Evaluating Robustness of Deep Reinforcement Learning for Autonomous Surface Vehicle Control in Field Tests
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910988308054016 |
|---|---|
| author | Batista, Luis F. W. Aravecchia, Stéphanie Hutchinson, Seth Pradalier, Cédric |
| author_facet | Batista, Luis F. W. Aravecchia, Stéphanie Hutchinson, Seth Pradalier, Cédric |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_10033 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating Robustness of Deep Reinforcement Learning for Autonomous Surface Vehicle Control in Field Tests Batista, Luis F. W. Aravecchia, Stéphanie Hutchinson, Seth Pradalier, Cédric Robotics Machine Learning 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. |
| title | Evaluating Robustness of Deep Reinforcement Learning for Autonomous Surface Vehicle Control in Field Tests |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2505.10033 |