Reinforcement Learning Informed Evolutionary Search for Autonomous Systems Testing

TL;DR

This paper introduces RIGAA, a novel method combining reinforcement learning with evolutionary search to improve the efficiency and effectiveness of testing autonomous systems, demonstrated through maze and road topology case studies.

Contribution

The paper presents RIGAA, a new approach that integrates RL to guide evolutionary search, resulting in faster convergence and higher quality test scenarios for autonomous systems.

Findings

RIGAA converges faster to fitter solutions.

RIGAA produces more diverse test scenarios.

RIGAA outperforms existing tools like AmbieGen and Frenetic.

Abstract

Evolutionary search-based techniques are commonly used for testing autonomous robotic systems. However, these approaches often rely on computationally expensive simulator-based models for test scenario evaluation. To improve the computational efficiency of the search-based testing, we propose augmenting the evolutionary search (ES) with a reinforcement learning (RL) agent trained using surrogate rewards derived from domain knowledge. In our approach, known as RIGAA (Reinforcement learning Informed Genetic Algorithm for Autonomous systems testing), we first train an RL agent to learn useful constraints of the problem and then use it to produce a certain part of the initial population of the search algorithm. By incorporating an RL agent into the search process, we aim to guide the algorithm towards promising regions of the search space from the start, enabling more efficient exploration of the solution space. We evaluate RIGAA on two case studies: maze generation for an autonomous ant robot and road topology generation for an autonomous vehicle lane keeping assist system. In both case studies, RIGAA converges faster to fitter solutions and produces a better test suite (in terms of average test scenario fitness and diversity). RIGAA also outperforms the state-of-the-art tools for vehicle lane keeping assist system testing, such as AmbieGen and Frenetic.