CN112683290A - Vehicle track planning method, electronic equipment and computer readable storage medium - Google Patents
Vehicle track planning method, electronic equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN112683290A CN112683290A CN202011588772.3A CN202011588772A CN112683290A CN 112683290 A CN112683290 A CN 112683290A CN 202011588772 A CN202011588772 A CN 202011588772A CN 112683290 A CN112683290 A CN 112683290A
- Authority
- CN
- China
- Prior art keywords
- node
- vehicle
- new
- nodes
- planning method
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000009499 grossing Methods 0.000 claims abstract description 7
- 238000012805 post-processing Methods 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 24
- 238000009966 trimming Methods 0.000 claims description 4
- 238000013138 pruning Methods 0.000 claims description 2
- 238000004422 calculation algorithm Methods 0.000 description 22
- 238000005070 sampling Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000004088 simulation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Abstract
The invention discloses a vehicle track planning method, electronic equipment and a computer-readable storage medium. The invention introduces the heuristic function, effectively reduces the path nodes and improves the running speed and quality; the geometric constraint of the vehicle body is considered, and the safety of the vehicle in a complex environment is ensured; and simplifying and smoothing the track by adopting a post-processing method to generate an executable track suitable for the vehicle characteristics.
Description
Technical Field
The invention belongs to the technical field of automatic driving, and particularly relates to a vehicle track planning method.
Background
Trajectory Planning (Trajectories Planning) mainly refers to Planning a trajectory as much as possible according to a planned path in consideration of an actual temporary or moving obstacle and in consideration of speed and dynamic constraints. The core of trajectory planning is to solve the problem of how to go for the vehicle. The inputs of the trajectory planning include a topological map, obstacles and predicted trajectories of the obstacles, states of traffic lights, and other information such as positioning navigation and vehicle states. The output of the trajectory plan is a trajectory that is a function of time to location, i.e., the vehicle is at a particular location at a particular time. The goal of trajectory planning is to calculate a safe, comfortable trajectory for the unmanned vehicle to perform a predetermined driving task.
A fast-spread random tree (RRT) algorithm is applied to trajectory planning. The RRT algorithm avoids the modeling of the space by performing collision detection on the sampling points in the state space, and can effectively solve the problem of path planning of high-dimensional space and complex constraint. The method is characterized in that a high-dimensional space can be quickly and effectively searched, the search is guided to a blank area through random sampling points of a state space, a planned path from a starting point to a target point is found, and the method is suitable for solving path planning in a complex environment and a dynamic environment.
The prior path planning technology has the following defects:
(1) the measurement function adopted by the RRT algorithm is a proximity rule, and the generated track is not optimal;
(1) because the sampling strategy adopts uniform sampling, the convergence speed of the algorithm is low, and a large amount of useless node calculation time is consumed;
(2) tracks generated by the RRT algorithm are all formed by connecting branch nodes and leaf nodes, are not smooth and cannot be executed by a vehicle; geometric constraints of the vehicle body are not taken into account, so that the vehicle may collide with an obstacle when located at the node.
Disclosure of Invention
In order to solve the technical problems mentioned in the background art, the invention provides a vehicle trajectory planning method, an electronic device and a computer-readable storage medium.
In order to achieve the technical purpose, the technical scheme of the invention is as follows:
a vehicle trajectory planning method based on heuristic search random tree comprises the following steps:
(1) establishing a geometric constraint condition of the vehicle body, and generating a new node of the track random tree by using the geometric constraint condition;
(2) introducing a heuristic cost function and determining a father node of the new node;
(3) and (3) carrying out post-processing on the track nodes obtained based on the steps (1) to (2), trimming the track nodes and smoothing the track.
Further, the specific process of step (1) is as follows:
(1a) simplifying the outline of the vehicle into a rectangular frame, and determining the area of the surrounding environment of the vehicle;
(1b) randomly generating a new node;
(1c) taking the new node in the step (1b) as the center of a circle and taking a half of the diagonal line of the rectangular frame in the step (1a) as a radius to make a circle;
(1d) judging whether the circle obtained in the step (1c) is intersected with the surrounding area of the vehicle; if the nodes are intersected, returning to the step (1b) to randomly generate new nodes again; and if the nodes are not intersected, taking the current new node as a branch node of the track random tree.
Further, in the step (2), firstly, a specific area is constructed, the specific area takes the new node as the center of a circle and takes the step value set manually as the radius, and a plurality of uneven nodes with the distance from the new node being less than the step value are distributed in the specific area; secondly, respectively calculating cost function values of all nodes in the specific area; and finally, selecting the node with the minimum cost function as a parent node of the new node.
Further, the cost function H is as follows:
H＝s+g+f
wherein (x)new,ynew) As coordinates of the new node, (x)qs,yqs) Is the coordinate of the start node, (x)qg,yqg) Is the coordinate of the target node, (x)i,yi) Is the coordinates of a certain node in a specific area.
Further, in step (3), the process of pruning the trace nodes is as follows:
generating an effective path node set TS from a starting point position to an end point position through the steps (1) and (2), sequentially connecting the effective path node set TS with a subsequent node in the set TS from a root node, judging whether a connecting line between a current node and a next node collides with an obstacle space, if so, judging whether the current node and the next node are respectively not intersected with the root node, if so, deleting the current node from the set TS, and so on until the connecting line between the next node and the root node collides with the obstacle space, and taking the current node as a new root node; the above process is repeated until the target node is connected.
Further, in step (3), trajectory smoothing is performed using a B-spline curve.
Further, the B spline curve adopts a quasi-uniform B spline curve.
An electronic device for vehicle trajectory planning comprises a processor and a memory, wherein the memory stores execution instructions of the processor, and the processor is configured to execute the execution instructions to realize the vehicle trajectory planning method.
A computer-readable storage medium stores a program, which is executed to implement the above-described vehicle trajectory planning method.
Adopt the beneficial effect that above-mentioned technical scheme brought:
(1) according to the invention, the heuristic function is introduced into a specific small-range adjustable area, a new cost function is established, path nodes are effectively reduced, and the running speed and quality are improved;
(2) according to the invention, the geometric constraint of the vehicle body is considered, and constraint conditions are established to screen new node positions to ensure the safety of the vehicle in a complex environment;
(3) the invention adopts a post-processing method to simplify and smooth the track and generate an executable track suitable for the vehicle characteristics.
Drawings
FIG. 1 is an overall process flow diagram of the present invention;
FIG. 2 is a schematic diagram of the geometric constraints of the present invention;
FIG. 3 is a diagram illustrating heuristic functions in accordance with the present invention;
FIG. 4 is a diagram of the effect of a conventional RRT algorithm;
FIG. 5 is an RRT algorithm effect graph considering geometric constraints of a vehicle body;
FIG. 6 is a simulation comparison graph of the RRT algorithm considering the geometric constraints of the vehicle body and the heuristic search random tree algorithm;
FIG. 7 is a graph of the post-processed effect of the heuristic search based random tree algorithm.
Detailed Description
The technical scheme of the invention is explained in detail in the following with the accompanying drawings.
The invention designs a vehicle track planning method based on heuristic search random tree, as shown in figure 1, the steps are as follows:
step 1, establishing a geometric constraint condition of the vehicle body, and generating a new node of the track random tree by using the geometric constraint condition.
According to the description of the basic principle of the RRT, the new node is obtained by extending a distance from the qnear node to the qrand node, but the new node generated by the method may cause the vehicle at the node to collide with the surrounding environment, so that a path which does not accord with the characteristics of the vehicle is planned. To ameliorate this deficiency, the present invention employs geometric constraints. As shown in fig. 2, the vehicle is simplified into a black rectangular frame, the black origin represents a new node, and the black area represents the surrounding environment, and the process is as follows:
1a, simplifying the outline of a vehicle into a rectangular frame, and determining the area of the surrounding environment of the vehicle;
1b, randomly generating a new node;
1c, taking the new node in the step 1b as a circle center, and taking a half of a diagonal line of the rectangular frame in the step 1a as a radius to make a circle;
1d, judging whether the circle obtained in the step 1c is intersected with the surrounding area of the vehicle or not; if the nodes are intersected, returning to the step 1b to randomly generate new nodes again; and if the nodes are not intersected, taking the current new node as a branch node of the track random tree.
And 2, introducing a heuristic cost function and determining a father node of the new node.
The traditional RRT algorithm is characterized in that a node which is the shortest from a random sampling node qrand is searched to serve as qnear, and then a new node is connected with the qnear node. However, as the algorithm is slow to converge and does not meet the real-time requirement of the vehicle, the invention redesigns the measurement mode, introduces the heuristic function concept, screens the nodes connected with the new nodes by calculating the cost function of each node in a specific area, and effectively verifies the feasibility and the correctness of the new measurement function in the experiment. In order to better reveal the logic and the principle of the new metric function, the principle of the new metric method is described in the form of a tree branch node diagram, and as shown in fig. 3, the tree branch nodes and the connecting lines between them can be clearly seen. Firstly, constructing a specific area, wherein the specific area takes a new node as a circle center and an artificially set step value as a radius, and a plurality of nodes which are uneven and have a distance with the new node smaller than the step value are distributed in the specific area; secondly, respectively calculating cost function values of all nodes in the specific area; and finally, selecting the node with the minimum cost function as a parent node of the new node. The cost function is as follows:
H＝s+g+f
wherein (x)new,ynew) As coordinates of the new node, (x)qs,yqs) Is the coordinate of the start node, (x)qg,yqg) Is the coordinate of the target node, (x)i,yi) Is the coordinates of a certain node in a specific area.
Compared with the traditional RRT algorithm, the method has the advantages that the improved measurement mode is more convergent as the node with the minimum distance to the new node is used as the father node, and the advantages of the method are well integrated into the basic RRT algorithm by using the characteristic of high convergence speed of the heuristic function, so that the new node is more greedy when the father node is selected.
And 3, post-processing the track nodes obtained based on the step 1-2, trimming the track nodes and smoothing the track.
Because the basic RRT path planning algorithm adopts a uniform random sampling strategy and the path is composed of a plurality of nodes, the generated track is unsmooth, jittered and has sharp included angles. Particularly, in a complex environment with a large number of irregular obstacles, the RRT generates a plurality of turning points and useless nodes. For a vehicle that is not fully constrained, it is difficult to track this path and the service life of the vehicle is greatly reduced and the safety of the vehicle is reduced. Therefore, the invention provides an efficient post-processing method aiming at the situation, thereby meeting the vehicle motion constraint and utilizing the advantages of the RRT algorithm.
And (3) trimming track nodes:
generating an effective path node set TS from a starting point position to an end point position through the step 1-2, sequentially connecting with subsequent nodes in the set TS from a root node, judging whether a connecting line between a current node and a next node collides with an obstacle space, if so, judging whether the current node and the next node do not intersect with the root node respectively, if so, deleting the current node from the set TS, and so on until the connecting line between the next node and the root node collides with the obstacle space, and taking the current node as a new root node; the above process is repeated until the target node is connected.
Bezier smoothing function:
the Bezier curve (B-spline curve) has the advantages of flexibility, continuity, straight line retentivity and the like. B-spline curves are of many types, including uniform B-splines, quasi-uniform B-splines, segmented bezier curves, and non-uniform B-splines. Because the quasi-uniform B-spline curve passes through the end points, the invention utilizes the quasi-uniform B-spline curve to fit the trimmed path nodes to generate an executable track conforming to the vehicle motion constraint.
The invention also intends to protect the electronic equipment for vehicle trajectory planning, which comprises a processor and a memory, wherein the memory stores execution instructions of the processor, and the processor is configured to execute the execution instructions to realize the vehicle trajectory planning method.
The invention is also intended to protect a computer-readable storage medium for storing a program, which is executed to implement the above vehicle trajectory planning method.
In order to verify the feasibility of the invention, the traditional RRT (fast extended search random tree) and the effect graph of the invention are compared. As shown in fig. 4, the dashed-line frame represents the size of the vehicle, the black area represents the surroundings of the vehicle, and the black solid line represents the trajectory. It is obvious that when the vehicle travels along the route planned by the basic RRT algorithm, the vehicle collides with the surrounding environment due to the geometric characteristics of the vehicle body and the route is not smooth. The black arrows in fig. 4 are path nodes where the vehicle collides with the surroundings.
From the perspective of vehicle safety, the RRT algorithm considering the geometric constraint condition of the vehicle body better satisfies the vehicle motion constraint requirement and the vehicle safety requirement, as shown in fig. 5.
Under the condition of considering the geometric constraint of the vehicle body, the improved RRT (with the constraint condition of the vehicle body added) and the heuristic search random tree algorithm (the step value of the specific area in FIG. 6 is set as 150) are respectively compared in a simulation experiment. As shown in fig. 6, the black dashed line trace is the result planned by the improved RRT algorithm, and the black solid line trace is generated by the heuristic search random tree algorithm. Although the dashed line trajectory and the solid line trajectory do not collide with the surrounding environment, it is obvious that the path length of the dashed line trajectory is much longer than that of the solid line trajectory, and the dashed line trajectory has a plurality of sharp path nodes. Since heuristic function is introduced to heuristic search random tree, it is obviously better than RRT algorithm only considering shortest distance when selecting nodes. It is for this reason that heuristic search of the random tree generated trajectories is preferred over RRT.
As shown in FIG. 7, the dashed black line is the trace generated by the heuristic search of the random tree; the combined motion trajectories of the solid black lines and the arcs are post-processed on the basis of heuristic search of the random tree. As is apparent from fig. 7, the trajectory after the post-processing method is smoother and the path distance is shortened.
The embodiments are only for illustrating the technical idea of the present invention, and the technical idea of the present invention is not limited thereto, and any modifications made on the basis of the technical scheme according to the technical idea of the present invention fall within the scope of the present invention.
Claims (9)
1. A vehicle track planning method based on heuristic search random tree is characterized by comprising the following steps:
(1) establishing a geometric constraint condition of the vehicle body, and generating a new node of the track random tree by using the geometric constraint condition;
(2) introducing a heuristic cost function and determining a father node of the new node;
(3) and (3) carrying out post-processing on the track nodes obtained based on the steps (1) to (2), trimming the track nodes and smoothing the track.
2. The heuristic search random tree-based vehicle trajectory planning method of claim 1, wherein the specific process of step (1) is as follows:
(1a) simplifying the outline of the vehicle into a rectangular frame, and determining the area of the surrounding environment of the vehicle;
(1b) randomly generating a new node;
(1c) taking the new node in the step (1b) as the center of a circle and taking a half of the diagonal line of the rectangular frame in the step (1a) as a radius to make a circle;
(1d) judging whether the circle obtained in the step (1c) is intersected with the surrounding area of the vehicle; if the nodes are intersected, returning to the step (1b) to randomly generate new nodes again; and if the nodes are not intersected, taking the current new node as a branch node of the track random tree.
3. The vehicle trajectory planning method based on heuristic search random tree of claim 1, wherein in step (2), first, a specific area is constructed, the specific area uses the new node as a center of a circle and uses an artificially set step value as a radius, and a plurality of nodes which are not uniform and have a distance to the new node smaller than the step value are distributed in the specific area; secondly, respectively calculating cost function values of all nodes in the specific area; and finally, selecting the node with the minimum cost function as a parent node of the new node.
4. The heuristic search random tree-based vehicle trajectory planning method of claim 3, wherein the cost function H is as follows:
H＝s+g+f
wherein (x)new,ynew) As coordinates of the new node, (x)qs,yqs) Is the coordinate of the start node, (x)qg,yqg) Is the coordinate of the target node, (x)i,yi) Is the coordinates of a certain node in a specific area.
5. The heuristic search random tree-based vehicle trajectory planning method of claim 1, wherein in step (3), the process of pruning trajectory nodes is as follows:
generating an effective path node set TS from a starting point position to an end point position through the steps (1) and (2), sequentially connecting the effective path node set TS with a subsequent node in the set TS from a root node, judging whether a connecting line between a current node and a next node collides with an obstacle space, if so, judging whether the current node and the next node are respectively not intersected with the root node, if so, deleting the current node from the set TS, and so on until the connecting line between the next node and the root node collides with the obstacle space, and taking the current node as a new root node; the above process is repeated until the target node is connected.
6. The heuristic search stochastic tree-based vehicle trajectory planning method of claim 1, wherein in step (3), trajectory smoothing is performed using a B-spline curve.
7. The heuristic search stochastic tree-based vehicle trajectory planning method of claim 6, wherein the B-spline curve is a quasi-uniform B-spline curve.
8. An electronic device for vehicle trajectory planning, comprising a processor and a memory, wherein the memory stores execution instructions of the processor, and the processor is configured to execute the execution instructions to implement the vehicle trajectory planning method according to any one of claims 1 to 7.
9. A computer-readable storage medium storing a program, wherein the program is executed to implement the vehicle trajectory planning method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011588772.3A CN112683290A (en) | 2020-12-29 | 2020-12-29 | Vehicle track planning method, electronic equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011588772.3A CN112683290A (en) | 2020-12-29 | 2020-12-29 | Vehicle track planning method, electronic equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112683290A true CN112683290A (en) | 2021-04-20 |
Family
ID=75454748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011588772.3A Pending CN112683290A (en) | 2020-12-29 | 2020-12-29 | Vehicle track planning method, electronic equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112683290A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113483775A (en) * | 2021-06-30 | 2021-10-08 | 上海商汤临港智能科技有限公司 | Path prediction method and device, electronic equipment and computer readable storage medium |
| CN113534844A (en) * | 2021-08-18 | 2021-10-22 | 广东电网有限责任公司 | Method and device for inspecting transmission line of rotor aircraft in unknown environment |
| CN114185352A (en) * | 2021-12-08 | 2022-03-15 | 东风悦享科技有限公司 | High-precision high-real-time automatic driving local path planning method |
| CN114935928A (en) * | 2021-11-02 | 2022-08-23 | 哈尔滨工程大学 | Method, system and device for planning paths of ship personnel in fire environment by using improved RRT (remote tracking transform) algorithm based on sampling path optimization |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103676944A (en) * | 2013-12-11 | 2014-03-26 | 北京理工大学 | Unmanned aerial vehicle route planning method based on Dubins route and sparse A* searching |
| CN104590259A (en) * | 2015-01-07 | 2015-05-06 | 福州华鹰重工机械有限公司 | Track searching method and system |
| CN108469827A (en) * | 2018-05-16 | 2018-08-31 | 江苏华章物流科技股份有限公司 | A kind of automatic guided vehicle global path planning method suitable for logistic storage system |
| CN110032187A (en) * | 2019-04-09 | 2019-07-19 | 清华大学 | Unmanned motor static-obstacle obstacle-avoiding route planning calculation method |
| CN110849385A (en) * | 2019-11-28 | 2020-02-28 | 的卢技术有限公司 | Trajectory planning method and system for searching conjugate gradient descent based on double-layer heuristic search |
| CN111152214A (en) * | 2019-12-13 | 2020-05-15 | 珠海格力电器股份有限公司 | Four-degree-of-freedom palletizing robot, control system and palletizing path planning method |
| CN111487959A (en) * | 2019-01-28 | 2020-08-04 | 通用汽车环球科技运作有限责任公司 | Autonomous vehicle movement planning system and method |
| CN111897341A (en) * | 2020-08-05 | 2020-11-06 | 三一专用汽车有限责任公司 | Parking path planning method, parking path planning device and computer-readable storage medium |
-
2020
- 2020-12-29 CN CN202011588772.3A patent/CN112683290A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103676944A (en) * | 2013-12-11 | 2014-03-26 | 北京理工大学 | Unmanned aerial vehicle route planning method based on Dubins route and sparse A* searching |
| CN104590259A (en) * | 2015-01-07 | 2015-05-06 | 福州华鹰重工机械有限公司 | Track searching method and system |
| CN108469827A (en) * | 2018-05-16 | 2018-08-31 | 江苏华章物流科技股份有限公司 | A kind of automatic guided vehicle global path planning method suitable for logistic storage system |
| CN111487959A (en) * | 2019-01-28 | 2020-08-04 | 通用汽车环球科技运作有限责任公司 | Autonomous vehicle movement planning system and method |
| CN110032187A (en) * | 2019-04-09 | 2019-07-19 | 清华大学 | Unmanned motor static-obstacle obstacle-avoiding route planning calculation method |
| CN110849385A (en) * | 2019-11-28 | 2020-02-28 | 的卢技术有限公司 | Trajectory planning method and system for searching conjugate gradient descent based on double-layer heuristic search |
| CN111152214A (en) * | 2019-12-13 | 2020-05-15 | 珠海格力电器股份有限公司 | Four-degree-of-freedom palletizing robot, control system and palletizing path planning method |
| CN111897341A (en) * | 2020-08-05 | 2020-11-06 | 三一专用汽车有限责任公司 | Parking path planning method, parking path planning device and computer-readable storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 康亮;赵春霞;郭剑辉;: "未知环境下改进的基于RRT算法的移动机器人路径规划", 模式识别与人工智能, no. 03, 15 June 2009 (2009-06-15) * |
| 王铭枫;李云伍;徐俊杰;刘得雄;: "基于A算法的丘陵山区田间路网路径规划", 江苏农业科学, no. 07, 7 May 2019 (2019-05-07) * |
| 郭洪月等: "自动泊车系统中AGV路径规划及碰撞规避问题分析", 装备制造技术, no. 04, 30 April 2020 (2020-04-30), pages 258 - 267 * |
| 齐尧;徐友春;李华;王任栋;: "一种基于改进混合A~*的智能车路径规划算法", 军事交通学院学报, no. 08, 25 August 2018 (2018-08-25) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113483775A (en) * | 2021-06-30 | 2021-10-08 | 上海商汤临港智能科技有限公司 | Path prediction method and device, electronic equipment and computer readable storage medium |
| CN113534844A (en) * | 2021-08-18 | 2021-10-22 | 广东电网有限责任公司 | Method and device for inspecting transmission line of rotor aircraft in unknown environment |
| CN113534844B (en) * | 2021-08-18 | 2024-02-27 | 广东电网有限责任公司 | Method and device for inspecting transmission line of rotorcraft in unknown environment |
| CN114935928A (en) * | 2021-11-02 | 2022-08-23 | 哈尔滨工程大学 | Method, system and device for planning paths of ship personnel in fire environment by using improved RRT (remote tracking transform) algorithm based on sampling path optimization |
| CN114185352A (en) * | 2021-12-08 | 2022-03-15 | 东风悦享科技有限公司 | High-precision high-real-time automatic driving local path planning method |
| CN114185352B (en) * | 2021-12-08 | 2024-01-19 | 东风悦享科技有限公司 | High-precision high-real-time automatic driving local path planning method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112683290A (en) | Vehicle track planning method, electronic equipment and computer readable storage medium | |
| CN108151751B (en) | Path planning method and device based on combination of high-precision map and traditional map | |
| CN113219998B (en) | Improved bidirectional-RRT-based vehicle path planning method | |
| CN110954122B (en) | Automatic driving track generation method under high-speed scene | |
| CN109540159B (en) | Rapid and complete automatic driving track planning method | |
| CN108762270B (en) | Improved path planning algorithm for variable probability bidirectional fast search random tree | |
| CN110231824B (en) | Intelligent agent path planning method based on straight line deviation method | |
| CN107168305A (en) | Unmanned vehicle method for planning track based on Bezier and VFH under the scene of crossing | |
| CN108444490B (en) | Robot path planning method based on depth fusion of visible view and A-x algorithm | |
| CN112650229A (en) | Mobile robot path planning method based on improved ant colony algorithm | |
| WO2023103692A1 (en) | Decision planning method for autonomous driving, electronic device, and computer storage medium | |
| Zhang et al. | Hybrid A-based Curvature Continuous Path Planning in Complex Dynamic Environments | |
| CN112061116A (en) | Parking strategy of reinforcement learning method based on potential energy field function approximation | |
| CN114323051B (en) | Intersection driving track planning method and device and electronic equipment | |
| CN113359721B (en) | Improved A-based AGV path planning method combined with motion control | |
| CN113701777B (en) | High-precision map lane associated trajectory line automatic generation method based on space vector | |
| CN110954124A (en) | Adaptive path planning method and system based on A-PSO algorithm | |
| CN114545921A (en) | Unmanned vehicle path planning algorithm based on improved RRT algorithm | |
| CN117007066A (en) | Unmanned trajectory planning method integrated by multiple planning algorithms and related device | |
| CN116698066A (en) | Robot path planning method and system based on neighborhood expansion and boundary point improvement A-star algorithm | |
| CN110849385A (en) | Trajectory planning method and system for searching conjugate gradient descent based on double-layer heuristic search | |
| Li et al. | Trajectory planning for autonomous ground vehicles driving in structured environments | |
| Tang et al. | A reference path guided rrt* method for the local path planning of UGVS | |
| CN116276955A (en) | Drilling and anchoring robot drill boom track planning method, system and electronic equipment | |
| CN110887503B (en) | Moving track simulation method, device, equipment and 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 |