Toward Time-Optimal Trajectory Planning for Autonomous Ship Maneuvering in Close-Range Encounters

Abstract

Ship intelligence has been a hot topic in recent years. How to achieve autonomous maneuvers in a complex marine environment in a safe, efficient, and low-cost manner is a fundamental task that ocean engineers face. This paper presents a two-stage trajectory planning scheme to address the minimumtime maneuvering problem in close-range encounters. The scheme is robust and versatile, as it can deal with the complex spatial variability, such as sea current, state constraints, marine traffic, and physical constraints, of close-range maneuvering. In the first stage, a directed graph with variable length is generated according to the sea current distribution. A wavefront search is applied on the graph to explore the reachability, the cost of state constraints, and the risk of collision. After a discrete solution has been found, the second stage involves searching for a smooth solution. A Bézier curve based parameter optimization approach is proposed to get rid of limited moving directions in the directed graph and explore around the discrete path. The result will be a near-optimal, smooth path. The proposed scheme has been tested to solve the Zermelo's ship steering problem and several other close-range maneuvering problems. The results demonstrate that the scheme is efficient in generating smoothed minimum-time trajectories for surface vessels when maneuvering in close-range encounters.

Deep Learning for Efficient and Optimal Motion Planning for AUVs with Disturbances

“…The results obtained are in Table 2 and Figure 5. First, in Table 2, we represent both the error e following (18) and the proportion of trajectories in which the DGM provides a lower cost than the baseline, i.e., the improvement proportion of trajectories. Note that, in both metrics, the DGM provides considerably better results than the baseline: first, the error is always negative, which means that the DGM is better than the baseline, and then, the improvement proportion of DGM is of 87% for all disturbances tested.…”

“…However, they use coverage path planning, which consists of solving the optimal control problem in a discrete environment, and then check whether the discrete solution can be applied to a continuous system. A similar procedure is described in [ 18 ], where the authors first find a discrete solution and then interpolate it. In contrast to these works, which rely on discretization of the states, we solve the problem in the continuous domain, and also use a different target function, as we intend to minimize the time to reach a certain target.…”

Interference Identification for Time-Varying Polyhedra

“…There has also been work done in detecting when collisions will happen between two ships for the purposes of autonomous ship routing [21], [16].…”

An Uncertainty-Aware Hybrid Approach for Sea State Estimation Using Ship Motion Responses

“…These ships have the potential to reduce human-based errors, lower fuel consumption, and extend the operational window [2]. Efforts have been made in the recent years to develop modern control [3] and path planning algorithm [4] for marine vehicles. Nonetheless, these autonomous systems must be able to process the current environmental conditions for safe and effective decision making.…”