Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions
This addresses a general open problem in engineering domains for control and prediction of dynamical systems with discrete events and multi-modal flows, representing a novel method for a known bottleneck.
The authors tackled the problem of learning stochastic hybrid system dynamics without prior knowledge of modes or transitions, introducing Neural Hybrid Automata (NHAs) that achieved mode recovery and flow learning in systems with stochastic transitions, and end-to-end learning of hierarchical robot controllers.
Effective control and prediction of dynamical systems often require appropriate handling of continuous-time and discrete, event-triggered processes. Stochastic hybrid systems (SHSs), common across engineering domains, provide a formalism for dynamical systems subject to discrete, possibly stochastic, state jumps and multi-modal continuous-time flows. Despite the versatility and importance of SHSs across applications, a general procedure for the explicit learning of both discrete events and multi-mode continuous dynamics remains an open problem. This work introduces Neural Hybrid Automata (NHAs), a recipe for learning SHS dynamics without a priori knowledge on the number of modes and inter-modal transition dynamics. NHAs provide a systematic inference method based on normalizing flows, neural differential equations and self-supervision. We showcase NHAs on several tasks, including mode recovery and flow learning in systems with stochastic transitions, and end-to-end learning of hierarchical robot controllers.