Path planning method of motor crane robot

Abstract

The invention relates to a path planning method for automobile crane robots, in particular to an improved autonomous mobile-robot path planning method based on neural network energy function. The method comprises the following steps: a total energy function of a path is defined as the weighted sum of a collision penalty function and an energy function corresponding to the length part of the path; whether a starting point and a target point of the path are on the central axis of a obstacle is detected; if the starting point and the target point are both on the central axis of the obstacle, a path point is selected at random, and the path is planned after the coordinates of the path point are appropriately altered; whether the position of the path point is in the obstacle is detected in a path planning process; the position of the path point is moved by use of different dynamic motion equations according to different positions of the path point positioned inside or outside the obstacle, so as to enable the path point to move towards the direction of reducing the function value of the total energy function; and the shortest obstacle-avoidance path is finally planned.

Description

technical field [0001] The invention relates to the path planning of a car crane robot, in particular to an improved path planning algorithm for an autonomous mobile robot based on a neural network energy function. Background technique [0002] With the development of science and technology, truck crane robots will replace people to work in dangerous environments. Truck crane robots are a kind of autonomous mobile robots. ability to move. The artificial potential field method in the traditional path planning method of autonomous mobile robot path planning, its basic idea is to make the path avoid obstacles by finding the minimum value point of the energy function of the path point, but there is a local minimum value problem and it is not suitable to find the shortest path. "Artificial neural network" is an engineering system that simulates its structure and intelligent behavior based on the understanding of the human brain's organizational structure and operating mechanism...

AI Technical Summary

Problems solved by technology

However, there is a local minimum problem in this algorithm

The present invention proposes an improved path planning algorithm based on neural network energy function, which can solve the local minimum value problem of such path planning

Images