Hybrid dynamical systems, which include continuous flow and discrete mode switching, can model robotics tasks like legged robot locomotion. Model-based methods usually depend on predefined gaits, while model-free approaches lack explicit mode-switching knowledge. Current methods identify discrete modes via segmentation before regressing continuous flow, but learning high-dimensional complex rigid body dynamics without trajectory labels or segmentation is a challenging open problem. This paper introduces Discrete-time Hybrid Automata Learning (DHAL), a framework to identify and execute mode-switching without trajectory segmentation or event function learning. Besides, we embedded it in reinforcement learning pipeline and incorporates a beta policy distribution and a multi-critic architecture to model contact-guided motions, exemplified by a challenging quadrupedal robot skateboard task. We validate our method through sufficient real-world tests, demonstrating robust performance and mode identification consistent with human intuition in hybrid dynamical systems.
View on arXiv@article{liu2025_2503.01842,
title={ Discrete-Time Hybrid Automata Learning: Legged Locomotion Meets Skateboarding },
author={ Hang Liu and Sangli Teng and Ben Liu and Wei Zhang and Maani Ghaffari },
journal={arXiv preprint arXiv:2503.01842},
year={ 2025 }
}