Local path planning method based on dynamic window method and suitable for Ackerman model robot

Abstract

The invention relates to a local path planning method based on a dynamic window method and suitable for an Ackerman model robot. The method comprises the steps of: firstly, acquiring the posture of the robot and the position of an obstacle according to a sensor carried by the robot, then calculating the coordinates of an obstacle avoidance starting point and coordinates and direction of a local target point, and determining a final speed space; meanwhile, segmenting the obstacle avoidance process of the robot to determine evaluation functions, judging the number of segments in segmented obstacle avoidance at present, and selecting the corresponding evaluation function for processing to obtain the speed corresponding to the minimum evaluation function value to serve as the optimal speed ofrobot operation, and repeatedly executing the obtained optimal speed, judging whether the robot reaches a local target point or not according to the current position of the robot, and if so, ending obstacle avoidance; conducting local path planning according to the size and position of the obstacle, the robot speed and the minimum turning radius, and promoting the robot to move in an optimal pathon the premise that the robot can avoid the obstacle and can return to a global path in a smooth direction after obstacle avoidance is finished.

Description

technical field [0001] The invention relates to the technical field of robot navigation, in particular to a local path planning method based on a dynamic window method and suitable for an Ackerman model robot. Background technique [0002] In recent years, with the development of artificial intelligence, robots have shown excellent characteristics in high-risk, repetitive, and complex tasks. However, in order to complete specific tasks, robots can actively avoid obstacles in complex environments. However, how to quickly avoid obstacles and find the optimal path to avoid obstacles has become one of the key factors affecting its performance. [0003] Robot path planning includes global path planning and local path planning. The global path planning is to plan a safe and feasible path in a known environment. The local path planning is to plan the path according to the local environmental information after detecting the working environment of the robot through sensors. Make the...

AI Technical Summary

Problems solved by technology

[0005] (1) If the robot starts avoiding obstacles at a position closer to the obstacle, the robot cannot successfully avoid the obstacle due to the minimum turning radius limit; Long, unable to bypass obstacles with the optimal path;

[0006] (2) At the end of obstacle avoidance, it cannot be ensured that the robot returns to the global path in a smooth direction. When the local path and the global path have a large angle, due to the limitation of the minimum turning radius, the robot needs to go around a larger arc to align the robot's orientation with the global path orientation

Images