CN117055559A - Automatic driving vehicle obstacle avoidance method for improving artificial potential field method - Google Patents
Automatic driving vehicle obstacle avoidance method for improving artificial potential field method Download PDFInfo
- Publication number
- CN117055559A CN117055559A CN202311103703.2A CN202311103703A CN117055559A CN 117055559 A CN117055559 A CN 117055559A CN 202311103703 A CN202311103703 A CN 202311103703A CN 117055559 A CN117055559 A CN 117055559A
- Authority
- CN
- China
- Prior art keywords
- repulsive force
- obstacle
- potential field
- grid
- road boundary
- 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 41
- 238000013459 approach Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 claims description 2
- 239000003086 colorant Substances 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 5
- 230000007423 decrease Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an automatic driving vehicle obstacle avoidance method for improving a manual potential field method, which comprises the following steps of: s1, importing an occupied grid map; s2, establishing a repulsive force function: establishing an obstacle repulsive force function and a road boundary repulsive force function; s3, establishing a total repulsive force function, calculating repulsive force sum of each grid point aiming at occupying a grid map, and taking the difference of the repulsive force sum as a resistance value in a resistance network, wherein the resistance network is formed by arranging a resistance at the midpoint of the side length of each two transversely adjacent grids in a passable area, arranging a resistance at the midpoint of the side length of each two longitudinally adjacent grids, and electrically connecting the adjacent resistances from the center of each grid along the longitudinal direction and the transverse direction respectively to construct the resistance network; s4, generating a path. The invention adopts a potential field method, uses a resistance network and current, is distinct from the traditional method, and widens the traditional thought.
Description
Technical Field
The invention relates to the field of vehicle obstacle avoidance, in particular to an automatic driving vehicle obstacle avoidance method for improving an artificial potential field method.
Background
Among the obstacle avoidance methods of vehicles, the most widely used artificial potential field method is currently used. Whereas conventional artificial potential fields have the following drawbacks:
1. local minima occur, leading to deadlock: when the attraction force and the repulsion force of the controlled target are opposite in direction and same in size, the artificial potential field method can produce a deadlock phenomenon. At this time, the attraction force and the repulsion force cancel out, the controlled target falls into a local minimum point of the potential field, and the planned path oscillates or cannot continuously advance towards the target point.
2. The goal is not reachable: since the position of the obstacle in the environment is not fixed, a situation may occur in which the target point is too close to the obstacle. When the obstacle is too close to the target point, as the distance between the controlled vehicle and the target point decreases, the obstacle also continuously approaches the obstacle near the target point, the attractive potential field decreases and the repulsive potential field increases. In this case, a situation may occur in which the repulsive force of the potential field is much larger than the attractive force of the potential field in the vicinity of the target point, possibly resulting in the controlled vehicle not reaching the target point.
Disclosure of Invention
Aiming at the problems of the existing artificial potential field method, the invention provides an automatic driving vehicle obstacle avoidance method for improving the artificial potential field method.
For this purpose, the invention adopts the following technical method:
an automatic driving vehicle obstacle avoidance method for improving an artificial potential field method is characterized by comprising the following steps of:
s1, importing an occupied grid map: in the occupied grid map, the grids where the barriers and the passable areas are located are distinguished through different colors;
s2, establishing a repulsive force function, including:
s21, establishing an obstacle repulsive force function:
the obstacle repulsive force function is:
wherein U is obs A repulsive potential field for an obstacle; k (k) obs Gain factors for the obstacle repulsive force; ρ 0 Is the influence range of the repulsive force of the obstacle; ρ (q, q) obs ) Distance from the center of the current grid to the nearest obstacle;
obstacle repulsive force F obs Negative gradient of potential field for obstacle repulsive force:
s22, establishing a road boundary repulsive force function:
wherein U is r A repulsive potential field for a road boundary; k (k) r Gain factors for road boundary repulsive forces; ρ 1 The influence range of the repulsive force of the road boundary is defined; ρ (q, q) r ) The minimum distance from the center of the grid where the controlled vehicle is currently located to the road boundary;
road boundary repulsive force F r Negative gradient of repulsive potential field for road boundary:
s3, establishing a total repulsive force function:
for an occupied grid map, calculating the repulsive force and the sum of each grid point:
F＝F r +F obs
wherein F is obs Is an obstacle repulsive force; f (F) r For the road boundary repulsive force,
calculating the difference of the repulsive force sum of a certain grid point in the passable area and the repulsive force sum of adjacent grid points, and taking the difference of the repulsive force sum as a resistance value in a resistance network, wherein the resistance network is as follows: for occupying the grid map, assuming that the vehicle has four directions, namely front, back, left and right, and does not comprise diagonal directions, in the passable area, a resistor is arranged at the midpoint of the side length of each two adjacent grids in the transverse direction, a resistor is arranged at the midpoint of the side length of each two adjacent grids in the longitudinal direction, and adjacent resistors are respectively and electrically connected from the center of each grid in the longitudinal direction and the transverse direction to construct a resistor network;
s4, path generation: in the resistor network of S3, a voltage is applied between the starting point and the end point of the autonomous vehicle, the current value flowing through each branch in the resistor network is determined, a plurality of paths can be obtained in the resistor network, and a collision-free path is selected according to the local maximum current direction at each continuous node between the starting point and the end point.
Preferably, the occupied grid map is a space divided into a limited plurality of grids, and the grid side length is the dividing precision.
Preferably, the k in S2 r The value of (C) is 0.1-0.5, and the k is obs The value of (2) is 0.1 to 0.5.
Preferably, ρ as described in S2 0 Has a value of 10m, said ρ 1 The value of (2) is 5m.
According to the invention, an automatic driving vehicle obstacle avoidance method with an improved artificial potential field method is adopted, a repulsive force function is used for constructing a resistance grid on an occupied grid map, and voltage is applied according to a circuit principle, so that an optimal path is obtained.
Compared with the prior art, the invention has the following beneficial effects:
1. the technical method improves the traditional artificial potential field method, and searches a path through current without attractive force, so that deadlock phenomenon can not occur; aiming at the fact that the target is not reachable, the method adopts an improved algorithm, and even if the distance between the target point and the obstacle is too close, the path can still be found.
2. The invention adopts a potential field method, uses a resistance network and current, is distinct from the traditional method, and widens the traditional thought.
3. Compared with the traditional artificial potential field method, the invention does not adopt an gravitation function, thereby reducing the work calculation amount.
Drawings
FIG. 1 is a schematic illustration of an occupied grid map according to one embodiment of the present invention;
FIG. 2 is a schematic diagram of an obstacle repulsive function in accordance with one embodiment of the present invention;
FIG. 3 is a schematic diagram of a road boundary repulsive function according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a resistor network according to one embodiment of the present invention;
FIG. 5 is a schematic diagram of current generation according to one embodiment of the present invention;
FIG. 6 is a schematic diagram of path generation according to one embodiment of the invention.
Detailed Description
The technical process of the present invention will be described in further detail with reference to the accompanying drawings and examples.
Examples
An automatic driving vehicle obstacle avoidance method for improving an artificial potential field method comprises the following steps:
s1, importing an occupied grid map: as shown in fig. 1, in the occupied grid map, a black grid represents an obstacle, and a white grid represents a passable area.
The occupied grid map adopted by the invention is a classical description mode of the map, the occupied grid map divides a space into a plurality of limited grids, and the side length of the grids is the dividing precision.
S2, establishing a repulsive force function, including:
s21, establishing an obstacle repulsive force function:
the vehicle obstacle avoidance needs to avoid the obstacle, so that an obstacle repulsive potential field is adopted. When the distance between the automatic driving vehicle and the obstacle is larger than the influence range of the repulsive force potential field, the automatic driving vehicle is not interfered by the obstacle; as the distance between the autonomous vehicle and the obstacle gets closer and closer, the resistance experienced by the autonomous vehicle increases; and the repulsive force tends to infinity when the autonomous vehicle collides with an obstacle.
The obstacle repulsive force function is:
wherein U is obs A repulsive potential field for an obstacle; k (k) obs Is the repulsive force of the obstacleGain factor, typically in the range of 0.1 to 0.5; ρ 0 The range of influence of the repulsive force of the obstacle can be generally set to about 10 m; ρ (q, q) obs ) Is the distance from the center of the current grid to the nearest obstacle.
Obstacle repulsive force F obs Negative gradient of potential field for obstacle repulsive force:
s22, establishing a road boundary repulsive force function:
the traditional artificial potential field method repulsive force only establishes potential fields for obstacles, but vehicles are still constrained by lane boundaries on a structured road, so that the invention adopts a road boundary repulsive force function, and repulsive force applied to the lane boundaries is larger when the vehicle approaches the lane boundaries.
The road boundary repulsive force function is:
wherein U is r A repulsive potential field for a road boundary; k (k) r A value between 0.1 and 0.5 may be generally set for the road boundary repulsive gain factor; ρ 1 The influence range of the road boundary repulsive force can be set to a value of about 5m in general; ρ (q, q) r ) Is the minimum distance from the center of the grid where the controlled vehicle is currently located to the road boundary.
Road boundary repulsive force F r Negative gradient of repulsive potential field for road boundary:
s3, establishing a total repulsive force function:
for an occupied grid map, calculating the repulsive force and the sum of each grid point:
F＝F r +F 0bs
wherein F is obs Is an obstacle repulsive force; f (F) r Is the road boundary repulsive force.
And calculating the difference of the sum of the repulsive force of a certain grid point and the repulsive force of the adjacent grid point in the passable area, and taking the difference of the sum of the repulsive force as one resistance value in the resistance network. Wherein:
the construction method of the resistor network comprises the following steps: for occupying the grid map, it is assumed that the vehicle has only four directions, namely front, rear, left and right, and does not include diagonal directions, as shown in fig. 4, in the passable area, a resistor is arranged at the midpoint of the side length of each two laterally adjacent grids, a resistor is arranged at the midpoint of the side length of each two longitudinally adjacent grids, and adjacent resistors are electrically connected from the center of each grid along the longitudinal direction and the lateral direction respectively, so as to form the resistor network.
S4, path generation: in the resistor network of S3, a voltage is applied between the start point and the end point of the autonomous vehicle, as shown in fig. 5. The value of the current flowing through each branch of the resistor network is determined, and a plurality of paths can be obtained in the resistor network. The collision-free path is selected in accordance with the local maximum current direction at each successive node between the start point and the end point, as shown in fig. 6.
Kirchhoff's current law states that in an electrical network, the sum of the currents flowing into any node is equal to the sum of the currents flowing out of that node. Current law: i=v/R, where V is voltage, R is resistance, and I is current.
The invention adopts the vehicle obstacle avoidance method of improving the artificial potential field method and the resistance network method, solves the problems that the artificial potential field method cannot reach the target and has local minimum value, and the resistance current method adopted by the invention can find a track inevitably, so that the problems that the target cannot reach and has local minimum value are avoided.
Claims (4)
1. An automatic driving vehicle obstacle avoidance method for improving an artificial potential field method is characterized by comprising the following steps of:
s1, importing an occupied grid map: in the occupied grid map, the grids where the barriers and the passable areas are located are distinguished through different colors;
s2, establishing a repulsive force function, including:
s21, establishing an obstacle repulsive force function:
the obstacle repulsive force function is:
wherein U is obs A repulsive potential field for an obstacle; k (k) obs Gain factors for the obstacle repulsive force; ρ 0 Is the influence range of the repulsive force of the obstacle; ρ (q, q) obs ) Distance from the center of the current grid to the nearest obstacle;
obstacle repulsive force F obs Negative gradient of potential field for obstacle repulsive force:
s22, establishing a road boundary repulsive force function:
wherein U is r A repulsive potential field for a road boundary; k (k) r Gain factors for road boundary repulsive forces; ρ 1 The influence range of the repulsive force of the road boundary is defined; ρ (q, q) r ) The minimum distance from the center of the grid where the controlled vehicle is currently located to the road boundary;
road boundary repulsive force F r Negative gradient of repulsive potential field for road boundary:
s3, establishing a total repulsive force function:
for an occupied grid map, calculating the repulsive force and the sum of each grid point:
F＝F r +F obs
wherein F is obs Is an obstacle repulsive force; f (F) r For the road boundary repulsive force,
calculating the difference of the repulsive force sum of a certain grid point in the passable area and the repulsive force sum of adjacent grid points, and taking the difference of the repulsive force sum as a resistance value in a resistance network, wherein the resistance network is as follows: for occupying the grid map, assuming that the vehicle has four directions, namely front, back, left and right, and does not comprise diagonal directions, in the passable area, a resistor is arranged at the midpoint of the side length of each two adjacent grids in the transverse direction, a resistor is arranged at the midpoint of the side length of each two adjacent grids in the longitudinal direction, and adjacent resistors are respectively and electrically connected from the center of each grid in the longitudinal direction and the transverse direction to construct a resistor network;
s4, path generation: in the resistor network of S3, a voltage is applied between the starting point and the end point of the autonomous vehicle, the current value flowing through each branch in the resistor network is determined, a plurality of paths can be obtained in the resistor network, and a collision-free path is selected according to the local maximum current direction at each continuous node between the starting point and the end point.
2. The method of obstacle avoidance for an autonomous vehicle improving the artificial potential field approach as claimed in claim 1 wherein: the occupied grid map is formed by dividing a space into a limited plurality of grids, and the side length of each grid is the dividing precision.
3. The method of obstacle avoidance for an autonomous vehicle improving the artificial potential field approach as claimed in claim 1 wherein: s2 is described as k r The value of (C) is 0.1-0.5, and the k is obs The value of (2) is 0.1 to 0.5.
4. The method of obstacle avoidance for an autonomous vehicle improving the artificial potential field approach as claimed in claim 1 wherein: p as described in S2 0 Has a value of 10m, said ρ 1 The value of (2) is 5m.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311103703.2A CN117055559A (en) | 2023-08-30 | 2023-08-30 | Automatic driving vehicle obstacle avoidance method for improving artificial potential field method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311103703.2A CN117055559A (en) | 2023-08-30 | 2023-08-30 | Automatic driving vehicle obstacle avoidance method for improving artificial potential field method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117055559A true CN117055559A (en) | 2023-11-14 |
Family
ID=88667530
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311103703.2A Pending CN117055559A (en) | 2023-08-30 | 2023-08-30 | Automatic driving vehicle obstacle avoidance method for improving artificial potential field method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117055559A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016045615A1 (en) * | 2014-09-25 | 2016-03-31 | 科沃斯机器人有限公司 | Robot static path planning method |
| US20200086486A1 (en) * | 2018-09-13 | 2020-03-19 | Pilz Gmbh & Co. Kg | Method and apparatus for collision-free motion planning of a manipulator |
| CN111955055A (en) * | 2018-04-10 | 2020-11-17 | 株式会社小糸制作所 | Vehicle lamp, lighting circuit, driving circuit, and driving integrated light source thereof |
| CN113359756A (en) * | 2021-06-29 | 2021-09-07 | 上海工程技术大学 | Method for realizing real-time planning of obstacle avoidance path of omnidirectional mobile robot based on grid method |
| CN114265410A (en) * | 2021-12-25 | 2022-04-01 | 长安大学 | Local path planning method and system based on multi-computational power fusion |
| CN114924559A (en) * | 2022-04-08 | 2022-08-19 | 南京航空航天大学 | Intelligent vehicle path planning method for controlling virtual force direction |
| CN115328152A (en) * | 2022-09-05 | 2022-11-11 | 北京理工大学 | Unmanned vehicle local real-time obstacle avoidance path planning method based on improved artificial potential field method |
| CN115782867A (en) * | 2022-11-17 | 2023-03-14 | 上海西井信息科技有限公司 | Track collision risk assessment method and device, electronic equipment and storage medium |
| CN116202550A (en) * | 2023-05-06 | 2023-06-02 | 华东交通大学 | Automobile path planning method integrating improved potential field and dynamic window |
-
2023
- 2023-08-30 CN CN202311103703.2A patent/CN117055559A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016045615A1 (en) * | 2014-09-25 | 2016-03-31 | 科沃斯机器人有限公司 | Robot static path planning method |
| CN111955055A (en) * | 2018-04-10 | 2020-11-17 | 株式会社小糸制作所 | Vehicle lamp, lighting circuit, driving circuit, and driving integrated light source thereof |
| US20200086486A1 (en) * | 2018-09-13 | 2020-03-19 | Pilz Gmbh & Co. Kg | Method and apparatus for collision-free motion planning of a manipulator |
| CN113359756A (en) * | 2021-06-29 | 2021-09-07 | 上海工程技术大学 | Method for realizing real-time planning of obstacle avoidance path of omnidirectional mobile robot based on grid method |
| CN114265410A (en) * | 2021-12-25 | 2022-04-01 | 长安大学 | Local path planning method and system based on multi-computational power fusion |
| CN114924559A (en) * | 2022-04-08 | 2022-08-19 | 南京航空航天大学 | Intelligent vehicle path planning method for controlling virtual force direction |
| CN115328152A (en) * | 2022-09-05 | 2022-11-11 | 北京理工大学 | Unmanned vehicle local real-time obstacle avoidance path planning method based on improved artificial potential field method |
| CN115782867A (en) * | 2022-11-17 | 2023-03-14 | 上海西井信息科技有限公司 | Track collision risk assessment method and device, electronic equipment and storage medium |
| CN116202550A (en) * | 2023-05-06 | 2023-06-02 | 华东交通大学 | Automobile path planning method integrating improved potential field and dynamic window |
Non-Patent Citations (3)
| Title |
|---|
| YANJUN HUANG，ET AL.: "A Motion Planning and Tracking Framework for Autonomous Vehicles Based on Artificial Potential Field Elaborated Resistance Network Approach", IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, vol. 67, no. 2, 29 February 2020 (2020-02-29), pages 1376 - 1386, XP011748139, DOI: 10.1109/TIE.2019.2898599 * |
| 姚靖靖;邱于兵;敖俊宇;: "移动机器人避障路径规划改进人工势场法", 科学技术与工程, no. 13, 8 May 2011 (2011-05-08) * |
| 海振洋等: "基于改进人工势场法的车辆路径规划与跟踪控制", 山东交通学院学报, vol. 31, no. 21, 30 April 2023 (2023-04-30), pages 1 - 7 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111238521B (en) | Path planning method and system for unmanned vehicle | |
| CN110136481B (en) | Parking strategy based on deep reinforcement learning | |
| DE102016204593B4 (en) | Vehicle cruise control device | |
| CN109987092A (en) | A kind of determination method on vehicle obstacle-avoidance lane-change opportunity and the control method of avoidance lane-change | |
| CN108762270B (en) | Improved path planning algorithm for variable probability bidirectional fast search random tree | |
| CN110361021B (en) | Lane line fitting method and system | |
| CN109579854B (en) | Unmanned vehicle obstacle avoidance method based on fast expansion random tree | |
| CN110928297B (en) | Intelligent bus route planning method based on multi-objective dynamic particle swarm optimization | |
| CN112965476B (en) | High-speed unmanned vehicle trajectory planning system and method based on multi-window model | |
| CN107608372A (en) | It is a kind of that path planning method is cooperateed with improving the multiple no-manned plane that PH curves are combined based on improvement RRT algorithms | |
| DE102019108795A1 (en) | FAHRZEUGWEGIDENTIFIKATION | |
| CN107085438B (en) | Unmanned aerial vehicle path correction method and system based on quasi-uniform spline curve | |
| US20210089036A1 (en) | Method and device for calculating a trajectory of a vehicle | |
| CN108120448A (en) | Path of navigation setting device and path of navigation setting method | |
| CN112622932A (en) | Automatic driving track-changing planning algorithm based on heuristic search of potential energy field | |
| CN113479217A (en) | Lane changing and obstacle avoiding method and system based on automatic driving | |
| WO2022062349A1 (en) | Vehicle control method, apparatus, storage medium, and electronic device | |
| CN101833699A (en) | Heuristic route segment path-finding method for ship route design | |
| CN108153328A (en) | A kind of more guided missiles based on segmentation Bezier cooperate with path planning method | |
| CN106595663A (en) | Aircraft auto-route planning method with combination of searching and optimization | |
| CN117055559A (en) | Automatic driving vehicle obstacle avoidance method for improving artificial potential field method | |
| CN114859905A (en) | Local path planning method based on artificial potential field method and reinforcement learning | |
| CN114924559A (en) | Intelligent vehicle path planning method for controlling virtual force direction | |
| CN113525375B (en) | Vehicle lane changing method and device based on artificial potential field method | |
| CN114355909A (en) | Path planning method and device, computer equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |