A Safe Self-evolution Algorithm for Autonomous Driving Based on Data-Driven Risk Quantification Model

TL;DR

This paper introduces a data-driven risk quantification model with attention mechanisms to enable safe self-evolution in autonomous driving systems, balancing safety and learning efficiency in complex environments.

Contribution

It proposes a novel risk quantification model and a safety-evolutionary decision-control algorithm with adjustable safety limits for autonomous driving.

Findings

Effective in complex scenarios with safe and reasonable actions

Maintains safety without compromising learning potential

Validated through simulation and real-vehicle experiments

Abstract

Autonomous driving systems with self-evolution capabilities have the potential to independently evolve in complex and open environments, allowing to handle more unknown scenarios. However, as a result of the safety-performance trade-off mechanism of evolutionary algorithms, it is difficult to ensure safe exploration without sacrificing the improvement ability. This problem is especially prominent in dynamic traffic scenarios. Therefore, this paper proposes a safe self-evolution algorithm for autonomous driving based on data-driven risk quantification model. Specifically, a risk quantification model based on the attention mechanism is proposed by modeling the way humans perceive risks during driving, with the idea of achieving safety situation estimation of the surrounding environment through a data-driven approach. To prevent the impact of over-conservative safety guarding policies on the self-evolution capability of the algorithm, a safety-evolutionary decision-control integration algorithm with adjustable safety limits is proposed, and the proposed risk quantization model is integrated into it. Simulation and real-vehicle experiments results illustrate the effectiveness of the proposed method. The results show that the proposed algorithm can generate safe and reasonable actions in a variety of complex scenarios and guarantee safety without losing the evolutionary potential of learning-based autonomous driving systems.