Supervised Visual Docking Network for Unmanned Surface Vehicles Using Auto-labeling in Real-world Water Environments

TL;DR

The paper addresses autonomous USV docking in real-world water environments where precise docking is hampered by labeling and calibration bottlenecks. It introduces an auto-labeling data collection pipeline and a Neural Dock Pose Estimator (NDPE) that predicts relative dock pose from monocular fisheye images without hand-crafted features or markers, enabling PBVS with a low-level PID controller. Real-world experiments show centimeter-level pose accuracy, robustness to distance and velocity variations, and a high docking success rate (18/20), validating the practical viability of the approach. The work offers a scalable path toward fully autonomous USV docking and points to future enhancements via adaptive learning, MPC, and reinforcement learning for even greater robustness.

Abstract

Unmanned Surface Vehicles (USVs) are increasingly applied to water operations such as environmental monitoring and river-map modeling. It faces a significant challenge in achieving precise autonomous docking at ports or stations, still relying on remote human control or external positioning systems for accuracy and safety which limits the full potential of human-out-of-loop deployment for USVs.This paper introduces a novel supervised learning pipeline with the auto-labeling technique for USVs autonomous visual docking. Firstly, we designed an auto-labeling data collection pipeline that appends relative pose and image pair to the dataset. This step does not require conventional manual labeling for supervised learning. Secondly, the Neural Dock Pose Estimator (NDPE) is proposed to achieve relative dock pose prediction without the need for hand-crafted feature engineering, camera calibration, and peripheral markers. Moreover, The NDPE can accurately predict the relative dock pose in real-world water environments, facilitating the implementation of Position-Based Visual Servo (PBVS) and low-level motion controllers for efficient and autonomous docking.Experiments show that the NDPE is robust to the disturbance of the distance and the USV velocity. The effectiveness of our proposed solution is tested and validated in real-world water environments, reflecting its capability to handle real-world autonomous docking tasks.

Figures (13)

• Figure 1: Illustration of a real-world autonomous docking task. The USV starts at the pre-docking area and then autonomously navigates to the dock.
• Figure 2: Block diagrams of visual-servo methods.
• Figure 3: Illustration of the coordinate frames.
• Figure 4: Overview of the framework. (a) The pipeline of data collection, augmentation and NPDE training. (b) The visual-servo architecture for PBVS-based autonomous docking task.
• Figure 5: Samples of logged data pairs.