Method for planning global path of robot under risk source environment

Abstract

The invention discloses a method for planning the global path of a robot under risk source environment, which aims at providing a method for planning the global path capable of ensuring the robot to quickly accomplish tasks in high efficiency under the risk source environment; the method comprises the following steps of: (1) detecting and determining the information of the work environment of therobot, wherein the information comprises the starting point and the target point of the robot, the position and the shape of an obstruction, and the position of a risk source; (2) building the mode for the work environment of the robot; (3) defining the length of the path and the risk degree as two performance indexes for evaluating the good and bad of the path, wherein the two performance indexes are two target functions of the path planning problem; (4) globally optimizing the two target functions defined in the step (3) by utilizing improved multi-target particle group optimal algorithm soas to obtain a group of Pareto optimal path collection; (5) adopting a fuzzy membership function to simulate the preference of the decision maker on the task, and selecting an approving eclectic solution from the Pareto optimal path collection as the final moving path of the robot.

Description

technical field [0001] The invention relates to a global path planning method for a robot, in particular to a global path planning method for a robot in a dangerous source environment. Background technique [0002] The task of robot path planning is to find a collision-free path from the starting point to the goal point that meets certain performance indicators (such as path length, degree of danger, or walking time, etc.). A good path planning scheme is the prerequisite for ensuring that the robot can complete tasks efficiently. [0003] According to the robot's grasp of the environment, the existing planning methods can be divided into model-based global path planning methods (also known as static path planning) and local path planning methods based on detection information (also known as online path planning). The local path planning method has good real-time performance, but it cannot guarantee that the robot will eventually reach the target point. [0004] Study the g...

AI Technical Summary

Problems solved by technology

[0006] The traditional global planning method has the following shortcomings when dealing with this type of global path planning problem: on the one hand, due to the essential difference between hazards and obstacles, the traditional method of dealing with obstacles cannot be used to deal with hazards; on the other hand , most of the traditional methods use the path length as a single performance index to evaluate the path, and do not consider the influence of hazards on the path, that is, the performance index of the path's dangerous degree

After checking the relevant literature, there is currently no robot global path planning method suitable for hazardous environment

Images