Learning to Dock: A Simulation-based Study on Closing the Sim2Real Gap in Autonomous Underwater Docking
This addresses the problem of performance degradation in real-world AUV docking for marine robotics, but it is an incremental simulation-based study without real-world validation.
The study tackled the sim2real gap in autonomous underwater vehicle docking by training reinforcement learning controllers in simulation and evaluating them under realistic disturbances like varying payloads. The results provided insights into improving robustness through methods such as randomization and history-conditioned controllers.
Autonomous Underwater Vehicle (AUV) docking in dynamic and uncertain environments is a critical challenge for underwater robotics. Reinforcement learning is a promising method for developing robust controllers, but the disparity between training simulations and the real world, or the sim2real gap, often leads to a significant deterioration in performance. In this work, we perform a simulation study on reducing the sim2real gap in autonomous docking through training various controllers and then evaluating them under realistic disturbances. In particular, we focus on the real-world challenge of docking under different payloads that are potentially outside the original training distribution. We explore existing methods for improving robustness including randomization techniques and history-conditioned controllers. Our findings provide insights into mitigating the sim2real gap when training docking controllers. Furthermore, our work indicates areas of future research that may be beneficial to the marine robotics community.