用对称性增强GNN，让无人集群更省数据、更省参数地保持队形。
Learning Decentralized Swarms Using Rotation Equivariant Graph Neural Networks
- 在GNN中强制旋转等变与平移不变，提升控制模型的对称性
- 训练数据减少70%，参数量少75%，仍能保持良好队形控制
- 更适合需要低资源、强泛化的分布式集群控制场景
在无中心化控制下协调智能体以优化集体目标具有挑战性但至关重要，例如自动驾驶车队或传感器网络的监控侦察。受自然界自组织现象启发，尤其是群体飞行行为，但现有去中心化控制器难以维持队形一致性。图神经网络（GNN）已成为开发具备队形保持能力的去中心化控制器的重要工具，但未能利用群体动力学中的对称性，限制了其泛化能力。本文在去中心化群体控制的GNN控制器中引入旋转等变性和平移不变性对称性，实现了与现有方法相当的群体控制性能，同时训练数据减少70%，可训练参数减少75%。此外，我们的对称性感知控制器表现出更强的泛化能力。代码与动画见 http://github.com/Utah-Math-Data-Science/Equivariant-Decentralized-Controllers。
原文摘要 · Abstract (English)
The orchestration of agents to optimize a collective objective without centralized control is challenging yet crucial for applications such as controlling autonomous fleets, and surveillance and reconnaissance using sensor networks. Decentralized controller design has been inspired by self-organization found in nature, with a prominent source of inspiration being flocking; however, decentralized controllers struggle to maintain flock cohesion. The graph neural network (GNN) architecture has emerged as an indispensable machine learning tool for developing decentralized controllers capable of maintaining flock cohesion, but they fail to exploit the symmetries present in flocking dynamics, hindering their generalizability. We enforce rotation equivariance and translation invariance symmetries in decentralized flocking GNN controllers and achieve comparable flocking control with 70% less training data and 75% fewer trainable weights than existing GNN controllers without these symmetries enforced. We also show that our symmetry-aware controller generalizes better than existing GNN controllers. Code and animations are available at http://github.com/Utah-Math-Data-Science/Equivariant-Decentralized-Controllers.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。