Current Effect-eliminated Optimal Target Assignment and Motion Planning for a Multi-UUV System

TL;DR

This work tackles the challenge of performing joint target assignment and motion planning for a small team of unmanned underwater vehicles in the presence of ocean currents. It proposes CBNNTAP, a BINN-based framework that combines a Hopfield-type neural network for path planning, a fast target-assignment matrix derived from pre-optimized path lengths, and a current-elimination component using an adjustment velocity vector to keep vehicles on their optimal trajectories. The approach demonstrates robust performance against both static and dynamic currents in 2D and 3D simulations, outperforming a baseline BINN path planner by maintaining collision-free, shortest-path trajectories under adverse flow. The results suggest significant practical impact for real-time, cooperative UUV missions in uncertain underwater environments where currents can otherwise degrade coordination and efficiency.

Abstract

The paper presents an innovative approach (CBNNTAP) that addresses the complexities and challenges introduced by ocean currents when optimizing target assignment and motion planning for a multi-unmanned underwater vehicle (UUV) system. The core of the proposed algorithm involves the integration of several key components. Firstly, it incorporates a bio-inspired neural network-based (BINN) approach which predicts the most efficient paths for individual UUVs while simultaneously ensuring collision avoidance among the vehicles. Secondly, an efficient target assignment component is integrated by considering the path distances determined by the BINN algorithm. In addition, a critical innovation within the CBNNTAP algorithm is its capacity to address the disruptive effects of ocean currents, where an adjustment component is seamlessly integrated to counteract the deviations caused by these currents, which enhances the accuracy of both motion planning and target assignment for the UUVs. The effectiveness of the CBNNTAP algorithm is demonstrated through comprehensive simulation results and the outcomes underscore the superiority of the developed algorithm in nullifying the effects of static and dynamic ocean currents in 2D and 3D scenarios.

Figures (22)

• Figure : Fig. 1. 2D grid-based map modeling for the system of multiple UUVs and targets in the underwater environment
• Figure : Fig. 2. The 2D bio-inspired neural network
• Figure : Fig. 3. Schematic of the CBNNTAP method designed for a multi-UUV system
• Figure : Fig. 4. Pre-optimal path planning for a multi-UUV system
• Figure : Fig. 5. Elimination of the ocean current effect by introducing a third party vector $\mathbf{v_{\rm adj}}$ on a 2D map.