Discrete-Time Hybrid Automata Learning: Legged Locomotion Meets Skateboarding

This paper introduces Discrete-time Hybrid Automata Learning (DHAL), a framework using on-policy Reinforcement Learning to identify and execute mode-switching without trajectory segmentation or event function learning. 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. Our approach 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 simulations and real-world tests, demonstrating robust performance in hybrid dynamical systems.

@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 }
}