Unknown space autonomous exploration planning method

Abstract

The invention provides an unknown space autonomous exploration planning method, and the method comprises the steps: obtaining the current positioning information of a robot to generate a three-dimensional point cloud map, taking the robot as a center to generate a Voronoi diagram, and carrying out the sampling based on the path center of the Voronoi diagram to generate Voronoi-RRT; using an RRT algorithm to find feasible paths from all boundary points of the Voronoi-RRT tree by taking the position of the robot as a starting point, calculating the exploration gain of each path, and taking the maximum exploration gain as an optimal path; using a path planning algorithm to execute dynamic obstacle avoidance to generate a collision-free candidate path, and when the path is shielded by a dynamic obstacle, planning the path to continue to move on other candidate paths; and using a DWA dynamic window algorithm to track the final path, and obtaining and issuing a speed instruction to a robot control platform; and when the robot is dead or the electric quantity of the robot is insufficient, calling the global planner, and pulling to the previously marked exploration space boundary or returning to the starting point. And rapid, safe and efficient underground unknown space autonomous exploration is realized.

Description

technical field [0001] The invention relates to the technical field of path planning, in particular to a method for autonomous exploration and planning of an unknown space. Background technique [0002] In recent years, with the rapid development of robot technology, there are more and more researches on autonomous mobile robots exploring environments that are not suitable for humans to live and work, such as mines and tunnels. Due to the complexity of the underground unknown environment, such as complex and deep terrain, the underdeveloped communication makes it impossible to directly control the robot remotely, and cannot use GPS for navigation. In such complex environments, autonomous mobile robots need to be highly autonomous, robust, reliable and adaptable to movement in complex environments. Autonomous exploration technology guides robots to move autonomously in unknown environments, rely on various sensors to sense unknown environments, and complete specific tasks su...

AI Technical Summary

Problems solved by technology

[0006] However, generating a topological map purely based on the Voronoi diagram, finding the frontier point in the topological map, and then using the Dijkstra algorithm to search for the shortest path to the best frontier point, this method of finding the frontier point based only on the original Voronoi diagram will be ignored in the tunnel environment. Some narrow branches with large exploration gains lead to incomplete exploration, and due to the multi-branch characteristics of the underground unknown space, this exploration method will randomly enter each branch when applied to a multi-branch environment, and the exploration efficiency is low

Images