Physical modeling-based robot obstacle avoidance path planning method

Abstract

The invention discloses a physical modeling-based robot obstacle avoidance path planning method, which comprises the following steps of: setting a gravitational field grid and a distance information grid of a robot working region to establish a robot double-grid information graph; based on the double-grid information graph, searching all feasible paths by using a directional ergodic method; calculating a comprehensive evaluation value of a gravity value and a distance value; and taking a path scheme corresponding to the maximum value as a robot optimal obstacle avoidance path planning scheme.By using the method, the defect that geometric attributes of moving objects and obstacles in robot path planning are not considered is overcome; during path searching after double grids are established by the method, robot obstacle avoidance path planning is performed according to the value of the double grids; and thus, the problems of the shortest path and moving safety are both taken into consideration, the efficiency of path planning is increased, and damage accidents which probably occur in path optimization are reduced.

Description

technical field [0001] The invention relates to robot obstacle avoidance path planning technology. The method performs robot obstacle avoidance path planning based on physical modeling, is suitable for optimal obstacle avoidance path planning of physical robots, and can also be used for virtual robot obstacle avoidance path planning. Background technique [0002] Robot obstacle avoidance path planning refers to the selection of a path from the starting point to the target point under the given environmental obstacle conditions, so that the robot can pass through all obstacles safely and without collision. The method of homework tasks is an important content in the research and application of robots. [0003] In 2001, Yu Jianli et al. published an article entitled A Neural Network-Based Robot Path Planning Algorithm in the Journal of Luoyang Institute of Technology, and proposed a neural network-based robot path planning method, which studied the shape and shape of obstacles....

AI Technical Summary

Problems solved by technology

These two methods belong to the method of path planning based on logical topological modeling. There is no buffer zone between the planned path and the robot, and the optimal path obtained from the planning result is often close to obstacles. Swing caused by vibration, etc. The path planned in this way is very dangerous for the movement of the robot. When the robot moves according to the planned path, if it swings, it may cause collisions between moving objects and obstacles beside the path, causing safety problems

[0004] The artificial potential field method is one of the few robot obstacle avoidance path planning methods that considers safety issues. The artificial potential field method is a virtual force method proposed by Khatib. It is applied to robot path planning is to move the robot in the surrounding environment. , designed as an abstract movement in an artificial gravitational field, the target point produces "gravity" on the mobile robot, and the obstacle produces "repulsion" on the mobile robot. Finally, the movement of the mobile robot is controlled by seeking the resultant force, which is planned by the potential field method The path is generally smooth and safe, but this method has a local optimum, that is, it is prone to local convergence problems; and when two obstacles are relatively close, according to the rules of the artificial potential field method, the channel between them Therefore, the path planning using the artificial potential field method at this time either fails because the obstacle is too close, or it has to go around the obstacle, resulting in the planned path being too long

In addition, the paths planned by the artificial potential field method are mostly irregular curves, which do not conform to the movement habits of robots.

Images