Persistent AUV Operations Using a Robust Reactive Mission and Path Planning (RRMPP) Architecture

TL;DR

This paper presents a hierarchical, robust reactive architecture for autonomous underwater vehicles that integrates mission planning and environmental adaptation using evolutionary algorithms and online re-planning, enhancing operational reliability in uncertain underwater environments.

Contribution

It introduces a modular, hierarchical architecture combining mission and motion planning with evolutionary algorithms and online re-planning for AUVs in dynamic environments.

Findings

Demonstrates robustness in various simulated underwater scenarios.

Achieves efficient mission task-time management.

Ensures secure and reliable AUV deployment.

Abstract

Providing a higher level of decision autonomy and accompanying prompt changes of an uncertain environment is a true challenge of AUVs autonomous operations. The proceeding approach introduces a robust reactive structure that accommodates an AUV's mission planning, task-time management in a top level and incorporates environmental changes by a synchronic motion planning in a lower level. The proposed architecture is developed in a hierarchal modular format and a bunch of evolutionary algorithms are employed by each module to investigate the efficiency and robustness of the structure in different mission scenarios while water current data, uncertain static-mobile/motile obstacles, and vehicles Kino-dynamic constraints are taken into account. The motion planner is facilitated with online re-planning capability to refine the vehicle's trajectory based on local variations of the environment. A small computational load is devoted for re-planning procedure since the upper layer mission planner renders an efficient overview of the operation area that AUV should fly thru. Numerical simulations are carried out to investigate robustness and performance of the architecture in different situations of a real-world underwater environment. Analysis of the simulation results claims the remarkable capability of the proposed model in accurate mission task-time-threat management while guarantying a secure deployment during the mission.