A Safe and Efficient Self-evolving Algorithm for Decision-making and Control of Autonomous Driving Systems

TL;DR

This paper introduces a hybrid self-evolving algorithm for autonomous driving that enhances safety and efficiency by combining human driving analogy with mechanistic safety constraints, enabling rapid, collision-free learning in complex scenarios.

Contribution

It proposes a novel hybrid approach integrating analogy-based driving tendencies and constrained optimization to improve reinforcement learning for autonomous vehicles.

Findings

The method generates safe, reasonable actions in complex scenarios.

Training is collision-free and completed in under 10 minutes.

Significantly improves safety and efficiency over traditional reinforcement learning.

Abstract

Autonomous vehicles with a self-evolving ability are expected to cope with unknown scenarios in the real-world environment. Take advantage of trial and error mechanism, reinforcement learning is able to self evolve by learning the optimal policy, and it is particularly well suitable for solving decision-making problems. However, reinforcement learning suffers from safety issues and low learning efficiency, especially in the continuous action space. Therefore, the motivation of this paper is to address the above problem by proposing a hybrid Mechanism-Experience-Learning augmented approach. Specifically, to realize the efficient self-evolution, the driving tendency by analogy with human driving experience is proposed to reduce the search space of the autonomous driving problem, while the constrained optimization problem based on a mechanistic model is designed to ensure safety during the self-evolving process. Experimental results show that the proposed method is capable of generating safe and reasonable actions in various complex scenarios, improving the performance of the autonomous driving system. Compared to conventional reinforcement learning, the safety and efficiency of the proposed algorithm are greatly improved. The training process is collision-free, and the training time is equivalent to less than 10 minutes in the real world.