. The modules in the foregoing examples may be combined into one module or may be further divided into a plurality of sub-modules.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. Furthermore, some of the embodiments are described herein as methods or combinations of method elements that may be implemented by a processor of a computer system or by other means of performing the functions. Thus, a processor with the necessary instructions for implementing the described method or method element forms a means for implementing the method or method element. Furthermore, the elements of the apparatus embodiments described herein are examples of the following apparatus: the apparatus is for carrying out the functions performed by the elements for carrying out the objects of the invention.
As used herein, unless otherwise specified the use of the ordinal terms "first," "second," "third," etc., to describe a general object merely denote different instances of like objects, and are not intended to imply that the objects so described must have a given order, either temporally, spatially, in ranking, or in any other manner.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of the above description, will appreciate that other embodiments are contemplated within the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter.
It will be apparent to those skilled in the art that various modifications and variations can be made in the present application without departing from the spirit or scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims and the equivalents thereof, the present application is intended to cover such modifications and variations.
Claims (9)
1. An automatic driving vehicle positioning adjustment method based on a driving track is characterized by comprising the following steps:
under the condition that the RTK is in a non-differential state and a laser or visual sensor cannot provide a reliable position, acquiring real-time positioning information of a target vehicle in tracking running, and determining the transverse deviation between the real-time positioning information of the target vehicle and a navigation track according to the real-time positioning information, wherein the method comprises the following steps: position information of a central point of a vehicle rear axle of the target vehicle, which is acquired by using the RTK, auxiliary vision or laser positioning technology; updating the position information of the center point by using a positioning filter to obtain real-time positioning information of the target vehicle; determining the distance between the real-time positioning information and a track point closest to the central point of the rear axle of the vehicle in the navigation track; taking the distance as the transverse deviation of the target vehicle and the navigation track;
determining whether the lateral deviation exceeds a corresponding error maximum allowable value according to the vehicle speed information of the target vehicle and the lateral deviation based on a comparison relation between a pre-calibrated vehicle speed and a vehicle lateral error;
and when the transverse deviation exceeds the corresponding maximum allowable error value, adjusting the real-time positioning of the target vehicle in a period of time T when the vehicle is available.
2. The method of claim 1, wherein adjusting the real-time positioning of the target vehicle comprises:
the lateral position in the set navigation track is used instead of the lateral position of the filter.
3. The method according to claim 1 or 2, wherein the usable time period T is a travel time period during which the target vehicle does not change lanes and does not stop through an intersection;
the step of obtaining the usable time length T includes:
mapping the navigation track and the real-time positioning information to a pre-stored map;
calculating the straight distance of the target vehicle according to the map and the navigation track;
and calculating the usable time length T of the target vehicle according to the straight distance and the vehicle speed information.
4. The method of claim 3, wherein adjusting the real-time positioning of the target vehicle further comprises:
limiting obstacle avoidance operation of the target vehicle within a usable time length T; and correcting the transverse position of the target vehicle according to the result of the visual lane line matching calculation, so as to ensure the positioning of the lane level.
5. The method of claim 4, wherein the obstacle avoidance operation comprises at least one of: active obstacle avoidance, overtaking operation and lane changing operation.
6. The method of claim 1, wherein the method is preceded by: calibrating the comparison relation between the vehicle speed and the vehicle transverse error, comprising:
and in the tracking mode, testing the vehicle vibration amplitude caused by the vehicle transverse error of the automatic driving vehicle with the same model as the target vehicle at different speeds, and determining the maximum allowable value of the transverse error at different speeds based on preset control parameters.
7. The method of claim 1, wherein the method further comprises:
and periodically updating the usable time length T, and reducing the speed of the target vehicle and waiting for the recovery of an RTK signal when no other vehicle is in the preset range of the target vehicle or the front speed of the target vehicle is lower than a preset speed threshold value.
8. The method of claim 7, wherein the method further comprises:
and if the RTK signal is recovered, eliminating the deviation according to the deviation of the recovered RTK positioning information of the target vehicle and the real-time positioning information of the target vehicle, and taking the RTK positioning information as the position information of the target vehicle to carry out tracking running.
9. An automatic driving vehicle positioning adjustment device based on a driving track, characterized by comprising:
the positioning module is used for acquiring real-time positioning information of a target vehicle in tracking running under the condition that the RTK is in a non-differential state and a laser or visual sensor cannot provide a reliable position, and determining the transverse deviation between the real-time positioning information of the target vehicle and a navigation track according to the real-time positioning information, and comprises the following steps: position information of a central point of a vehicle rear axle of the target vehicle, which is acquired by using the RTK, auxiliary vision or laser positioning technology; updating the position information of the center point by using a positioning filter to obtain real-time positioning information of the target vehicle; determining the distance between the real-time positioning information and a track point closest to the central point of the rear axle of the vehicle in the navigation track; taking the distance as the transverse deviation of the target vehicle and the navigation track;
the comparison module is used for determining whether the transverse deviation exceeds the corresponding maximum error allowable value according to the speed information of the target vehicle and the transverse deviation based on the comparison relation between the pre-calibrated speed and the maximum vehicle transverse error allowable value;
and the adjusting module is used for adjusting the real-time positioning of the target vehicle in a period of time T when the transverse deviation exceeds the corresponding maximum allowable error value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410051504.XA CN117572476B (en) | 2024-01-15 | 2024-01-15 | Automatic driving vehicle positioning adjustment method and device based on driving track |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410051504.XA CN117572476B (en) | 2024-01-15 | 2024-01-15 | Automatic driving vehicle positioning adjustment method and device based on driving track |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117572476A CN117572476A (en) | 2024-02-20 |
| CN117572476B true CN117572476B (en) | 2024-04-09 |
Family
ID=89888471
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410051504.XA Active CN117572476B (en) | 2024-01-15 | 2024-01-15 | Automatic driving vehicle positioning adjustment method and device based on driving track |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117572476B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004007232A1 (en) * | 2002-07-16 | 2004-01-22 | Daimler Chrysler Ag | Method for assisting a driver when performing driving maneuvers |
| CN110979305A (en) * | 2019-03-18 | 2020-04-10 | 长城汽车股份有限公司 | Vehicle abnormal lane change control method, device and system |
| CN113753080A (en) * | 2021-08-31 | 2021-12-07 | 的卢技术有限公司 | Self-adaptive parameter control method for transverse motion of automatic driving automobile |
| CN115127576A (en) * | 2022-09-02 | 2022-09-30 | 青岛慧拓智能机器有限公司 | Path planning method, device, chip, terminal, electronic equipment and storage medium |
| CN117240890A (en) * | 2023-08-17 | 2023-12-15 | 华能伊敏煤电有限责任公司 | Method and system for calibrating tracking driving steering median of unmanned mining truck |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8392064B2 (en) * | 2008-05-27 | 2013-03-05 | The Board Of Trustees Of The Leland Stanford Junior University | Systems, methods and devices for adaptive steering control of automotive vehicles |
-
2024
- 2024-01-15 CN CN202410051504.XA patent/CN117572476B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004007232A1 (en) * | 2002-07-16 | 2004-01-22 | Daimler Chrysler Ag | Method for assisting a driver when performing driving maneuvers |
| CN110979305A (en) * | 2019-03-18 | 2020-04-10 | 长城汽车股份有限公司 | Vehicle abnormal lane change control method, device and system |
| CN113753080A (en) * | 2021-08-31 | 2021-12-07 | 的卢技术有限公司 | Self-adaptive parameter control method for transverse motion of automatic driving automobile |
| CN115127576A (en) * | 2022-09-02 | 2022-09-30 | 青岛慧拓智能机器有限公司 | Path planning method, device, chip, terminal, electronic equipment and storage medium |
| CN117240890A (en) * | 2023-08-17 | 2023-12-15 | 华能伊敏煤电有限责任公司 | Method and system for calibrating tracking driving steering median of unmanned mining truck |
Non-Patent Citations (1)
| Title |
|---|
| 基于视觉复杂环境下车辆行驶轨迹预测方法;张润生;黄小云;刘晶;马雷;韩睿;赵玉勤;杨新红;;机械工程学报;20110120(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117572476A (en) | 2024-02-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109946732B (en) | Unmanned vehicle positioning method based on multi-sensor data fusion | |
| US11846522B2 (en) | Warning polygons for weather from vehicle sensor data | |
| US20200143671A1 (en) | Detection and estimation of variable speed signs | |
| CN105936294B (en) | The travel controlling system of vehicle | |
| EP2959268B1 (en) | Path curve confidence factors | |
| EP3678110A1 (en) | Method for correcting positional error and device for correcting positional error in driving assistance vehicle | |
| US20110046843A1 (en) | Systems and methods of vehicular path prediction for cooperative driving applications through digital map and dynamic vehicle model fusion | |
| US20100191461A1 (en) | System and method of lane path estimation using sensor fusion | |
| US8731769B2 (en) | Inertial sensor calibration method for vehicles and device therefor | |
| CN101201255A (en) | Vehicle combined navigation system based on intelligent navigation algorithm | |
| CN109696177B (en) | Device for compensating gyro sensing value, system having the same and method thereof | |
| JP6806891B2 (en) | Information processing equipment, control methods, programs and storage media | |
| KR102331312B1 (en) | 3D vehicular navigation system using vehicular internal sensor, camera, and GNSS terminal | |
| CN110967008A (en) | Automatic driving full scene positioning method for commercial vehicle | |
| US11726212B2 (en) | Detector for point cloud fusion | |
| EP4134627A1 (en) | Map information correction method, driving assistance method, and map information correction device | |
| US11579628B2 (en) | Method for localizing a vehicle | |
| CN113252022A (en) | Map data processing method and device | |
| US20200250864A1 (en) | Hazard warning polygons constrained based on end-use device | |
| CN117572476B (en) | Automatic driving vehicle positioning adjustment method and device based on driving track | |
| JP2019066444A (en) | Position calculation method, vehicle control method, and position calculation device | |
| US11392140B2 (en) | Two inertial measurement units and GPS based localization system for an autonomous driving truck | |
| Wisiol et al. | GNSS-based vehicle state determination tailored to cooperative driving and collision avoidance | |
| US20210188266A1 (en) | A camera-based low-cost lateral position calibration method for level-3 autonomous vehicles | |
| JP6413816B2 (en) | Random driving judgment device |
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 |