A continuous action online learning control method and system for an autonomous vehicle

Abstract

The invention discloses a continuous action online learning control method and system for an automatic driving vehicle. The continuous action online learning control method comprises the following steps: encoding a perceptual image It through a deep encoding network to obtain an encoding state feature st; respectively inputting encoding state features st into actuators-actuators, wherein the evaluator models all adopt an evaluator network and an actuator network of a cerebellar model neural network, an action at is output through the actuator network, and an actuator is updated through the evaluator network; parameters of an evaluator model. According to the invention, a synthetic deep neural network feature coding technology and an enhanced learning principle are adopted; the learning control problem of a continuous action space is solved under high-dimensional state input; on-line learning control of a continuous action space under large-scale continuous state input can be realized,the learning period is shortened while the learning effect is ensured, the learning process can be quickly converged to obtain a control strategy with a good performance effect, and the data utilization rate is good.

Description

technical field [0001] The present invention relates to the field of environment perception of self-driving vehicles, in particular to a continuous action online learning control method and system for self-driving vehicles, which is used for combining deep neural network feature encoding technology and enhanced learning principles, and is oriented to high-dimensional state input. Solving the problem of learning control in continuous action spaces. Background technique [0002] With the development and innovation of artificial intelligence technology and the continuous growth of the automobile industry in domestic and foreign markets, as the product of the organic combination of intelligent driving technology and automobiles-intelligent driving vehicles have gradually become an important part of major automobile companies, high-tech companies, universities and research institutes. The focus of the institute's attention. Under the organic cooperation of environment perception...

AI Technical Summary

Problems solved by technology

In the adaptive heuristic evaluator algorithm, the learning of the evaluator adopts the traditional linear TD(λ) algorithm, which has the problem of insufficient data efficiency, and the selection of the learning and training step size needs to be carefully designed according to the specific problem, too large or too small Any step size value will have an adverse effect on the performance of the algorithm, prone to oscillation, and the convergence process becomes long or even divergent

Images