Biogeography-Based Combinatorial Strategy for Efficient AUV Motion Planning and Task-Time Management

TL;DR

This paper presents a biogeography-based combinatorial motion planning framework for AUVs that maximizes task completion and safety in complex underwater environments, improving mission efficiency and reliability.

Contribution

It introduces a novel BBO-based route-path planning model that enhances AUV mission performance by optimizing task scheduling and safety in cluttered, time-varying fields.

Findings

The model achieves high task completion rates in simulations.

It demonstrates stable performance across different scenarios.

The approach is feasible for real-world AUV missions.

Abstract

Autonomous Underwater Vehicles (AUVs) are capable of spending long periods of time for carrying out various underwater missions and marine tasks. In this paper, a novel conflict-free motion planning framework is introduced to enhance underwater vehicle's mission performance by completing maximum number of highest priority tasks in a limited time through a large scale waypoint cluttered operating field, and ensuring safe deployment during the mission. The proposed combinatorial route-path planner model takes the advantages of the biogeography-based optimization (BBO) algorithm toward satisfying objectives of both higher-lower level motion planners and guarantees maximization of the mission productivity for a single vehicle operation. The performance of the model is investigated under different scenarios including the particular cost constraints in time-varying operating fields. To show the reliability of the proposed model, performance of each motion planner assessed separately and then statistical analysis is undertaken to evaluate the total performance of the entire model. The simulation results indicate the stability of the contributed model and its feasible application for real experiments.