Understanding decentralized dynamics from collective behaviors in swarms is crucial for informing robot controller designs in artificial swarms and multiagent robotic systems. However, the complexity in agent-to-agent interactions and the decentralized nature of most swarms pose a significant challenge to the extraction of single-robot control laws from global behavior. In this work, we consider the important task of learning decentralized single-robot controllers based solely on the state observations of a swarm's trajectory. We present a general framework by adopting knowledge-based neural ordinary differential equations (KNODE) -- a hybrid machine learning method capable of combining artificial neural networks with known agent dynamics. Our approach distinguishes itself from most prior works in that we do not require action data for learning. We apply our framework to two different flocking swarms in 2D and 3D respectively, and demonstrate efficient training by leveraging the graphical structure of the swarms' information network. We further show that the learnt single-robot controllers can not only reproduce flocking behavior in the original swarm but also scale to swarms with more robots.
翻译:了解群群中集体行为的分散动态对于向人工群和多试剂机器人系统中的机器人控制器设计提供信息至关重要。 然而,代理人与代理人互动的复杂性和大多数群群的分散性质对从全球行为中提取单机器人控制法提出了重大挑战。 在这项工作中,我们认为学习完全基于对群体轨迹的状态观测的分散的单一机器人控制器是一项重要任务。 我们通过采用基于知识的神经普通差异方程式(KODE) -- -- 一种能够将已知的代理体动态与人工神经网络相结合的混合机器学习方法 -- -- 提出了一个总体框架。 我们的方法将自己与大多数先前的工作区别开来,因为我们不需要为学习而采取行动的数据。 我们分别将我们的框架应用于2D和3D的两个不同的群群群中,并通过利用群体信息网络的图形结构来展示有效的培训。 我们还进一步表明,学习的单一机器人控制器不仅可以在原始的群中复制羊群行为,而且还可以与更多的机器人相交。