Evaluating Robustness of Deep Reinforcement Learning for Autonomous Surface Vehicle Control in Field Tests
This work addresses the robustness challenge for deploying DRL-based controllers in autonomous surface vehicles, particularly for tasks like capturing floating waste, but it is incremental as it focuses on evaluation and benchmarking rather than introducing new methods.
The paper tackled the problem of evaluating the robustness of Deep Reinforcement Learning (DRL) for Autonomous Surface Vehicle (ASV) control in real-world conditions, specifically under external disturbances like asymmetric drag and off-center payload, and found that the DRL agent performed reliably despite significant disturbances, with performance degradation quantified and benchmarked against an MPC baseline.
Despite significant advancements in Deep Reinforcement Learning (DRL) for Autonomous Surface Vehicles (ASVs), their robustness in real-world conditions, particularly under external disturbances, remains insufficiently explored. In this paper, we evaluate the resilience of a DRL-based agent designed to capture floating waste under various perturbations. We train the agent using domain randomization and evaluate its performance in real-world field tests, assessing its ability to handle unexpected disturbances such as asymmetric drag and an off-center payload. We assess the agent's performance under these perturbations in both simulation and real-world experiments, quantifying performance degradation and benchmarking it against an MPC baseline. Results indicate that the DRL agent performs reliably despite significant disturbances. Along with the open-source release of our implementation, we provide insights into effective training strategies, real-world challenges, and practical considerations for deploying DRLbased ASV controllers.