Learning orbitally stable dynamics via transverse contraction criteria for modeling periodic tasks

Haoyu Zhang, Long Cheng, Zeyu Liu, Yu Zhang, School of Artificial Intelligence, University of Chinese Academy of Sciences, State Key Laboratory for Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences

The International Journal of Robotics Research

Published online on September 17, 2025

Abstract

The International Journal of Robotics Research, Volume 45, Issue 5, Page 775-800, April 2026.
This paper presents a novel framework for learning orbitally stable nonlinear dynamical systems from demonstrations for rhythmic tasks in robotics. The core innovation is a reproducing kernel Hilbert space (RKHS) parametrization method for rhythmic ...