Mobile robot path planning method based on deep reinforcement learning

Abstract

The invention discloses a mobile robot path planning method based on deep reinforcement learning. The method comprises the steps of S1 determining state information according to a motion scene of a mobile robot; S2 initializing basic parameters of deep reinforcement learning, and pre-training a state value network weight through imitation learning; S3 carrying out forward transmission on the state information through a state value network, and using an epsilon-greedy strategy for guiding the robot to act; S4 obtaining rewards through a comprehensive reward function; S5 continuously updating the weight through the target value network, and updating related parameters; and S6 recording related data and a model which is finally trained in the training process to obtain an optimal navigation strategy of the robot. The method has a path planning scene aiming at the pedestrian environment in the public service field; and a state value network is designed by utilizing an artificial potential field method and an attention mechanism, so that the state information of the robot and a pedestrian is effectively expanded, and the state information interaction is promoted.

Description

technical field [0001] The present invention relates to a mobile robot path planning method in pedestrian environment based on deep reinforcement learning and artificial potential field method, combining data drive and physical model, using artificial potential field method and attention mechanism to design state value network, effectively expanding the The status information of robots and pedestrians promotes the interaction of status information; constructs a new potential field reward function based on the artificial potential field theory, fully considers the position and direction of the robot, and sets rewards in different spaces to balance each part, improving the reward feedback mechanism ; The robot's self-learning efficiency and motion safety are improved, and the time it takes to reach the target position is shorter, and the robot's action is more robust. Background technique [0002] With the rapid development of mobile robot technology, its application scenarios...

AI Technical Summary

Problems solved by technology

[0003] The traditional path planning method in the pedestrian environment is to use a mathematical model or a physical model to construct the interaction state between the robot and pedestrians, and then combine traditional search algorithms such as genetic algorithms to complete the path planning task. Parameters, the generalization ability for unfamiliar scenes is limited, and the navigation effect is not good; with the development of machine learning, data-driven methods have become a popular research direction for robot path planning in pedestrian environments. This method enables robots to have "learning ability". Dadi improves scene adaptability, but also faces problems such as low learning efficiency and difficulty in convergence

Images