Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

ATLS: Automated Trailer Loading for Surface Vessels

Amer Abughaida, Meet Gandhi, Jun Heo, Vaishnav Tadiparthi, Yosuke Sakamoto, Joohyun Woo, Sangjae Bae

TL;DR

The study tackles automated trailer loading for surface vessels in wind-affected environments by developing a complete pipeline that fuses localization, system identification, and trajectory optimization. It leverages a wind-augmented 3DOF dynamic model, identifies hull parameters from maneuvers, and uses a Dubin's-path reference with nonlinear programming to generate feedforward trajectories, augmented by extensions such as an extended docking point, a floating reference point, soft docking-angle constraints, and a bail mechanism. Demonstrations on a commercial pontoon (Premier Intrigue) in Lake Belleville, MI, show an 80% success rate across 40 trials, with localization accuracy achieving approximately 0.58 m longitudinal and 0.26 m lateral errors, and a heading error around 2.3° within 23 m of the trailer; wind disturbances and perception noise remain primary sources of failure. The approach highlights practical potential for autonomous trailer loading in coastal and harbor environments, while outlining concrete directions for incorporating feedback control and handling dynamic obstacles in future work.

Abstract

Automated docking technologies of marine boats have been enlightened by an increasing number of literature. This paper contributes to the literature by proposing a mathematical framework that automates "trailer loading" in the presence of wind disturbances, which is unexplored despite its importance to boat owners. The comprehensive pipeline of localization, system identification, and trajectory optimization is structured, followed by several techniques to improve performance reliability. The performance of the proposed method was demonstrated with a commercial pontoon boat in Michigan, in 2023, securing a success rate of 80\% in the presence of perception errors and wind disturbance. This result indicates the strong potential of the proposed pipeline, effectively accommodating the wind effect.

ATLS: Automated Trailer Loading for Surface Vessels

TL;DR

The study tackles automated trailer loading for surface vessels in wind-affected environments by developing a complete pipeline that fuses localization, system identification, and trajectory optimization. It leverages a wind-augmented 3DOF dynamic model, identifies hull parameters from maneuvers, and uses a Dubin's-path reference with nonlinear programming to generate feedforward trajectories, augmented by extensions such as an extended docking point, a floating reference point, soft docking-angle constraints, and a bail mechanism. Demonstrations on a commercial pontoon (Premier Intrigue) in Lake Belleville, MI, show an 80% success rate across 40 trials, with localization accuracy achieving approximately 0.58 m longitudinal and 0.26 m lateral errors, and a heading error around 2.3° within 23 m of the trailer; wind disturbances and perception noise remain primary sources of failure. The approach highlights practical potential for autonomous trailer loading in coastal and harbor environments, while outlining concrete directions for incorporating feedback control and handling dynamic obstacles in future work.

Abstract

Automated docking technologies of marine boats have been enlightened by an increasing number of literature. This paper contributes to the literature by proposing a mathematical framework that automates "trailer loading" in the presence of wind disturbances, which is unexplored despite its importance to boat owners. The comprehensive pipeline of localization, system identification, and trajectory optimization is structured, followed by several techniques to improve performance reliability. The performance of the proposed method was demonstrated with a commercial pontoon boat in Michigan, in 2023, securing a success rate of 80\% in the presence of perception errors and wind disturbance. This result indicates the strong potential of the proposed pipeline, effectively accommodating the wind effect.
Paper Structure (27 sections, 11 equations, 9 figures, 2 tables)

This paper contains 27 sections, 11 equations, 9 figures, 2 tables.

Table of Contents

  1. INTRODUCTION
  2. Related works
  3. Problem Settings
  4. Target scenario
  5. System Pipeline
  6. System Dynamics and Estimation
  7. Reference Path
  8. Localization System
  9. Target level of Accuracy
  10. Applied Methods to Enhance Accuracy
  11. Resulting Sensor Configuration
  12. Performance
  13. Trajectory Optimization
  14. Objective
  15. Constraints
  16. ...and 12 more sections

Figures (9)

  • Figure 1: Motivation scenario: automatic loading of a pontoon boat to a trailer.
  • Figure 2: Test boat: Premier Intrigue of 2022 model year. Specifications are with overall length of 8.36 [m], beam length of 3.1 [m], and dry weight of 3,500 [lb].
  • Figure 3: System pipeline, consisting of localization, reference path generation, and trajectory planning. There exists an intermittent condition to necessitate a bail strategy (in case docking is not feasible).
  • Figure 4: The camera installed at the bow of the pontoon. Specifications: 2880x1860 of resolution, 6.9 [FPS], 8 [mm] of focal length, 58.4 [deg] of FOV.
  • Figure 5: Performance of the localization based on the camera images against RTK. Top left: distance of the goal position from the ego vehicle. Circles represent some examples of detection at distance (23, 36, 60 [m]). Top right: longitudinal target distance and its error in an ego-centric frame. Bottom left: lateral target distance and its error in the ego-centric frame. Bottom right: relative heading of the trailer in the ego-centric frame and its error. Note that the camera starts to detect within 60 [m] from the tag, which occurs around 45 [sec] in the time axis.
  • ...and 4 more figures

Theorems & Definitions (3)

  • Remark 1
  • Remark 2
  • Remark 3