CN116793377A - Path planning method for fixed scene - Google Patents
Path planning method for fixed scene Download PDFInfo
- Publication number
- CN116793377A CN116793377A CN202310562661.2A CN202310562661A CN116793377A CN 116793377 A CN116793377 A CN 116793377A CN 202310562661 A CN202310562661 A CN 202310562661A CN 116793377 A CN116793377 A CN 116793377A
- Authority
- CN
- China
- Prior art keywords
- path
- distance
- risk
- algorithm
- curve
- 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 51
- 238000009499 grossing Methods 0.000 claims abstract description 7
- 230000001105 regulatory effect Effects 0.000 claims abstract description 5
- 238000010845 search algorithm Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 230000000903 blocking effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3446—Details of route searching algorithms, e.g. Dijkstra, A*, arc-flags, using precalculated routes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
A path planning method for a fixed scene, comprising: acquiring a map of a fixed scene, constructing a KD tree based on obstacles in the map, and planning a moving path of a moving object through a path searching algorithm; calculating the shortest distance between the current path node and the obstacle based on the KD tree, marking the shortest distance as a risk distance, and judging the risk degree of the moving object according to the risk distance; expanding path nodes according to the risk degree of the mobile object; when the method is extended to a path node capable of directly utilizing the RS curve to connect with the terminal point, the angle information of the path node is regulated; and smoothing the RS curve. The invention provides a path planning method for a fixed scene, which adjusts a hybrid A-algorithm based on the distance between a moving object and an obstacle, improves the path planning efficiency, and simultaneously improves the quality of the planned moving path.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a path planning method for a fixed scene.
Background
Along with the gradual maturity of the automatic driving technology, the application scene of automatic driving is also more and more wide, wherein the application scene comprises grain depot factories, airports, code heads and the like. Under the closed factory, the shape of the obstacle such as a warehouse is generally in a regular rectangle, and the passable road network does not have road conditions such as a rotary island. Moreover, the work of the intelligent logistics vehicles under the closed factory generally has the condition of multi-vehicle cooperation, so that the path specification coordination of the intelligent logistics vehicles is more needed in the global path planning algorithm of the multi-intelligent mobile platform, and the unordered random intersection among the global paths is avoided. The automatic driving technology is cited in the scene, and the method has great significance in realizing standardized management of vehicle driving, reducing the running confusion of a vehicle team, reducing the occurrence of blocking, improving the working efficiency of a factory, reducing the workload of personnel and improving the intelligent degree of the factory. At present, most intelligent logistics vehicles use an A-algorithm to carry out path planning, and the planned path has the problems that the kinematics of the vehicle is not satisfied, the path clings to obstacles, the direction of the vehicle is not considered by the path, and the like.
The hybrid a algorithm is proposed by Dmitri Dolgov, sebastian Thrun, michael Montemerlo et al of stanfu in 2010 and is used for solving the problem of path planning in the process of lateral parking and reversing and warehousing, and meanwhile, the hybrid a is a combination of the a algorithm and vehicle kinematics and is used for solving the problem that the a algorithm does not meet the vehicle kinematics. Compared with the A-algorithm, the mixed A-algorithm meets the vehicle kinematics and increases the head orientation, the steering cost and the reversing cost, so that the path generated by the mixed A-algorithm accords with the vehicle running requirement more than the path generated by the A-algorithm. The current hybrid a-algorithm is often used for global path planning in automatic driving technology, and comprises the following steps: (1) Acquiring a starting point position and a starting point direction of a vehicle and setting an ending point position and an ending point direction; (2) calculating and selecting the minimum cost node as the parent node; (3) connecting the parent node and the end point using an RS curve; (4) If there is no obstacle on the curve, the parent node and the destination point are connected by using the RS curve, and if there is an obstacle on the curve, the search is continued by returning to (2). The path generated by the mixed A-type algorithm accords with the kinematics of the vehicle, but the safety and the stability of the running of the vehicle are not considered, so the current mixed A-type algorithm also has the following problems that (1) the distance between a current node and an obstacle is not considered in a cost function of the mixed A-type algorithm, and the distance between part of the path and the obstacle is too close; (2) The mixed A algorithm uses fixed curvature and step length to expand searching, and can lead to frequent steering of vehicles in an open area and overlong searching time when the algorithm is applied to a large map; (3) The hybrid a algorithm uses a RS curve of fixed curvature in generating the RS curve, resulting in the generated RS curve being unfavorable for vehicle travel. When a plurality of intelligent mobile platforms plan a global path by using a mixed A-algorithm, the intelligent mobile platforms randomly cross each other in an unordered way, so that the running confusion of a vehicle team, the collision risk and the blocking probability are increased.
For example, chinese patent CN113359757a discloses an improved hybrid a-algorithm unmanned vehicle path planning and trajectory tracking method, which mainly improves the local path planning of the unmanned vehicle, uses an adaptive model prediction algorithm to track, and sets an error threshold for a period of time, so that the trajectory error is limited within a fixed range, and the error of the trajectory tracking is reduced. However, the global path planning of this patent does not take into account the distance of the path from the obstacle, the varying search steps and curvatures, and the rules for keeping the vehicle's path parallel to the road.
In addition, chinese patent document CN112606830a discloses a two-stage autonomous parking path planning method based on a hybrid a-algorithm, which divides a parking path into two stages, a first stage being a path from a vehicle entering a parking lot to a vehicle traveling to a minimum parking distance point, and a second stage being a path from the minimum parking distance point to a parking end point. And by combining the characteristics of the two paths, the two paths are respectively planned by adopting different heuristic functions, so that the path planning efficiency is improved. But the invention does not consider the distance to the obstacle in the first path searching process; the invention does not take into account the varying search step size and curvature during the second-stage search.
Disclosure of Invention
In order to solve the defects in the prior art, the invention provides a path planning method for a fixed scene, which adjusts a hybrid A algorithm based on the distance between a moving object and an obstacle, improves the path planning efficiency, and simultaneously improves the quality of the planned moving path.
In order to achieve the above purpose, the invention adopts the following specific scheme: a path planning method for a fixed scene, comprising:
acquiring a map of a fixed scene, constructing a KD tree based on obstacles in the map, and planning a moving path of a moving object through a path searching algorithm;
calculating the shortest distance between the current path node and the obstacle based on the KD tree, marking the shortest distance as a risk distance, and judging the risk degree of the moving object according to the risk distance;
expanding path nodes according to the risk degree of the mobile object;
when the method is extended to a path node capable of directly utilizing the RS curve to connect with the terminal point, the angle information of the path node is regulated; and smoothing the RS curve.
As a further optimization of the path planning method for a fixed scenario described above: the path searching algorithm adopts a mixed A-type algorithm;
after the risk distance is calculated, the risk distance is added to the cost function of the hybrid a-algorithm.
As a further optimization of the path planning method for a fixed scenario described above: when judging the risk degree of the mobile object according to the risk distance, determining a plurality of expansion areas with different areas based on the maximum self-size data of the mobile object, wherein the different expansion areas correspond to different risk degrees, and determining the risk degree of the mobile object based on the fitting relation between the risk distance and the expansion areas.
As a further optimization of the path planning method for a fixed scenario described above: when the risk degree reaches a first limit, the step length of the mixed A-algorithm is adjusted to a preset minimum value, the curvature is adjusted to a preset maximum value, and when the risk degree reaches a second limit, the step length and the curvature of the mixed A-algorithm are dynamically adjusted based on the risk distance.
As a further optimization of the path planning method for a fixed scenario described above: the method for dynamically adjusting the step length of the mixed A-algorithm based on the risk distance comprises the following steps:
wherein D (x) is a risk distance, max_l and min_l respectively represent a preset maximum step length and a preset minimum step length, and epsilon is the maximum self-size data of the moving object;
the method for dynamically adjusting the curvature of the hybrid a-algorithm based on the risk distance comprises the following steps:
wherein max_c and min_c represent preset maximum and minimum curvatures, respectively.
As a further optimization of the path planning method for a fixed scenario described above: when extending to a path node capable of directly connecting with an end point by using an RS curve, angle information of the path node is regulated toIs an integer multiple of (a).
As a further optimization of the path planning method for a fixed scenario described above: the method for smoothing the RS curve comprises the following steps:
determining a path node with an angle jump as an angle jump point;
calculating the shortest distance between the angle jump point and the obstacle and marking the shortest distance as a correction distance;
calculating length correction data and curvature correction data of the RS curve based on the correction distance;
and correcting the RS curve according to the length correction data and the curvature correction data.
As a further optimization of the path planning method for a fixed scenario described above: the method for determining the angle jump point comprises the following steps:
traversing the angle of each path node on the moving path;
calculating a difference between the angle of the path node and the angle of the previous path node;
and when the difference value is larger than a preset threshold value, determining that the angle of the path node jumps, and marking the path node as an angle jump point.
The beneficial effects are that: the invention can accelerate the searching speed by changing the searching step length of the mixed A algorithm, and realize the large-step-length small-curvature expansion in the open area and the short-step-length large-curvature expansion in the narrow area, thereby avoiding frequent steering of a moving object and improving the efficiency of path planning; the generated moving path is kept at a certain distance from the obstacle by adding the distance constraint with the obstacle, so that the safety of the moving object is improved; by optimizing the generation of the RS curve in the mixed A algorithm and correcting the RS curve, the generated path is kept parallel to the road network of the fixed scene as much as possible, so that the quality of the path is improved, and the safety and stability of the moving object are further improved. The invention can be applied to automatic driving of vehicles in fixed scenes such as grain depots, factories, airports and wharfs, provides a safe, stable and highly-executable path for the automatic driving vehicles, improves the driving stability of the automatic driving vehicles, greatly reduces the occurrence of dangerous situations in the driving process and improves the working efficiency of the vehicles.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a schematic diagram of a distribution of extended regions;
FIG. 3 is a schematic diagram showing the effect of smoothing the RS curve;
fig. 4 is a graph comparing the method of the present invention with a prior art hybrid a algorithm.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a path planning method for a fixed scene includes the following steps.
First, a map of a fixed scene is acquired, a KD-tree is constructed based on obstacles in the map, and a moving path of a moving object is planned by a path search algorithm. In this embodiment, the path search algorithm employs a hybrid a algorithm.
And secondly, calculating the shortest distance between the current path node and the obstacle based on the KD tree, marking the shortest distance as a risk distance, and judging the risk degree of the moving object according to the risk distance. Specifically, the shortest distance between the current search node and the obstacle KD tree is calculated by using a kdtree () function, which belongs to the prior art in the field and is not described herein.
Referring to fig. 2, when determining the risk degree of the mobile object according to the risk distance, determining a plurality of expansion areas with different areas based on the maximum self-size data of the mobile object, wherein the different expansion areas correspond to different risk degrees, and determining the risk degree of the mobile object based on the fitting relation between the risk distance and the expansion areas. In stationary scenes such as grain depots, factories, airports and wharfs, the moving object is mainly a vehicle, the maximum self-size data is the diagonal length of the vehicle when the size of the vehicle is empty or the size of the load does not exceed the size of the vehicle itself, and the maximum self-size data can be the maximum length of the load when the size of the vehicle load exceeds the size of the vehicle itself, and the maximum self-size data needs to be determined according to actual conditions and is not described in detail herein. After the maximum self-size data is determined, the expansion area may be determined based on the maximum self-size data, for example, a circular area may be constructed as the expansion area with a certain multiple of the maximum self-size data as a diameter. The number of the expansion areas directly corresponds to the level of the risk degree, for example, after the expansion areas are determined to be three, the risk degree may be divided into three levels, and the corresponding three expansion areas may be respectively defined as a collision area, a dangerous area and a safe area, specifically, during the movement of the moving object, the moving object may collide with the moving object when the obstacle enters the collision area, the moving object may collide with the obstacle when the obstacle enters the dangerous area, and the moving object may not collide with the obstacle when the obstacle only enters the safe area.
After judging the risk degree, the mixed a algorithm needs to be adjusted so as to avoid interference between the planned moving path and the obstacle, and the specific adjustment method is as follows.
When the risk degree reaches a first limit, adjusting the step length of the mixed A algorithm to a preset minimum value and the curvature to a preset maximum value, wherein the first limit corresponds to the collision area; when the risk degree reaches a second limit, dynamically adjusting the step length and the curvature of the mixed A-type algorithm based on the risk distance, wherein the second limit corresponds to the dangerous area; and when the risk degree reaches a third limit, adjusting the step length of the mixed A algorithm to a preset maximum value and the curvature to a preset minimum value, wherein the third limit corresponds to the safety area.
Further, the method for dynamically adjusting the step length of the hybrid a-algorithm based on the risk distance comprises the following steps:
wherein D (x) is a risk distance, max_l and min_l respectively represent a preset maximum step length and a preset minimum step length, and epsilon is the maximum self-size data of the moving object;
the method for dynamically adjusting the curvature of the hybrid a-algorithm based on the risk distance comprises the following steps:
wherein max_c and min_c represent preset maximum and minimum curvatures, respectively.
Through the above process, in the process of expanding the path node, the step length and the curvature of the hybrid a-algorithm can be continuously adjusted along with the change of the risk distance, so that the safety of the obtained moving path can be ensured, and the searching speed of the hybrid a-algorithm and the quality of the moving path generated in an open area are improved.
Again, the path nodes are extended according to the risk level of the moving object. In the process of expanding the path nodes, the risk distance is added into the cost function of the mixed A-type algorithm, so that the path generated by the mixed A-type algorithm keeps a certain distance with the obstacle as far as possible, and the possibility of collision between the moving object and the obstacle is further reduced.
Then, when the moving path is extended to a path node where the end point can be directly connected by the RS curve, the angle information of the path node is normalized. Specifically, the normalization method is to normalize the angle information of the path node toIs an integer multiple of (a). Because the passable road network in the fixed scene is generally set to be a horizontal, flat and vertical route, the corrected RS curve can be kept parallel to the road network, and therefore the quality of the RS curve is improved.
Since the starting point of the RS curve is forcedly regulated, an angle jump exists between the corrected RS curve and a path expanded by the mixed a-algorithm, and the movement of the moving object is possibly interfered, so that further processing is required for the corrected RS curve. Specifically, it is necessary to smooth the RS curve. The method for smoothing the RS curve comprises the following steps.
The path node for determining the angle jump is recorded as an angle jump point, and the method for determining the angle jump point is as follows.
First, the angle of each path node on the path of travel is traversed.
Second, the difference between the angle of the path node and the angle of the previous path node is calculated.
Thirdly, when the difference value is larger than a preset threshold value, determining that the angle of the path node jumps, and marking the path node as an angle jump point. The threshold may be determined according to the actual situation, and in this embodiment, the threshold is set to 15 °, that is, when the difference between the threshold and the threshold is greater than 15 °, the current path node may be determined to be the angle trip point of the moving path.
After the angle jump point is determined, the shortest distance between the angle jump point and the obstacle is calculated and recorded as a correction distance. In the invention, the Kd_Tree module of the KD Tree algorithm is used for calculating the shortest distance between the angle jump point and surrounding obstacles and recording the shortest distance as a correction distance turn_dis.
The length correction data and curvature correction data of the RS curve are calculated based on the correction distance turn_dis. The calculation method of the curvature correction data is consistent with a method for dynamically adjusting the curvature of the hybrid a-algorithm based on the risk distance, and will not be described herein. The specific calculation method of the length correction data comprises the following steps: taking the angle jump point as a midpoint, respectively taking the node number of 2 x turn_dis forwards as the starting point of the RS curve, and taking the node number of 2 x turn_dis backwards as the end point of the RS curve.
And finally, correcting the RS curve according to the length correction data and the curvature correction data. After the length correction data is well determined, the starting point and the end point of the RS curve are determined, and then the RS curve can be subjected to smooth correction processing by combining the curvature correction data.
Referring to fig. 3, because the RS curve only considers the vehicle kinematic model and does not consider surrounding obstacles, the RS curve is too close to the obstacle or even passes through the obstacle, so the invention mainly corrects the length and curvature of the RS curve, when the angle jump point is close to the obstacle, the generated RS curve is shorter in length and larger in curvature, and when the angle jump point is far from the obstacle, the generated RS curve is longer in length and smaller in curvature, and the quality of the moving path is improved.
The invention can accelerate the searching speed by changing the searching step length of the mixed A algorithm, and realize the large-step-length small-curvature expansion in the open area and the short-step-length large-curvature expansion in the narrow area, thereby avoiding frequent steering of a moving object and improving the efficiency of path planning; the generated moving path is kept at a certain distance from the obstacle by adding the distance constraint with the obstacle, so that the safety of the moving object is improved; by optimizing the generation of the RS curve in the mixed A algorithm and correcting the RS curve, the generated path is kept parallel to the road network of the fixed scene as much as possible, so that the quality of the path is improved, and the safety and stability of the moving object are further improved. The invention can be applied to automatic driving of vehicles in fixed scenes such as grain depots, factories, airports and wharfs, provides a safe, stable and highly-executable path for the automatic driving vehicles, improves the driving stability of the automatic driving vehicles, greatly reduces the occurrence of dangerous situations in the driving process and improves the working efficiency of the vehicles.
Finally, in the specific model, comparing the present invention with the existing hybrid a-algorithm, the result is shown in fig. 4, and it can be seen that the search duration of the present invention is effectively reduced, and the planned moving path is smoother.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A path planning method for a fixed scene, comprising:
acquiring a map of a fixed scene, constructing a KD tree based on obstacles in the map, and planning a moving path of a moving object through a path searching algorithm;
calculating the shortest distance between the current path node and the obstacle based on the KD tree, marking the shortest distance as a risk distance, and judging the risk degree of the moving object according to the risk distance;
expanding path nodes according to the risk degree of the mobile object;
when the method is extended to a path node capable of directly utilizing the RS curve to connect with the terminal point, the angle information of the path node is regulated; and smoothing the RS curve.
2. A path planning method for a fixed scene according to claim 1, characterized in that the path search algorithm employs a hybrid a-algorithm;
after the risk distance is calculated, the risk distance is added to the cost function of the hybrid a-algorithm.
3. The path planning method for a fixed scene according to claim 2, wherein when judging the risk level of the moving object according to the risk distance, a plurality of expansion areas with different areas are determined based on the maximum self-size data of the moving object, the different expansion areas correspond to the different risk levels, and the risk level of the moving object is determined based on the fitting relation of the risk distance and the expansion areas.
4. A path planning method for a fixed scene according to claim 3, characterized in that the step size of the hybrid a-algorithm is adjusted to a preset minimum value and the curvature is adjusted to a preset maximum value when the risk level reaches a first limit, and the step size and curvature of the hybrid a-algorithm are dynamically adjusted based on the risk distance when the risk level reaches a second limit.
5. The path planning method for a fixed scene according to claim 4, wherein the method for dynamically adjusting the step size of the hybrid a-algorithm based on the risk distance is as follows:
wherein D (x) is a risk distance, max_l and min_l respectively represent a preset maximum step length and a preset minimum step length, and epsilon is the maximum self-size data of the moving object;
the method for dynamically adjusting the curvature of the hybrid a-algorithm based on the risk distance comprises the following steps:
wherein max_c and min_c represent preset maximum and minimum curvatures, respectively.
6. The path planning method for a fixed scene according to claim 1, wherein when expanding to a path node capable of directly connecting an end point using an RS curve, angle information of the path node is normalized toIs an integer multiple of (a).
7. The path planning method for a fixed scene as claimed in claim 1, wherein the method of smoothing the RS curve comprises:
determining a path node with an angle jump as an angle jump point;
calculating the shortest distance between the angle jump point and the obstacle and marking the shortest distance as a correction distance;
calculating length correction data and curvature correction data of the RS curve based on the correction distance;
and correcting the RS curve according to the length correction data and the curvature correction data.
8. The path planning method for a fixed scene as claimed in claim 7, wherein the method for determining the angle trip point is:
traversing the angle of each path node on the moving path;
calculating a difference between the angle of the path node and the angle of the previous path node;
and when the difference value is larger than a preset threshold value, determining that the angle of the path node jumps, and marking the path node as an angle jump point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310562661.2A CN116793377A (en) | 2023-05-18 | 2023-05-18 | Path planning method for fixed scene |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310562661.2A CN116793377A (en) | 2023-05-18 | 2023-05-18 | Path planning method for fixed scene |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116793377A true CN116793377A (en) | 2023-09-22 |
Family
ID=88038273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310562661.2A Pending CN116793377A (en) | 2023-05-18 | 2023-05-18 | Path planning method for fixed scene |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116793377A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130112507A (en) * | 2012-04-04 | 2013-10-14 | 인하대학교 산학협력단 | Safe path planning method of a mobile robot using s× algorithm |
| CN108981715A (en) * | 2018-08-22 | 2018-12-11 | 北航（四川）西部国际创新港科技有限公司 | A kind of unmanned plane paths planning method of mountain area flight safety degree constraint |
| CN110361013A (en) * | 2019-07-22 | 2019-10-22 | 上海应用技术大学 | A kind of path planning system and method for auto model |
| US20200017102A1 (en) * | 2019-09-26 | 2020-01-16 | Intel Corporation | Safety module, automated driving system, and methods thereof |
| CN112013846A (en) * | 2020-08-18 | 2020-12-01 | 南京信息工程大学 | Path planning method combining dynamic step RRT algorithm and potential field method |
| CN113984080A (en) * | 2021-10-26 | 2022-01-28 | 西安交通大学 | Hierarchical local path planning method suitable for large complex scene |
| CN115562265A (en) * | 2022-09-29 | 2023-01-03 | 哈尔滨理工大学 | Mobile robot path planning method based on improved A-x algorithm |
-
2023
- 2023-05-18 CN CN202310562661.2A patent/CN116793377A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20130112507A (en) * | 2012-04-04 | 2013-10-14 | 인하대학교 산학협력단 | Safe path planning method of a mobile robot using s× algorithm |
| CN108981715A (en) * | 2018-08-22 | 2018-12-11 | 北航（四川）西部国际创新港科技有限公司 | A kind of unmanned plane paths planning method of mountain area flight safety degree constraint |
| CN110361013A (en) * | 2019-07-22 | 2019-10-22 | 上海应用技术大学 | A kind of path planning system and method for auto model |
| US20200017102A1 (en) * | 2019-09-26 | 2020-01-16 | Intel Corporation | Safety module, automated driving system, and methods thereof |
| CN112013846A (en) * | 2020-08-18 | 2020-12-01 | 南京信息工程大学 | Path planning method combining dynamic step RRT algorithm and potential field method |
| CN113984080A (en) * | 2021-10-26 | 2022-01-28 | 西安交通大学 | Hierarchical local path planning method suitable for large complex scene |
| CN115562265A (en) * | 2022-09-29 | 2023-01-03 | 哈尔滨理工大学 | Mobile robot path planning method based on improved A-x algorithm |
Non-Patent Citations (1)
| Title |
|---|
| 田雨等: "基于改进HybridA*的非完整约束机器人路径规划算法研究", 机械, vol. 50, no. 3, 31 March 2023 (2023-03-31) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114234998B (en) | Unmanned multi-target point track parallel planning method based on semantic road map | |
| CN107702716B (en) | Unmanned driving path planning method, system and device | |
| CN109579854B (en) | Unmanned vehicle obstacle avoidance method based on fast expansion random tree | |
| US20230159056A1 (en) | Method and apparatus for planning obstacle avoidance path of traveling apparatus | |
| CN114791288B (en) | Method and device for planning driving path of mine vehicle and computer equipment | |
| CN112284393B (en) | Global path planning method and system for intelligent mobile robot | |
| CN111152784B (en) | Intelligent passenger-riding parking local path planning method | |
| Fassbender et al. | Trajectory planning for car-like robots in unknown, unstructured environments | |
| CN115346385B (en) | Unmanned mine car automatic obstacle avoidance method based on complex road conditions | |
| CN113296119B (en) | Unmanned obstacle avoidance driving method and terminal based on laser radar and UWB array | |
| CN112092810B (en) | Vehicle parking-out method and device and electronic equipment | |
| CN114281084B (en) | Intelligent vehicle global path planning method based on improved A-algorithm | |
| CN115140096A (en) | Spline curve and polynomial curve-based automatic driving track planning method | |
| CN113296118A (en) | Unmanned obstacle-avoiding method and terminal based on laser radar and GPS | |
| CN116793377A (en) | Path planning method for fixed scene | |
| CN110673610A (en) | ROS-based factory AGV path planning method | |
| CN112327887B (en) | Unmanned vehicle collision avoidance path planning method and system based on iteration improved APF | |
| Buckman et al. | Generating visibility-aware trajectories for cooperative and proactive motion planning | |
| CN113799776A (en) | Vehicle lane changing method and device and electronic equipment | |
| CN115903854B (en) | Automatic driving real-time track planning method for dynamic structured road | |
| CN114475652B (en) | Vehicle motion planning method, device, equipment and medium | |
| CN114460933A (en) | Mobile robot local path planning algorithm for dynamic environment | |
| Park et al. | Occlusion-aware risk assessment and driving strategy for autonomous vehicles using simplified reachability quantification | |
| CN115950431A (en) | Path planning method, system, computer equipment, readable storage medium and motor vehicle | |
| CN115871709A (en) | Method, device, equipment, medium and vehicle for planning station-entering track of automatic driving vehicle |
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 |