Sim-to-Real Transfer and Robustness Evaluation of Reinforcement Learning Control with Integrated Perception on an ASV for Floating Waste Capture

2026-05-04

AI Summary

This work addresses the challenge of stably capturing floating debris with autonomous surface vehicles under complex hydrodynamics, external disturbances, and limited perceptual input. The authors propose an end-to-end solution that integrates polarimetric visual perception with a lightweight deep reinforcement learning controller. By employing two-stage simulation training augmented with a perception abstraction module and domain randomization, the approach enables seamless sim-to-real transfer. Temporal synchronization across multiple system modules ensures overall consistency. Evaluated under 14 distinct disturbance scenarios, the method achieves centimeter-level terminal accuracy, demonstrating strong control robustness. Successful search-and-capture missions were conducted in a real-world 450 m² water environment, significantly enhancing the feasibility and reproducibility of autonomous surface litter collection.

Abstract

Autonomous surface vessels for floating-waste removal operate under varying hydrodynamics, external disturbances, and challenging water-surface perception. We present a field-validated system that combines camera-based polarimetric perception with a lightweight DRL-based controller for floating-waste detection and capture. Camera detections are converted into water-surface target points and tracked by a controller trained entirely in simulation and deployed directly on a retrofitted ASV platform. Our main contribution is a sim-to-real testing methodology that combines a two-stage simulation protocol with a perception abstraction module designed to mimic real camera behavior, enabling reproducible field trials and explicit evaluation of the sim-to-real gap. We apply this framework in matched simulation and field experiments across 14 disturbance regimes to expose failure modes and evaluate robustness. The results show centimeter-level terminal accuracy and indicate robust control performance under the evaluated perturbation regimes. The main source of degradation is insufficient actuation-model fidelity. We also demonstrate the system in a search-and-capture application using real camera detections in real-world conditions over areas of up to $450~m^2$. The study distills practical lessons for reliable transfer, including improved actuation-model fidelity, targeted domain randomization, and careful management of latency and timestamps across modules, while highlighting remaining challenges.

Problem

• sim-to-real transfer
• reinforcement learning
• autonomous surface vessel
• robustness evaluation
• floating waste capture

Innovation

• sim-to-real transfer
• reinforcement learning control
• polarimetric perception
• autonomous surface vessel
• robustness evaluation