Path planning method based on structured data

Abstract

The invention relates to the field of robot navigation path planning methods, and particularly discloses a path planning method based on structured data. The method comprises the following steps: (1),performing global path planning: firstly, constructing a road network according to the structured data; reading and analyzing the structured road network data, and constructing lane lines and road edges in a road network data structure; (2), performing candidate trajectory generation; (3), performing candidate trajectory evaluation; and (4), performing candidate trajectory anti-shake filtering. According to the path planning method, a structured road network data mode is adopted; environmental elements such as lane lines and road edges are defined; map elements are drawn on a coordinate system of a point cloud map; and the areas where the robot can pass through and can not pass through are constructed. The method has the advantages that the structure is light and simple, the occupied resources are small, the response is fast, the path planning of the outdoor robot under the large-range scene can be realized according to the road network data for the motion task of the given target point, and the performance bottleneck problem of the path planning under the outdoor large-range scene is effectively solved.

Description

technical field [0001] The invention relates to the field of robot navigation path planning methods. Background technique [0002] Path planning is a basic part of robot navigation. It is a method to solve how the robot finds the shortest path from the current position to the target position, and enables the robot to bypass obstacles without collision during the movement. Path planning can be divided into global path planning and local path planning according to the mastery of environmental information and the difference in response time. The global path planning constructs the shortest path from the starting position to the target position based on the known static environmental information. The optimal feature; the local path planning is based on the planned global path, generates local candidate trajectories that respond to the dynamic environment in real time, and selects the optimal trajectory according to the evaluation system. The former is a kind of pre-planning, an...

AI Technical Summary

Problems solved by technology

[0013] The A* algorithm gradually determines the next path node by comparing the heuristic function value F of the 8 adjacent nodes of the current path. When there are multiple minimum values, the A* algorithm cannot guarantee that the searched path is optimal.

For outdoor scenes, the range is often large. If you reduce the number of search points and improve efficiency by selecting h(n) that is greater than the actual distance, the optimal solution will not be obtained.

Images