6 papers
Closing the Loop on the Poppy Humanoid: Bipedal Locomotion with Linear-Quadratic Control and Learned Cost Functions
Xulin Chen, Borui He, Ruipeng Liu +3
The Poppy Humanoid is an open-source, low-cost robot suitable for research and education in artificial intelligence. However, we are unaware of any published methodology that achie…
Beyond Coefficients: Forecast-Necessity Testing for Interpretable Causal Discovery in Nonlinear Time-Series Models
Valentina Kuskova, Dmitry Zaytsev, Michael Coppedge
Nonlinear machine-learning models are increasingly used to discover causal relationships in time-series data, yet the interpretation of their outputs remains poorly understood. In…
Beyond Topology: A Morphological Symmetry Graph Representation for Locomotion Policy Learning
Sizhe Wei, Xulin Chen, Fengze Xie +3
Reinforcement learning has enabled impressive locomotion skills on articulated robots, but common policy representations remain only weakly aligned with robot physics. Generic netw…
Towards Dynamic Quadrupedal Gaits: A Symmetry-Guided RL Hierarchy Enables Free Gait Transitions at Varying Speeds
Jiayu Ding, Xulin Chen, Garrett E. Katz +1
Quadrupedal robots exhibit a wide range of viable gaits, but generating specific footfall sequences often requires laborious expert tuning of numerous variables, such as touch-down…
Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics Uncertainty
Xulin Chen, Ruipeng Liu, Zhenyu Gan +1
Uncertainties in transition dynamics pose a critical challenge in reinforcement learning (RL), often resulting in performance degradation of trained policies when deployed on hardw…
Towards Dynamic Quadrupedal Gaits: A Symmetry-Guided RL Hierarchy Enables Free Gait Transitions at Varying Speeds
Jiayu Ding, Xulin Chen, Garret E. Katz +1
Quadrupedal robots exhibit a wide range of viable gaits, but generating specific footfall sequences often requires laborious expert tuning of numerous variables, such as touch-down…