Learning to Swarm with Knowledge-Based Neural Ordinary Differential Equations
This addresses the challenge of designing robot controllers for artificial swarms and multiagent systems, though it appears incremental as it builds on hybrid machine learning methods.
The paper tackles the problem of learning decentralized single-robot controllers from swarm trajectory observations without requiring action data, using a knowledge-based neural ODE framework, and demonstrates that the learned controllers reproduce flocking behavior and scale to larger swarms in 2D and 3D simulations.
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.