Sim2Swim: Zero-Shot Velocity Control for Agile AUV Maneuvering in 3 Minutes

TL;DR

This paper introduces Sim2Swim, a novel zero-shot sim2real deep reinforcement learning controller that enables agile 6DOF maneuvering for AUVs within 3 minutes of training, eliminating the need for re-tuning.

Contribution

The paper presents the first general zero-shot sim2real DRL-based velocity controller for AUVs, capable of agile maneuvering without post-processing or tuning.

Findings

Successfully trained in 3 minutes using domain randomization

Validated in pool trials with diverse configurations

Achieved robust control for highly agile motions

Abstract

Holonomic autonomous underwater vehicles (AUVs) have the hardware ability for agile maneuvering in both translational and rotational degrees of freedom (DOFs). However, due to challenges inherent to underwater vehicles, such as complex hydrostatics and hydrodynamics, parametric uncertainties, and frequent changes in dynamics due to payload changes, control is challenging. Performance typically relies on carefully tuned controllers targeting unique platform configurations, and a need for re-tuning for deployment under varying payloads and hydrodynamic conditions. As a consequence, agile maneuvering with simultaneous tracking of time-varying references in both translational and rotational DOFs is rarely utilized in practice. To the best of our knowledge, this paper presents the first general zero-shot sim2real deep reinforcement learning-based (DRL) velocity controller enabling path following and agile 6DOF maneuvering with a training duration of just 3 minutes. Sim2Swim, the proposed approach, inspired by state-of-the-art DRL-based position control, leverages domain randomization and massively parallelized training to converge to field-deployable control policies for AUVs of variable characteristics without post-processing or tuning. Sim2Swim is extensively validated in pool trials for a variety of configurations, showcasing robust control for highly agile motions.