4 papers
Safe Navigation of Bipedal Robots via Koopman Operator-Based Model Predictive Control
Jeonghwan Kim, Yunhai Han, Harish Ravichandar +1
Nonlinearity in dynamics has long been a major challenge in robotics, often causing significant performance degradation in existing control algorithms. For example, the navigation…
On the Surprising Effectiveness of Spectral Clipping in Learning Stable Linear and Latent-Linear Dynamical Systems
Hanyao Guo, Yunhai Han, Harish Ravichandar
When learning stable linear dynamical systems from data, three important properties are desirable: i) predictive accuracy, ii) verifiable stability, and iii) computational efficien…
ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation
Yangcen Liu, Woo Chul Shin, Yunhai Han +3
Learning robot manipulation from abundant human videos offers a scalable alternative to costly robot-specific data collection. However, domain gaps across visual, morphological, an…
AsymDex: Asymmetry and Relative Coordinates for RL-based Bimanual Dexterity
Zhaodong Yang, Yunhai Han, Ai-Ping Hu +1
We present Asymmetric Dexterity (AsymDex), a novel and simple reinforcement learning (RL) framework that can efficiently learn a large class of bimanual skills in multi-fingered ha…