Adversarial Reinforcement Learning Framework for Benchmarking Collision Avoidance Mechanisms in Autonomous Vehicles

TL;DR

This paper introduces a deep reinforcement learning framework to benchmark autonomous vehicle collision avoidance systems by simulating adversarial scenarios, enabling robust comparison of their safety performance.

Contribution

It presents a novel adversarial reinforcement learning framework specifically designed for benchmarking collision avoidance mechanisms in autonomous vehicles.

Findings

The framework effectively identifies weaknesses in collision avoidance systems.

It enables comparison of different mechanisms under worst-case adversarial conditions.

Demonstrated through a case study comparing two collision avoidance methods.

Abstract

With the rapidly growing interest in autonomous navigation, the body of research on motion planning and collision avoidance techniques has enjoyed an accelerating rate of novel proposals and developments. However, the complexity of new techniques and their safety requirements render the bulk of current benchmarking frameworks inadequate, thus leaving the need for efficient comparison techniques unanswered. This work proposes a novel framework based on deep reinforcement learning for benchmarking the behavior of collision avoidance mechanisms under the worst-case scenario of dealing with an optimal adversarial agent, trained to drive the system into unsafe states. We describe the architecture and flow of this framework as a benchmarking solution, and demonstrate its efficacy via a practical case study of comparing the reliability of two collision avoidance mechanisms in response to intentional collision attempts.