Enregistré dans:
Détails bibliographiques
Auteurs principaux: Liu, Hang, Teng, Sangli, Liu, Ben, Zhang, Wei, Ghaffari, Maani
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2503.01842
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908304068837376
author Liu, Hang
Teng, Sangli
Liu, Ben
Zhang, Wei
Ghaffari, Maani
author_facet Liu, Hang
Teng, Sangli
Liu, Ben
Zhang, Wei
Ghaffari, Maani
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_01842
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Discrete-Time Hybrid Automata Learning: Legged Locomotion Meets Skateboarding
Liu, Hang
Teng, Sangli
Liu, Ben
Zhang, Wei
Ghaffari, Maani
Robotics
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.
title Discrete-Time Hybrid Automata Learning: Legged Locomotion Meets Skateboarding
topic Robotics
url https://arxiv.org/abs/2503.01842