Coverage Path Planning for Autonomous Sailboats in Inhomogeneous and Time-Varying Oceans: A Spatiotemporal Optimization Approach

TL;DR

This work tackles coverage path planning for autonomous sailboats in inhomogeneous, time-varying oceans where wind and current fields drive anisotropic feasibility and partial accessibility. It proposes a spatiotemporal CPP framework that (i) imposes morphological constraints in the spatial domain to maintain compact, connected coverage and (ii) uses forecast-aware look-ahead planning via phase-wise Monte Carlo Tree Search with a horizon $K\Delta t$ and a discrete action set. The main contributions are: (a) the first dedicated solution for sailboats under coupled spatiotemporal constraints, (b) a geometry-based regularity and a rollout reward that balance immediate efficiency with long-horizon feasibility, and (c) validation against a boustrophedon baseline in randomized scenarios showing faster convergence to a target coverage threshold $\eta$ while maintaining robustness to forecast uncertainty. The framework enables efficient long-duration ocean observation and provides a foundation for cooperative multi-sailboat deployments in realistic marine environments.

Abstract

Autonomous sailboats are well suited for long-duration ocean observation due to their wind-driven endurance. However, their performance is highly anisotropic and strongly influenced by inhomogeneous and time-varying wind and current fields, limiting the effectiveness of existing coverage methods such as boustrophedon sweeping. Planning under these environmental and maneuvering constraints remains underexplored. This paper presents a spatiotemporal coverage path planning framework tailored to autonomous sailboats, combining (1) topology-based morphological constraints in the spatial domain to promote compact and continuous coverage, and (2) forecast-aware look-ahead planning in the temporal domain to anticipate environmental evolution and enable foresighted decision-making. Simulations conducted under stochastic inhomogeneous and time-varying ocean environments, including scenarios with partial directional accessibility, demonstrate that the proposed method generates efficient and feasible coverage paths where traditional strategies often fail. To the best of our knowledge, this study provides the first dedicated solution to the coverage path planning problem for autonomous sailboats operating in inhomogeneous and time-varying ocean environments, establishing a foundation for future cooperative multi-sailboat coverage.

Figures (11)

• Figure 1: Representative categories of classical CPP strategies.
• Figure 3: Illustration of action definitions in autonomous sailboat CPP. The segmented markers indicate that the physical properties of each path segment are computed based on the environmental field of the corresponding grid.
• Figure 4: Key parameters in regularity term
• Figure 5: Detailed coverage process of S42 (Stage 1--3). The baseline method stalls when facing temporary inaccessibility (highlighted in black box), while both proposed variants maintain effective coverage. $K{=}0$ and $K{=}1$ exhibit similar results due to shared parameters in early stages.
• Figure 6: Detailed coverage process of S42 (Stage 4--6). In stages without infeasible regions, the baseline maintains stable and efficient coverage. $K{=}0$ heads upward in Stage 5 but is hindered by adverse currents in Stage 6. In contrast, $K{=}1$ anticipates favorable conditions and achieves more efficient coverage in the lower-right.