CN112415538A - Planning method and system for automatic driving vehicle to detour conical cylinder and vehicle - Google Patents
Planning method and system for automatic driving vehicle to detour conical cylinder and vehicle Download PDFInfo
- Publication number
- CN112415538A CN112415538A CN202011281129.6A CN202011281129A CN112415538A CN 112415538 A CN112415538 A CN 112415538A CN 202011281129 A CN202011281129 A CN 202011281129A CN 112415538 A CN112415538 A CN 112415538A
- Authority
- CN
- China
- Prior art keywords
- point
- cone
- conical
- point cloud
- vehicle
- 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.)
- Withdrawn
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
- G01S17/88—Lidar systems specially adapted for specific applications
- G01S17/93—Lidar systems specially adapted for specific applications for anti-collision purposes
- G01S17/931—Lidar systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- 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
- G01S7/00—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00
- G01S7/48—Details of systems according to groups G01S13/00, G01S15/00, G01S17/00 of systems according to group G01S17/00
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Human Computer Interaction (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Electromagnetism (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method and a system for planning a bypassing conical cylinder of an automatic driving vehicle and the vehicle, wherein the method comprises the following steps: step 1, obtaining point cloud information of a vehicle periodic environment scanned by a laser radar; step 2, clustering and screening out the central position of the cone-shaped cylinder according to the point cloud information obtained by scanning; step 3, fitting and generating a passable path according to the obtained central position of the conical cylinder, and pre-aiming to obtain a pre-aiming point for transverse control; and 4, receiving the preview point generated by the path to complete corresponding transverse control. The method can plan a path for the vehicle to automatically detour the conical cylinder by utilizing the scanning of the laser radar, and has high calculation efficiency.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to a planning method and system for a bypassing conical cylinder of an automatic driving vehicle, the vehicle and a storage medium.
Background
With the development of artificial intelligence technology, multi-sensor fusion technology and control decision technology, the demand for automatically driving automobiles is more and more strong. The automatic driving automobile can be classified into no grades from L1 to L5 according to the use scene, technical capability and the like of the automatic driving automobile. Where L2 is advanced driving assistance, L3 level is conditional autonomous driving, L4 level is full autonomous driving of a defined area, and L5 level is full autonomous driving.
The industry is currently focusing on mass production of automated driving technologies at the level L2-L3, which is primarily directed to limited automated driving capabilities in urban expressway and highway scenarios. The system comprises main functions of lane centering driving, vehicle self-adaptive cruising, automatic lane changing and the like.
In addition to conventional structured road scenes, a large number of road repair scenes are encountered in actual driving. In the scene, vehicles are required to accurately identify a conical cylinder area and automatically plan a barrier-detouring path so as to avoid road repairing sections. At present, a method based on camera vision and a method based on laser radar are mainly applied to conical barrel detection aiming at a road repairing scene. The method based on camera vision is strong in expansibility and detection capability, but has high requirements on related vision algorithms, needs a large amount of data to train various cone roadblocks, and is not high enough in robustness to backlight and dim light scenes.
Therefore, there is a need to develop a method, system, vehicle and storage medium for planning the detour of a cone of an autonomous vehicle.
Disclosure of Invention
The invention aims to provide a method and a system for planning a vehicle to bypass a conical cylinder by using an automatic driving vehicle, the vehicle and a storage medium, which can plan a path for the vehicle to bypass the conical cylinder automatically by using laser radar scanning and have high calculation efficiency.
The invention relates to a method for planning a bypassing conical cylinder of an automatic driving vehicle, which comprises the following steps of:
step 1, obtaining point cloud information of a vehicle periodic environment scanned by a laser radar;
step 2, clustering and screening out the central position of the cone-shaped cylinder according to the point cloud information obtained by scanning;
step 3, fitting and generating a passable path according to the obtained central position of the conical cylinder, and pre-aiming to obtain a pre-aiming point for transverse control;
and 4, receiving the preview point generated by the path to complete corresponding transverse control.
Further, the step 2 specifically includes:
step 2a, conical cylinder clustering: carrying out density clustering on the obtained point cloud data according to the density characteristics of the distribution of the point cloud data, and dividing the point cloud data after the density clustering to obtain a plurality of point cloud clusters with similar density distribution;
and 2b, screening the conical cylinder: and calculating the standard deviation of the point cloud cluster obtained by density clustering, screening the point cloud cluster of the cone-shaped cylinder according to the standard deviation characteristics of the point cloud of the cone-shaped cylinder, and calculating the central point of all the point clouds in the point cloud cluster to obtain the central position of the cone-shaped cylinder.
Further, the step 3 comprises:
step 3a, fitting a conical cylinder passing path: dividing a front area into a left part and a right part according to the coordinates of the vehicle by using the obtained central positions of a plurality of conical cylinders, respectively searching the matched conical cylinders on the left side and the right side, calculating the middle points of central connecting lines of the two conical cylinders after the matched conical cylinders are found, repeating the steps to find the middle points of a plurality of central connecting lines, and fitting based on the middle points to obtain a passable path, wherein y is f (x);
and 3b, generating a vehicle transverse control preview point: and according to the longitudinal pre-aiming distance of the vehicle, searching a corresponding transverse distance on the obtained passing path to generate a pre-aiming point for transverse control.
Further, the cone clustering is to perform DBSCAN clustering by using all the obtained point cloud coordinates, and specifically includes:
step 2a-1, extracting a point p which is not checked from the point cloud data, if the point is not processed, namely the point is not classified as a certain cluster or marked as noise, checking the neighborhood of the point p, if the number of objects is not less than the preset number, establishing a new cluster C, and adding the points into a candidate set N;
step 2a-2, checking the neighborhood of all the unprocessed objects q in the candidate set N, if at least a preset number of objects are contained, adding the objects into N, otherwise, adding the objects into noise, and if the q is not classified into any cluster, adding the q into C;
step 2a-3, repeating step 2a-2, and continuously checking the unprocessed objects in the N until the current candidate set N is empty;
step 2a-4, repeating the step 2a-1 to the step 2a-3 until all points are processed;
and 2a-5. the cluster obtained by the calculation is the point after being clustered.
Further, the conical drum screening specifically comprises:
step 2b-1, calculating the standard deviation of each cluster, setting a threshold value by using the calculated standard deviation, and screening out the point cloud cluster representing the cone;
and 2b-2. if the point cloud cluster of the cone-shaped cylinder exists, calculating a central point of all the point clouds in the cone-shaped cylinder, namely the central position of the cone-shaped cylinder, and if the point cloud cluster of the cone-shaped cylinder does not exist, finishing the calculation.
Further, the fitting of the cone-shaped tube passing path specifically comprises:
step 3a-1, taking the origin of the vehicle as a transverse position central point at the initial moment;
step 3a-2, dividing a front area into a left area and a right area according to a transverse position center point, traversing the longitudinal position of the center point of the conical cylinder from near to far, finding out left and right matched conical cylinders within a certain longitudinal threshold value, and calculating the middle point of a center connecting line of the two conical cylinders after finding out the matched conical cylinders; if only the left side or the right side of the conical cylinder exists, the conical cylinder is translated in the opposite direction according to a half of the default value of the road width to obtain a midpoint;
3a-3, repeating the step 3a-2 to obtain a midpoint to update the central point of the transverse position, and continuing to match until all conical cylinder points are traversed;
and 3a-4, fitting all the middle points obtained by matching to obtain a passable path, wherein y is f (x).
In a second aspect, the present invention provides a system for planning an autonomous vehicle to detour around a conical drum, comprising:
the laser radar is used for scanning point cloud information of a vehicle periodic environment;
a memory for storing a computer readable program;
a controller for receiving information from the lidar, the controller being coupled to the lidar and the memory, respectively, the computer readable program when invoked by the memory being operable to perform the steps of the method for planning a detour cone for an autonomous vehicle according to the invention.
In a third aspect, the invention provides a vehicle, which adopts the planning system for the automatic driving vehicle to detour the conical cylinder.
In a fourth aspect, the present invention provides a storage medium having a computer readable program stored therein, the computer readable program when invoked being capable of performing the steps of the method for planning for an autonomous vehicle to detour around a conical drum according to the present invention.
The invention has the following advantages:
(1) the path around which the conical cylinder bypasses is planned by using a laser radar, so that the method is reliable and mature;
(2) the laser radar with low cost and low scanning line number can be used, so that the cost is greatly reduced;
(3) the path planning method has high calculation efficiency and meets the performance requirement of vehicle-mounted calculation.
Drawings
Fig. 1 is a flowchart of the present embodiment.
Detailed Description
The invention will be further explained with reference to the drawings.
In this embodiment, a method for planning a detour conical cylinder of an autonomous vehicle includes the following steps:
step 1, obtaining point cloud information of a vehicle periodic environment scanned by a laser radar;
step 2, clustering and screening out the central position of the cone-shaped cylinder according to the point cloud information obtained by scanning;
step 3, fitting and generating a passable path according to the obtained central position of the conical cylinder, and pre-aiming to obtain a pre-aiming point for transverse control;
and 4, receiving the preview point generated by the path to complete corresponding transverse control.
As shown in fig. 1, the present embodiment is explained in detail as follows:
(A) point cloud information processing
And A1, judging whether the laser radar finishes scanning one frame and generating point cloud information. If yes, point cloud information obtained by scanning of the laser radar is obtained, and if not, the calculation is finished.
A2, restoring point cloud coordinates in a two-dimensional plane according to the distance and course angle information of each laser scanning point; wherein, the point cloud coordinate of the ith laser scanning point is (x)i,yi)：
xi＝distancei×sin(anglei)
yi＝distancei×cos(anglei)
Wherein distanceiIs the distance, angle, of the ith laser scanning spotiThe heading angle information of the ith laser scanning point is obtained.
(B) Cone-shaped cylinder clustering and screening
And B1, performing DBSCAN clustering by using all the obtained point cloud coordinates. The DBSCAN algorithm is a density-based clustering algorithm that accomplishes clustering by finding the largest set of density-connected points. The DBSCAN algorithm mainly comprises the following steps:
b1-1, extracting a point p which is not checked from the point cloud data, if the point is not processed (not classified as a certain cluster or marked as noise), checking the neighborhood, if the number of objects is not less than the preset number, establishing a new cluster C, and adding the points into a candidate set N;
b1-2, checking the neighborhood of all the unprocessed objects q in the candidate set N, and adding the objects to N if at least a preset number of objects are contained, otherwise, the objects are noise. If q does not belong to any cluster, adding it to C;
b1-3, repeating the step B1-2, and continuously checking the unprocessed objects in the N until the current candidate set N is empty;
b1-4. repeat step B1-1 to step B1-3 until all points have been processed.
B1-5. the cluster obtained by the above calculation is the point after being clustered.
And B2, calculating the standard deviation of each cluster, wherein the calculated standard deviation is small enough because the point cloud distribution of the cone is concentrated and the diffusion is very small. And setting a threshold value by using the standard deviation obtained by calculation so as to screen out the point cloud cluster representing the cone.
B3, if there is a cone point cloud cluster, finding the center point of all the point clouds in the cone point cloud cluster, namely the center position of the cone. If not, the calculation is ended.
C. Cone barrel traffic path fitting
C1, finding a left conical cylinder and a right conical cylinder which are matched by using the obtained central positions of the plurality of conical cylinders. The method mainly comprises the following steps:
c1-1, the initial time takes the origin of the vehicle as the center point of the transverse position.
C1-2, dividing the front area into left and right areas according to the transverse position center point. Traversing the longitudinal position of the center point of the conical cylinder from near to far, finding out the conical cylinders matched left and right within a certain longitudinal threshold, and calculating the midpoint of the central connecting line of the two conical cylinders after finding out the matched conical cylinders. If only the left or right tapered cylinders are available, the midpoint is obtained in the opposite direction according to half of the default value of the road width.
C1-3. repeat step C1-2 to update the lateral positional center point with the resulting midpoint, continuing the match until all cone points are traversed.
And C1-4, fitting all the middle points obtained by matching (such as direct fitting, piecewise fitting, curve fitting, straight line fitting and the like) to obtain a passable path, wherein y is f (x).
C2, generating transverse control preview point
According to the obtained communication path and the longitudinal distance needing to be previewed, a preview point position (hookah head lng, y) is obtained, wherein y is a transverse position, and the hookah head lng is the longitudinal preview distance. The preview point information is sent to a controller (in this embodiment, the controller is a vehicle transverse controller), and the vehicle transverse controller performs corresponding transverse control.
In this embodiment, a vehicle adopts the planning system for an autonomous vehicle to detour around a conical cylinder as described in this embodiment.
In this embodiment, a storage medium has a computer readable program stored therein, and the computer readable program when invoked can execute the steps of the method for planning a detour cone of an autonomous vehicle as described in this embodiment.
Claims (9)
1. A planning method for a conical cylinder bypassed by an automatic driving vehicle is characterized by comprising the following steps:
step 1, obtaining point cloud information of a vehicle periodic environment scanned by a laser radar;
step 2, clustering and screening out the central position of the cone-shaped cylinder according to the point cloud information obtained by scanning;
step 3, fitting and generating a passable path according to the obtained central position of the conical cylinder, and pre-aiming to obtain a pre-aiming point for transverse control;
and 4, receiving the preview point generated by the path to complete corresponding transverse control.
2. The method for planning the detour cone of the autonomous vehicle according to claim 1, wherein: the step 2 specifically comprises the following steps:
step 2a, conical cylinder clustering: carrying out density clustering on the obtained point cloud data according to the density characteristics of the distribution of the point cloud data, and dividing the point cloud data after the density clustering to obtain a plurality of point cloud clusters with similar density distribution;
and 2b, screening the conical cylinder: and calculating the standard deviation of the point cloud cluster obtained by density clustering, screening the point cloud cluster of the cone-shaped cylinder according to the standard deviation characteristics of the point cloud of the cone-shaped cylinder, and calculating the central point of all the point clouds in the point cloud cluster to obtain the central position of the cone-shaped cylinder.
3. The method for planning the detour cone of the autonomous vehicle according to claim 2, characterized in that: the step 3 comprises the following steps:
step 3a, fitting a conical cylinder passing path: dividing a front area into a left part and a right part according to the coordinates of the vehicle by using the obtained central positions of a plurality of conical cylinders, respectively searching the matched conical cylinders on the left side and the right side, calculating the middle points of central connecting lines of the two conical cylinders after the matched conical cylinders are found, repeating the steps to find the middle points of a plurality of central connecting lines, and fitting based on the middle points to obtain a passable path, wherein y is f (x);
and 3b, generating a vehicle transverse control preview point: and according to the longitudinal pre-aiming distance of the vehicle, searching a corresponding transverse distance on the obtained passing path to generate a pre-aiming point for transverse control.
4. The method for planning the detour cone of the autonomous vehicle according to claim 2 or 3, characterized in that: the cone clustering is to perform DBSCAN clustering by using all the obtained point cloud coordinates, and specifically comprises the following steps:
step 2a-1, extracting a point p which is not checked from the point cloud data, if the point is not processed, namely the point is not classified as a certain cluster or marked as noise, checking the neighborhood of the point p, if the number of objects is not less than the preset number, establishing a new cluster C, and adding the points into a candidate set N;
step 2a-2, checking the neighborhood of all the unprocessed objects q in the candidate set N, if at least a preset number of objects are contained, adding the objects into N, otherwise, adding the objects into noise, and if the q is not classified into any cluster, adding the q into C;
step 2a-3, repeating step 2a-2, and continuously checking the unprocessed objects in the N until the current candidate set N is empty;
step 2a-4, repeating the step 2a-1 to the step 2a-3 until all points are processed;
and 2a-5. the cluster obtained by the calculation is the point after being clustered.
5. The method for planning the detour cone of the autonomous vehicle according to claim 4, wherein: the screening of the conical cylinder comprises the following specific steps:
step 2b-1, calculating the standard deviation of each cluster, setting a threshold value by using the calculated standard deviation, and screening out the point cloud cluster representing the cone;
and 2b-2. if the point cloud cluster of the cone-shaped cylinder exists, calculating a central point of all the point clouds in the cone-shaped cylinder, namely the central position of the cone-shaped cylinder, and if the point cloud cluster of the cone-shaped cylinder does not exist, finishing the calculation.
6. The method for planning the detour cone of the autonomous vehicle according to claim 5, wherein: the fitting of the conical barrel passing path specifically comprises the following steps:
step 3a-1, taking the origin of the vehicle as a transverse position central point at the initial moment;
step 3a-2, dividing a front area into a left area and a right area according to a transverse position center point, traversing the longitudinal position of the center point of the conical cylinder from near to far, finding out left and right matched conical cylinders within a certain longitudinal threshold, and calculating the middle point of a center connecting line of the two conical cylinders after finding out the matched conical cylinders; if only the left side or the right side of the conical cylinder exists, the conical cylinder is translated in the opposite direction according to a half of the default value of the road width to obtain a midpoint;
3a-3, repeating the step 3a-2 to obtain a midpoint to update the central point of the transverse position, and continuing to match until all conical cylinder points are traversed;
and 3a-4, fitting all the middle points obtained by matching to obtain a passable path, wherein y is f (x).
7. A system for planning a detour cone for an autonomous vehicle, comprising:
the laser radar is used for scanning point cloud information of a vehicle periodic environment;
a memory for storing a computer readable program;
a controller for receiving information from the lidar, the controller being coupled to the lidar and the memory, respectively, the computer readable program when invoked by the memory being operable to perform the steps of the method of planning for an autonomous vehicle to detour a conical drum as claimed in any one of claims 1 to 6.
8. A vehicle, characterized in that: a planning system for bypassing a conical canister with an autonomous vehicle as recited in claim 7.
9. A storage medium having a computer-readable program stored therein, characterized in that: the computer readable program when invoked by a controller is capable of performing the steps of the method for planning for an autonomous vehicle to detour around a conical drum according to any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011281129.6A CN112415538A (en) | 2020-11-16 | 2020-11-16 | Planning method and system for automatic driving vehicle to detour conical cylinder and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011281129.6A CN112415538A (en) | 2020-11-16 | 2020-11-16 | Planning method and system for automatic driving vehicle to detour conical cylinder and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112415538A true CN112415538A (en) | 2021-02-26 |
Family
ID=74831308
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011281129.6A Withdrawn CN112415538A (en) | 2020-11-16 | 2020-11-16 | Planning method and system for automatic driving vehicle to detour conical cylinder and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112415538A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109386155A (en) * | 2018-09-20 | 2019-02-26 | 同济大学 | Nobody towards automated parking ground parks the alignment method of transfer robot |
| WO2019119350A1 (en) * | 2017-12-19 | 2019-06-27 | 深圳市海梁科技有限公司 | Obstacle recognition method and apparatus for unmanned vehicle, and terminal device |
| CN110488319A (en) * | 2019-08-22 | 2019-11-22 | 重庆长安汽车股份有限公司 | A kind of collision distance calculation method and system merged based on ultrasonic wave and camera |
| CN110780305A (en) * | 2019-10-18 | 2020-02-11 | 华南理工大学 | Track cone bucket detection and target point tracking method based on multi-line laser radar |
| US20200104612A1 (en) * | 2018-09-27 | 2020-04-02 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for detecting obstacle, electronic device, vehicle and storage medium |
-
2020
- 2020-11-16 CN CN202011281129.6A patent/CN112415538A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019119350A1 (en) * | 2017-12-19 | 2019-06-27 | 深圳市海梁科技有限公司 | Obstacle recognition method and apparatus for unmanned vehicle, and terminal device |
| CN109386155A (en) * | 2018-09-20 | 2019-02-26 | 同济大学 | Nobody towards automated parking ground parks the alignment method of transfer robot |
| US20200104612A1 (en) * | 2018-09-27 | 2020-04-02 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for detecting obstacle, electronic device, vehicle and storage medium |
| CN110488319A (en) * | 2019-08-22 | 2019-11-22 | 重庆长安汽车股份有限公司 | A kind of collision distance calculation method and system merged based on ultrasonic wave and camera |
| CN110780305A (en) * | 2019-10-18 | 2020-02-11 | 华南理工大学 | Track cone bucket detection and target point tracking method based on multi-line laser radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109186617B (en) | Method and system for automatically generating lane-level topological relation based on visual crowdsourcing data and memory | |
| CN110148144B (en) | Point cloud data segmentation method and device, storage medium and electronic device | |
| CN110045729B (en) | Automatic vehicle driving method and device | |
| KR102512207B1 (en) | Roadway line fitting method and system | |
| CN109760675B (en) | Method, device, storage medium and terminal equipment for predicting vehicle track | |
| CN111695546B (en) | Traffic signal lamp identification method and device for unmanned vehicle | |
| CN111656421B (en) | Vehicle image data generation device, travel track data generation system, section image data generation program, and storage medium | |
| CN110763246A (en) | Automatic driving vehicle path planning method and device, vehicle and storage medium | |
| CN114413881B (en) | Construction method, device and storage medium of high-precision vector map | |
| CN113916246A (en) | Unmanned obstacle avoidance path planning method and system | |
| US20210004011A1 (en) | Device and method for determining u-turn strategy of autonomous vehicle | |
| CN109579857B (en) | Method and equipment for updating map | |
| CN109635701B (en) | Lane passing attribute acquisition method, lane passing attribute acquisition device and computer readable storage medium | |
| CN113870246A (en) | Obstacle detection and identification method based on deep learning | |
| CN113432615A (en) | Detection method and system based on multi-sensor fusion drivable area and vehicle | |
| CN112415538A (en) | Planning method and system for automatic driving vehicle to detour conical cylinder and vehicle | |
| CN116125980A (en) | Unmanned truck driving method and device, electronic equipment and storage medium | |
| CN112785072B (en) | Route planning and model training method, device, equipment and storage medium | |
| CN114429622A (en) | Automatic vehicle driving method and device, vehicle and storage medium | |
| CN115082894A (en) | Distance detection method, vehicle high beam control method, device, medium and vehicle | |
| CN113386771A (en) | Road model generation method and equipment | |
| JP2011214961A (en) | Reference pattern information generating device, method, program and general vehicle position specifying device | |
| CN117115773B (en) | Stop line generation method, apparatus, electronic device, medium, and program product | |
| CN115236696B (en) | Method and device for determining obstacle, electronic equipment and storage medium | |
| CN118097606A (en) | Obstacle detection method and 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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210226 |