Answers are grounded in this paper and cite their sources.
Rapidly-exploring Random Trees (RRT) and their variants, such as RRT*, have been widely applied to ship path planning in complex waterways. However, these methods were originally developed primarily for ground robots, and their planning objective usually emphasizes geometric path minimization. As a result, they cannot adequately capture the directional effects of currents and wind on energy-related route cost and navigational safety. Therefore, in complex navigable waters, a geometrically optimal path does not necessarily correspond to an environmentally favorable one. To address this issue, this paper proposes Multi-Dimensional Information-Enhanced IRRT* (MI-IRRT*), an Informed-RRT*-based framework integrating environmental information with AIS-derived navigation structure. Euclidean edge length is retained as the geometric base term, while optimization uses a composite, anisotropic, and directed edge cost derived from the tangential and normal responses of current and wind vectors together with adaptive shoreline-clearance constraints. This cost consistently governs parent selection and tree rewiring, allowing environmental information to shape the search-tree topology during construction. AIS-derived topological priors guide long-range search, while flow-aware local smoothing improves continuity near navigation keypoints. Comparative results show that, under the adopted relative energy-index measure, MI-IRRT* reduces the total energy index by 7.06% relative to conventional IRRT*, with a statistically significant difference ( p < 0.001 ).
No takes yet. Share an insight, caveat, or question.
Dang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: