OCEAN ENGINEERING, vol.310, 2024 (SCI-Expanded)
This paper presents a novel feedback motion planning and control framework tailored for unmanned surface vehicles (USVs), validated through experiments on a physical USV platform. The framework utilizes sparse random neighborhood trees and a velocity command generator based on partial feedback linearization. Compared to existing approaches, the methodology introduces a sequential composition of elliptical regions and associated nonlinear feedback control algorithms (funnels) to enhance sparsity and computational efficiency. The approach comprises two primary stages: neighborhood tree generation and feedback motion control. In the tree generation stage, a sparse, collision-free, connected tree structure is constructed within the environment using elliptical regions (funnels). Subsequently, each funnel is assigned a dedicated control policy to ensure safe vehicle operation and guide it toward its goal position. To validate the effectiveness of the proposed approach, comprehensive experiments were conducted involving both simulation studies and physical implementations on an autonomous surface vehicle platform. A significant contribution of this work is the development and hardware validation of a partial feedback linearization-based controller, which ensures robust navigation of the vehicle within elliptical regions. The proposed trajectory-free, sampling-based feedback motion planning scheme is compatible with 2D polygonal map representations, enabling practical deployment in real-world environments for USVs. Moreover, the use of elliptical funnels enhances tree sparsity compared to circular funnels, thereby improving computational efficiency, reducing mode changes, and decreasing the total operation duration.