A method of distance map reconstruction and skip path planning based on anti-collision radius

Abstract

The invention discloses a distance map reconstruction and jump point path planning method based on anti-collision radius, comprising: constructing a distance map based on anti-collision radius on a two-dimensional plane eight-connected grid path planning map and initializing it; The distance matrix of the distance map is used as the search space for path planning of the planning subject. When the grid state in the search space changes, the distance map is dynamically updated according to the wave front of the grid state change; When the search space expands the grid and identifies the jump point, the collision detection is performed according to the obstacle distance information carried by the distance map and the anti-collision radius of the planning subject. It is used to solve the problems of computational resource consumption caused by transitional update of redundant areas and the low efficiency of task map dynamic reconstruction and path planning in the process of integration with DM due to the self-planning of the JPS method, so as to realize efficient dynamic reconstruction and improvement of task maps Efficiency of path planning.

Description

technical field [0001] The invention belongs to the technical field of artificial intelligence, and in particular relates to a distance map reconstruction and skip path planning method based on anti-collision radius. Background technique [0002] In the field of artificial intelligence, robotics and computer game intelligence are regarded as comprehensive fields that model human perception, planning, decision-making, and action capabilities in complex environments. In recent years, various types of robots have been widely used in production and life, and the academic and industrial circles have gradually paid more attention to computer game intelligence. Typical examples include the StarCraft game AI developed by the DeepMind team and the Dota game AI developed by OpenAI. As the basis of all aspects of robot and game non-player characters (NPC, Non-Player Characters), the shortest path planning technology based on uniform grids (uniform grids) map has been The industry's op...

AI Technical Summary

Problems solved by technology

However, the existing DM generation algorithm does not consider the anti-collision radius of the planning subject when updating, and the update process will always cover the largest area that the wavefront can govern, which is when the proportion of obstacles is small and the spatial distribution of obstacles is sparse. In the large terrain space, it leads to unacceptable computing overhead, and for the non-collision path planning task that meets a certain anti-collision radius, this DM update method has a large number of redundant detections, which is the reason for the robustness of DM in practical applications. and real-time performance cannot meet the requirements in a specific task space

Images