Indoor environment robot exploration method based on heuristic bias sampling

Abstract

The invention discloses an indoor environment robot exploration method based on heuristic bias sampling. The indoor environment robot exploration method comprises the steps: A, performing initialization; B, performing positioning and mapping; C, extracting boundary points by using the two fast growth random trees, and recording the boundary points as RRT boundary points; extracting boundary points in the priori area through an offset sampling fast search random tree algorithm and recording as room boundary points; eliminating invalid boundary points in the RRT boundary points and the room boundary points; D, the robot preferentially selecting the room boundary point with the maximum profit value as a target point to explore, and preferentially selecting the RRT boundary point with the maximum profit value as the target point to explore after all the room boundary points are explored; E, guiding the robot to navigate to the target point and updating the map; F, when no boundary point is detected in the prior area, destroying the prior area; and G, circulating the steps A-F until the whole environment exploration is completed. According to the method, the backtracking phenomenon in the exploration process can be effectively reduced, and the exploration efficiency is improved.

Description

technical field [0001] The invention relates to the technical field of robots, in particular to an indoor environment robot exploration method based on heuristic bias sampling. Background technique [0002] With the development of computer software and hardware technology and the breakthrough of artificial intelligence technology, the research of service mobile robots has achieved remarkable results, and the application scenarios and service modes of intelligent public service robots have continued to expand, driving the rapid growth of my country's service robot market. Mobile robot autonomous exploration refers to the process of building a complete environment map by moving in a new environment without any prior knowledge. [0003] At present, the mainstream autonomous exploration algorithm is based on the boundary point exploration method. The boundary divides the detection space into known areas and unknown areas. Guiding the robot to explore the unknown area can gradual...

AI Technical Summary

Problems solved by technology

For example, when a robot explores a room area, if the profit value of the boundary points outside the room is large, the robot turns to explore outside the room, and then circles back to complete the room area exploration, which produces a backtracking phenomenon; secondly, due to the RRT algorithm Due to its own randomness, when extracting the boundary points, it is often impossible to extract the boundary points of the robot's forward area in time, so the robot will also choose another area to explore and then go back to explore.

Leading to the problem of slow and inefficient robot exploration

Images