Urban road automatic parking method and system based on reinforcement learning

Abstract

The invention discloses an urban road automatic parking method based on reinforcement learning, and the method comprises the steps: S1, a parking space line recognition process, S2, a state input process, and S3, a parking decision control process, and the parking decision control process comprises the steps: S31, enabling Actor to predict a current state value through employing a calculated state value in an experience pool and a Critic network, and carrying out the updating of a neural network, taking the M mean square error as a Loss function, training the neural network, and obtaining an updated target neural network; and S32, inputting the state input vector into the updated target neural network corresponding to the parking action strategy pi *, outputting the obtained steering angle and acceleration of the vehicle, and controlling the movement of the vehicle.

Description

technical field [0001] The invention relates to the technical field of automatic parking, in particular to a method and system for automatic parking on urban roads based on reinforcement learning. Background technique [0002] The current automatic parking technologies in the industry are all based on trajectory planning, trajectory tracking, or parking space line recognition. However, with the increase of vehicles on urban roads, the increasingly complex urban road conditions, and the uneven driving level of drivers, the parking operation of many vehicles has not been guaranteed to be standardized and safe. When many vehicles are parked, due to the above-mentioned situation, or the imperfect road conditions of urban traffic facilities, the parking action is not strictly followed by the parking space line. If the self-driving vehicle still performs the automatic parking operation after detecting a parking space that meets the requirements according to the standardized parki...

AI Technical Summary

Problems solved by technology

If the self-driving vehicle still performs the automatic parking operation after detecting the parking space that meets the requirements according to the standardized parking space recognition method, it will cause a large number of parking spaces that can be parked but are not standardized enough to be wasted, and it will also cause the driver waste of time

For non-standard parking behaviors, the current automatic parking methods in the industry cannot be safe and efficient.

Images