Dynamic obstacle avoidance method and system for mobile robot and mobile robot

Abstract

The invention provides a dynamic obstacle avoidance method and system for a mobile robot and the mobile robot, and the method comprises the following steps: obtaining the position information of an obstacle, and converting the position information of the obstacle in a polar coordinate system into an inertial coordinate system; the minimum obstacle avoidance distance is calculated according to the minimum turning radius of the vehicle, and then an obstacle avoidance path is planned according to the minimum obstacle avoidance distance; and selecting an optimal obstacle avoidance path according to the current running angle and the obstacle avoidance path of the vehicle, and converting the optimal obstacle avoidance path into the running angle and speed of the vehicle in the next control period to realize dynamic obstacle avoidance. Based on the method, the invention further provides a dynamic obstacle avoidance system for the mobile robot and the mobile robot. The laser radar is used for detecting the surrounding environment of the mobile robot, based on a dynamic obstacle avoidance algorithm of local sampling, only obstacles appearing in front of the vehicle during running are detected, corresponding obstacle avoidance decisions are made according to the actual running parameters of the vehicle, and the safety and stability of dynamic obstacle avoidance of the mobile robot are improved.

Description

technical field [0001] The invention belongs to the technical field of mobile robots, and particularly relates to a dynamic obstacle avoidance method and system for a mobile robot and a mobile robot. Background technique [0002] Mobile robot path planning is usually carried out in two steps. First, global path planning is performed according to the known path and obstacle information, and then based on the global path, local dynamic obstacle avoidance is performed for obstacles that suddenly appear on the path. Since the location, shape, size and other information of the obstacles are known during the global path planning, the global path can be easily planned, while the local dynamic obstacle avoidance is easily affected by the environment, sensor types, and the computational performance of the controller. Due to the influence of other factors, it is difficult to achieve a safe and stable obstacle avoidance effect. [0003] At present, the commonly used dynamic obstacle a...

AI Technical Summary

Problems solved by technology

The BUG algorithm needs to go around along the edge of the obstacle when it encounters an obstacle. This method has high security, but its obstacle avoidance path is too long, which does not meet the requirements of actual use.

The dynamic window method predicts the trajectory of the robot based on the kinematic characteristics of the robot, which has high flexibility, but the obstacle avoidance effect is poor and the stability is low in complex environments.

The visual obstacle avoidance method based on deep learning can obtain rich obstacle information, but its calculation is too large, and it is difficult to run on the embedded processor with weaker performance.

Images