Obstacle avoidance method, device and equipment for mobile robot and storage medium

The invention discloses a mobile robot obstacle avoidance method, device and equipment and a storage medium, and relates to the technical field of robot control, and the method comprises the steps: respectively inputting dynamic obstacle state information and robot state information at a current moment into a corresponding full-connection network for coding to obtain environment features; inputting the environment characteristics into a recurrent neural network constructed based on a gated recurrent neural network and a probabilistic neural network so as to model the current dynamic environment, and determining whether the current environment characterization condition meets a preset condition based on the probability output by the probabilistic neural network; the probabilistic neural network is a network constructed based on a probability activation function; if yes, generating a corresponding Q value and an obstacle avoidance action strategy based on the environment intermediate characteristics output by t