Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks
Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks
复制标题
DOI：
--
复制
发表时间：
2019-03
期刊：
影响因子：
--
通讯作者：
Ekaterina V. Tolstaya;Fernando Gama;James Paulos;George Pappas;Vijay R. Kumar;Alejandro Ribeiro
中科院分区：
文献类型：
--
作者：
Ekaterina V. Tolstaya;Fernando Gama;James Paulos;George Pappas;Vijay R. Kumar;Alejandro Ribeiro
我们考虑为具有交互动态和稀疏可用通信的大型移动机器人网络寻找分布式控制器的问题。我们的方法是通过模仿集中控制器在训练时使用全局信息的策略来学习在测试时仅需要本地信息和本地通信的本地控制器。通过将聚合图神经网络扩展到时变信号和时变网络支持，我们学习了一个通用的本地控制器，该控制器仅使用本地通信交换来利用来自远程队友的信息。我们将这种方法应用于分散式线性二次调节器问题，并观察更快的通信速率和更小的网络度如何增加多跳信息的价值。学习分散式集群控制器的单独实验展示了随着机器人移动而变化的通信图的性能。
We consider the problem of finding distributed controllers for large networks of mobile robots with interacting dynamics and sparsely available communications. Our approach is to learn local controllers which require only local information and local communications at test time by imitating the policy of centralized controllers using global information at training time. By extending aggregation graph neural networks to time varying signals and time varying network support, we learn a single common local controller which exploits information from distant teammates using only local communication interchanges. We apply this approach to a decentralized linear quadratic regulator problem and observe how faster communication rates and smaller network degree increase the value of multi-hop information. Separate experiments learning a decentralized flocking controller demonstrate performance on communication graphs that change as the robots move.