An autonomous mobile robot and its path navigation and path planning method and system

Abstract

The invention discloses an autonomous mobile robot and its path navigation and path planning method and system. The method includes a global planning process and a local planning process; details are as follows: acquiring positioning information and sensing information; generating a cost according to the positioning information and sensing information map, the cost map is used for A-star path search to obtain an initial navigation path; optimize the initial navigation path, sample the vertices of the optimized path, take out key points therein for interpolation, and obtain a global navigation path; The positioning information and the global navigation path generate a candidate path group; evaluate each candidate path according to the real-time perception information, obtain the optimal path, and output it; can quickly search for a near-optimal navigation path in a wide range, A series of points describing the global navigation path are obtained, and the points of the global navigation path are adjusted and selected to obtain a global navigation path that can meet the requirements of continuous curvature and no collision.

Description

technical field [0001] The invention belongs to the technical field of autonomous mobile robots, and in particular relates to an autonomous mobile robot and a path navigation and path planning method and system thereof. Background technique [0002] In unmanned systems, path planning is done in two stages, global planning and local planning. The global planning generates a navigation path from the starting point to the target point, while the local planning generates a collision-free driving path that satisfies the dynamic constraints of the robot under the guidance of the global planning path. In this way, the results of the global planning will have a huge impact on the local planning. [0003] The A-star algorithm is one of the most common and effective methods in global planning. However, there are still gaps between most of the results it gives and the optimal solution. In order to solve this problem, some researchers proposed a method of global path planning by back...

AI Technical Summary

Problems solved by technology

[0004] However, compared with the traditional A-star algorithm, the hybrid A-star algorithm requires a large time overhead and is not complete

However, the front-end result obtained by the A-star algorithm is farther away from the optimal solution in the solution space than the front-end result obtained by the hybrid A-star algorithm. It is difficult to achieve the ideal result by directly using conjugate gradient descent to optimize the results of the A-star algorithm.

Images