[论文解读] Development of an Autonomous Reactive Mission Scheduling and Path Planning (ARMSP) Architecture Using Evolutionary Algorithms for AUV Operation in a Sever Ocean Environment.

Somaiyeh Mahmoud Zadeh, David Powers+1 more|arXiv (Cornell University)|May 6, 2016

Robotic Path Planning Algorithms参考文献 48被引用 4

一句话总结

本文提出了一种用于恶劣海洋环境中自主AUV的自主反应式任务调度与路径规划（ARMSP）架构，通过多层进化算法实现实时任务自适应。该系统集成了动态避障、时变威胁管理以及低计算开销的在线重规划，在多种元启发式算法下表现出稳定性能。

ABSTRACT

Providing a higher level of decision autonomy is a true challenge in development of today AUVs and promotes a single vehicle to accomplish multiple tasks in a single mission as well as accompanying prompt changes of a turbulent and highly uncertain environment, which has not been completely attained yet. The proceeding approach builds on recent researches toward constructing a comprehensive structure for AUV mission planning, routing, task-time managing and synchronic online motion planning adaptive to sudden changes of the time variant environment. Respectively, an Autonomous Reactive Mission Scheduling and Path Planning (ARMSP) architecture is constructed in this paper and a bunch of evolutionary algorithms are employed by different layers of the proposed control architecture to investigate the efficiency of the structure toward handling addressed objectives and prove stability of its performance in real-time mission task-time-threat management regardless of the applied metaheuristic algorithm. Static current map data, uncertain dynamic-static obstacles, vehicles Kino-dynamic constraints are taken into account and online path re-planning strategy is adopted to consider local variations of the environment so that a small computational load is devoted for re-planning procedure since the upper layer, which is responsible for mission scheduling, renders an overview of the operation area that AUV should fly thru. Numerical simulations for analysis of different situations of the real-world environment is accomplished separately for each layer and also for the entire ARMSP model at the end. Performance and stability of the model is investigated thorough employing metaheuristic algorithms toward furnishing the stated mission goals.

研究动机与目标

• 解决AUV在湍流、不确定海洋环境中实现高级决策自主性的挑战。
• 使单个AUV能够在一次任务中执行多项任务，同时适应突发的环境变化。
• 设计一种分层控制架构，集成任务调度、路径规划与实时重规划。
• 通过进化算法确保在时变条件下稳定高效的性能。
• 通过将高层规划任务卸载至上层概览系统，最小化在线重规划期间的计算负载。

提出的方法

• 设计一种多层ARMSP架构，各层使用进化算法解决特定子问题：任务调度、路径规划与动态重规划。
• 在规划过程中引入静态海流图与动态-静态障碍物作为环境约束。
• 应用AUV的运动学-动力学约束，以确保轨迹的物理可行性。
• 实施一种在线重规划策略，利用实时数据对局部环境变化作出反应。
• 将高层任务概览与低层运动规划解耦，以降低重规划期间的计算负载。
• 在不同层级使用元启发式算法（如遗传算法、粒子群优化）高效探索解空间。

实验结果

研究问题

• RQ1 如何使自主AUV系统在任务执行期间对动态且不确定的海洋环境实现实时适应？
• RQ2 ARMSP架构在不同元启发式算法下的任务调度与路径规划中，性能稳定性如何？
• RQ3 系统是否能在保持任务目标与安全约束的前提下，实现低计算开销的在线重规划？
• RQ4 分层进化算法方法在处理时变威胁与动态障碍物方面有多高效？
• RQ5 ARMSP模型在不同环境条件与任务复杂度下，性能稳定性如何？

主要发现

• ARMSP架构成功实现了在动态海洋条件下使用进化算法进行实时任务调度与路径规划。
• 系统在不同元启发式算法下表现出稳定性能，表明其在解生成方面具有鲁棒性。
• 由于上层任务概览的存在，在线重规划实现了低计算负载，减少了对完整重优化的需求。
• 集成静态海流数据、动态障碍物与AUV运动学-动力学约束显著提升了任务的安全性与可行性。
• 数值仿真证实了ARMSP模型在处理复杂、时变环境方面在所有层级及端到端运行中的有效性。
• 即使在突发环境变化下，该架构仍能维持任务目标与威胁规避，证明了其反应能力与适应性。