Unlock instant, AI-driven research and patent intelligence for your innovation.

Local path planning method and system based on multi-computing power fusion

A technology of local path planning and path planning, applied in the field of local navigation of intelligent vehicles

Pending Publication Date: 2022-04-01
CHANGAN UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the artificial potential field method often encounters the problem of local minimum in the process of obstacle avoidance application.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Local path planning method and system based on multi-computing power fusion
  • Local path planning method and system based on multi-computing power fusion
  • Local path planning method and system based on multi-computing power fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] A local path planning method based on multi-computing power fusion, comprising the following steps:

[0040] S1: Obtain obstacle information and build a map containing obstacle information; obstacle information includes the coordinates and size of the obstacle;

[0041] S2: Obtain obstacle information, establish artificial force field, calculate and initialize path planning tasks, and establish repulsion potential field and repulsion function;

[0042] S3: Detect whether there are obstacles on the original set path based on the repulsion function, and control the vehicle to avoid obstacles under the action of the repulsion potential field;

[0043] S4: Set the sampling time distance threshold, and judge whether to fall into a local optimal situation;

[0044] If it is a local optimum, create a two-dimensional grid map;

[0045] If it is not a local optimal situation, return to S3;

[0046] S5: Based on the two-dimensional grid map, combined with the initialization pa...

Embodiment 2

[0048] A local path planning method based on multi-computing power fusion, comprising the following steps:

[0049] S1: In the process of following the global path, the vehicle collects road network information through the vehicle and combines the vehicle lidar, camera and millimeter-wave radar to perceive the surrounding environment in real time, and obtain key information such as the coordinates and sizes of obstacles.

[0050] S2: According to the information extracted by the intelligent vehicle sensor, a map containing obstacle information is established;

[0051] S3: Initialize the map global path planning algorithm and various parameters in the artificial potential field algorithm. The artificial potential field is the impact of obstacles and target points on the smart vehicle, and the planned path is the path to be followed by the smart car; and initialize the path planning Task;

[0052] S4: Calculate the repulsive force received by the current vehicle position in the...

Embodiment 3

[0060] A local path planning method based on multi-computing power fusion, comprising the following steps:

[0061] S1: In the process of following the global path, the vehicle collects road network information through the vehicle and combines the vehicle lidar, camera and millimeter-wave radar to perceive the surrounding environment in real time, and obtain key information such as the coordinates and sizes of obstacles.

[0062] S2: According to the information extracted by the intelligent vehicle sensor, a map containing obstacle information is established;

[0063] S3: Initialize the map global path planning algorithm and various parameters in the artificial potential field algorithm. The artificial potential field is the impact of obstacles and target points on the smart vehicle, and the planned path is the path to be followed by the smart car; and initialize the path planning Task;

[0064] S4: Calculate the repulsive force received by the current vehicle position in the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a local path planning method and system based on multi-computing power fusion, and belongs to the field of local navigation of intelligent vehicles. According to information extracted by an intelligent vehicle sensor, a map containing obstacle information is established, an artificial potential field is constructed, a path planning task is initialized, repulsive force received by the current position of a vehicle in the artificial potential field is calculated, the distance from the current position of the vehicle to a target point serves as an adjustment factor and is added into a repulsive force function, and segmented adjustment is carried out. And designing a sampling time distance threshold value, judging whether a local optimal condition is trapped or not based on the unit sampling time distance threshold value, and if so, establishing a two-dimensional grid map. And if not, continuing to return to the designed artificial potential field method for local path planning, and locally planning the plurality of intermediate target points one by one by using the improved artificial potential field method.

Description

technical field [0001] The invention belongs to the field of local navigation of intelligent vehicles, and relates to a local path planning method and system based on multi-computing fusion. Background technique [0002] Real-time path planning and navigation of intelligent vehicles is one of the key elements reflecting the autonomy of robots, and it is also one of the more difficult problems to solve. Intelligent vehicle path planning is mainly divided into planning with known environmental information and planning with unknown environmental information. For the former, offline planning is mostly used, and the obtained path is better, while the latter mostly uses online planning, which reflects the real-time nature of path planning. [0003] In recent years, many methods of intelligent vehicle path planning have been studied. The main path planning methods can be divided into two categories: artificial intelligence methods (AI) and artificial potential field methods (APF)...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G05D1/02
Inventor 韩毅崔洋陈扬帆顾恒之徐震
Owner CHANGAN UNIV