arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2303.08933cs.MAcs.RO
收藏

利用具有高阶拓扑抽象的图强化学习高效规划多机器人集体运输

Efficient Planning of Multi-Robot Collective Transport using Graph Reinforcement Learning with Higher Order Topological Abstraction

University at Buffalo(布法罗大学);Temple University(天普大学);University of Texas at Dallas(德克萨斯大学达拉斯分校)

Steve Paul, Wenyuan Li, Brian Smyth, Yuzhou Chen, Yulia Gel, Souma Chowdhury

AI总结:

针对大规模多机器人集体运输任务分配难题,本文提出用持续同调拓扑描述符增强图神经网络并以 PPO 训练,从而在更大问题上实现快速且可迁移的规划。

摘要:

高效的多机器人任务分配(MRTA)是灾害响应、仓库作业和建筑施工等各类时间敏感应用的基础。本文处理这些问题中的一个特定类别,我们称之为 MRTA-集体运输或 MRTA-CT——在该问题中,任务具有不同的工作量和截止期限,而机器人受到飞行距离、通信距离和有效载荷约束。对于涉及数百至数千个任务以及数十至数百个机器人的大规模问题实例,传统的非学习求解器通常时间效率低下,而新兴的基于学习的策略若不进行代价高昂的再训练,便无法很好地扩展到更大规模的问题。为弥补这一差距,我们采用近期提出的包含 Capsule 网络和多头注意力机制的编码器-解码器图神经网络,并创新性地加入拓扑描述符(TD)作为新特征,以提升向未见的相似规模和更大规模问题的迁移能力。我们使用持续同调推导 TD,并使用近端策略优化训练该 TD 增强的图神经网络。所得策略模型在性能上优于最先进的非学习基线,同时速度快得多。在扩展到规模大于训练所用问题的测试问题时,使用 TD 的优势会清晰显现。

英文摘要:

Efficient multi-robot task allocation (MRTA) is fundamental to various time-sensitive applications such as disaster response, warehouse operations, and construction. This paper tackles a particular class of these problems that we call MRTA-collective transport or MRTA-CT -- here tasks present varying workloads and deadlines, and robots are subject to flight range, communication range, and payload constraints. For large instances of these problems involving 100s-1000's of tasks and 10s-100s of robots, traditional non-learning solvers are often time-inefficient, and emerging learning-based policies do not scale well to larger-sized problems without costly retraining. To address this gap, we use a recently proposed encoder-decoder graph neural network involving Capsule networks and multi-head attention mechanism, and innovatively add topological descriptors (TD) as new features to improve transferability to unseen problems of similar and larger size. Persistent homology is used to derive the TD, and proximal policy optimization is used to train our TD-augmented graph neural network. The resulting policy model compares favorably to state-of-the-art non-learning baselines while being much faster. The benefit of using TD is readily evident when scaling to test problems of size larger than those used in training.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑