ORIGINAL RESEARCH article
Front. Robot. AI
Sec. Robotic Control Systems
Volume 12 - 2025 | doi: 10.3389/frobt.2025.1607676
Vision Driven Trailer Loading for Autonomous Surface Vehicles in Dynamic Environments
Provisionally accepted
- Purdue University, West Lafayette, United States
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
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.
Keywords: autonomous surface vehicle (ASV), Autonomous Trailer Loading, vision-based navigation, Finite state machine (FSM), object detection
Received: 07 Apr 2025; Accepted: 18 Aug 2025.
Copyright: © 2025 Li, Chavez-Galaviz and Mahmoudian. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Nina Mahmoudian, Purdue University, West Lafayette, United States
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.