Mobile robot path planning method based on improved PRM and artificial potential field

Abstract

The invention discloses a mobile robot path planning method based on an improved PRM and an artificial potential field, and relates to the technical field of robot path planning, and the method comprises the following steps: S1, carrying out the learning of global environment information through the PRM, carrying out the random point scattering in an undirected graph, and adding the elliptic constraint to a sampling point; s2, performing path search on the feasible nodes by the PRM, calculating an optimal path, and exporting path nodes; s3, constructing an artificial potential field, wherein the artificial potential field is formed by superposing a gravitational potential field and a repulsive potential field; the method is simple and easy to implement, the advantages of complete probability and good convergence of the PRM algorithm and small calculation, high real-time performance and the like of the APF algorithm are combined at the same time, the local minimum problem and the target unreachable problem of the artificial potential field method are solved, and by adding elliptic constraint to the PRM, the target point can be accurately determined. Sampling points of the PRM are more dense under the same sampling point, path planning time is shorter, and the requirement for dynamic obstacle avoidance of the mobile robot is met.

Description

technical field [0001] The invention relates to the technical field of robot path planning, in particular to a mobile robot path planning method based on improved PRM and artificial potential field. Background technique [0002] Under the boom of artificial intelligence, mobile robot technology has developed rapidly. Among them, autonomous navigation technology of mobile robots is an important research direction in the field of mobile robots, and path planning is one of the core contents of autonomous navigation. At present, mobile robot path planning The main research direction is real-time obstacle avoidance in dynamic uncertain environments. Dynamic uncertain environments usually include moving obstacles with uncertain motion trajectories and stationary obstacles with unknown positions. The commonly used path planning algorithms mainly include: Probabilistic Roadmaps Method (Probabilistic Roadmaps Method). , PRM), ant colony algorithm, genetic algorithm and artificial pot...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the deficiencies mentioned in the above background technology, the object of the present invention is to provide a mobile robot path planning method based on improved PRM and artificial potential field. The method of the present invention is simple and easy to implement, and combines the probabilistic completeness and convergence It has the advantages of good performance, small calculation and high real-time performance of the APF algorithm, which solves the local minimum problem and target unreachable problem of the artificial potential field method, and by adding ellipse constraints to the PRM, it ensures that the sampling points of the PRM are more dense at the same sampling point , less time to plan the path, and meet the requirements of dynamic obstacle avoidance for mobile robots

Images