Mobile robot collision avoidance planning method based on deep reinforcement learning in static environment

Abstract

The invention belongs to the technical field of mobile robot navigation, and particularly relates to a mobile robot collision avoidance planning method based on deep reinforcement learning in a staticenvironment. The method comprises the following steps of: acquiring original data by using a laser range finder, taking the processed data as a state S of an A3C algorithm, constructing an A3C-LSTM neural network, taking the state S as network input, outputting corresponding parameters by the neural network through the A3C algorithm, and selecting actions executed by a mobile robot in each step through normal distribution by utilizing the parameters. According to the method, the environment does not need to be modeled, and the mobile robot successfully avoids obstacles in a complex static obstacle environment through a deep reinforcement learning algorithm. According to the method, a continuous action space model with bow turning constraint is designed, multi-thread asynchronous learningis adopted, and compared with a common deep reinforcement learning method, the learning training time is greatly prolonged, the sample correlation is reduced, the high utilization of the exploration space and the diversity of the exploration strategy are guaranteed, and the algorithm convergence, stability and obstacle avoidance success rate are improved.

Description

technical field [0001] The invention belongs to the technical field of mobile robot navigation, and in particular relates to a mobile robot collision avoidance planning method based on deep reinforcement learning in a static environment. Background technique [0002] The application of mobile robots has penetrated into all areas of life. In industrial production lines, robots can replace humans in heavy and repetitive tasks, improving production efficiency and liberating human labor. [0003] Obstacle avoidance is a key problem in robotics research in the process of multi-robots performing tasks. It is a dynamic, real-time, uncertain typical environment model. Furthermore, it requires the robot to quickly and independently adapt to changes in the environment. For obstacle avoidance problems, behavior-based response control methods and rule-based control strategies are often used. Both methods are simple, highly deterministic, and the robot responds better to the environme...

AI Technical Summary

Problems solved by technology

Generally speaking, traditional obstacle avoidance methods have relatively large limitations, especially for complex and dynamic unknown environments; while intelligent obstacle avoidance algorithms, especially the popular obstacle avoidance algorithms combined with deep learning and reinforcement learning in recent years, are suitable for continuous High-dimensional complex dynamic unknown environment has great advantages

Images