AUTHOR=Li Jianwen , Chavez-Galaviz Jalil , Mahmoudian Nina 

TITLE=Vision driven trailer loading for autonomous surface vehicles in dynamic environments

JOURNAL=Frontiers in Robotics and AI

VOLUME=Volume 12 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/robotics-and-ai/articles/10.3389/frobt.2025.1607676

DOI=10.3389/frobt.2025.1607676

ISSN=2296-9144

ABSTRACT=Automated docking technologies for marine vessels have advanced significantly, yet trailer loading, a critical and routine task for autonomous surface vehicles (ASVs), remains largely underexplored. This paper presents a novel, vision-based framework for autonomous trailer loading that operates without GPS, making it adaptable to dynamic and unstructured environments. The proposed method integrates real-time computer vision with a finite state machine (FSM) control strategy to detect, approach, and align the ASV with the trailer using visual cues such as LED panels and bunk boards. A realistic simulation environment, modeled after real-world conditions and incorporating wave disturbances, was developed to validate the approach and is available1. Experimental results using the WAM-V 16 ASV in Gazebo demonstrated a 100% success rate under calm to medium wave disturbances and a 90% success rate under high wave conditions. These findings highlight the robustness and adaptability of the vision-driven system, offering a promising solution for fully autonomous trailer loading in GPS-denied scenarios.