发表机构
South China University of Technology; South China Normal University; Aerospace Information Research Institute, CAS; Nankai University（华南理工大学; 华南师范大学; 中国科学院空天信息创新研究院; 南开大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对无人机在无线传感器网络中数据感知的路径规划问题，提出景观感知元差分进化（LAMDE）框架，通过双层学习优化与变长编码策略，实现自适应规划并达到最先进性能。
AI 中文摘要
无人机已成为无线传感器网络（WSN）中数据感知的高度灵活平台。在此类任务中，无人机的路径规划在确保遥感有效性和能耗友好性方面发挥着关键作用。然而，现有方法存在两个关键局限性：i）它们主要依靠手工设计，带有一定的设计偏差，这损害了在未见任务上的适应性。ii）它们主要通过简化模拟来假设实际环境的理想化空间复杂度，导致在实际部署中表现不佳。在本文中，我们提出了一种新颖的学习辅助规划框架，称为景观感知元差分进化（LAMDE），以解决上述局限性。主要贡献来自以下几个方面。我们首先重新表述了此类无人机路径规划问题，以包含具有挑战性的约束。为了高效地导航这个高度受限的空间，我们提出了一种双层学习优化方法，其中元层是一个可训练的算法配置策略，它为低层规划算法元学习一种适应性规划策略。为了解决现实环境中潜在的训练数据稀缺和分布偏移问题，我们引入了一种景观感知的自动增强方案，以丰富训练数据。在低层，部署差分进化算法来解决路径规划任务。为了增强求解灵活性，我们进一步设计了一种变长编码策略，该策略在统一的搜索空间中动态修剪冗余的悬停点，并同时优化连续飞行参数。基于所有提出的设计，我们对LAMDE进行元训练，并将其与代表性基线进行比较。综合实验表明，LAMDE在WSN数据收集场景中测试的复杂无人机路径规划任务上达到了最先进的性能。
英文摘要
UAVs have emerged as highly flexible platforms for data sensing in Wireless Sensor Networks (WSNs). Path planning for UAVs in such tasks plays a key role to assure remote sensing effectiveness and friendly energy consumption. However, existing approaches show two key limitations: i) they are primarily hand-crafted with certain design biases that harm adaptation on unseen tasks. ii) they predominantly assume idealized spatial complexities of actual environments through simplified simulation, causing them to underperform during real-world deployment. In this paper, we propose a novel learning-assisted planning framework, termed Landscape-Aware Meta Differential Evolution (LAMDE), to tackle the mentioned limitations. The major contributions come from the following aspects. We first re-formulate such UAV path planning problem to embrace challenging constraints. To efficiently navigate this highly constrained space, we propose a bi-level learning to optimize approach, where the meta-level is a trainable algorithm configuration policy that meta-learns an adaptable planning strategy for low-level planning algorithm. To address the potential training data scarcity and distribution shift in real-world environments, we introduce a landscape-aware automatic augmentation scheme that enriches training data. At the low-level, a Differential Evolution algorithm is deployed for solving the path planning tasks. To enhance the solving flexibility, we further design a variable-length encoding strategy that dynamically prunes redundant hover points and optimizes continuous flight parameters concurrently within a unified search space. Based on all proposed designs, we meta-train LAMDE and compare it with representative baselines. Comprehensive experiments demonstrate that LAMDE achieves state-of-the-art performance on the tested complex UAV path planning tasks in WSN data collection scenarios.
