5 papers · 1 filter
CARO: Contact-Agnostic Residual Observation for Zero-Shot Robust Quadruped Locomotion
Zihan Yang, Shixuan Han, Kexin Guo +1
We propose CARO, a contact-agnostic residual observation framework for policy adaptation. CARO embeds a fixed-base Euler--Lagrange model into the reinforcement learning control loo…
Physics Filtering Favors the Generalization of Robot Learning
Jindou Jia, Shixuan Han, Meng Wang +8
Living organisms exhibit extraordinary adaptability to unseen environments through their intrinsic physical structures and lifelong feedback-driven learning. Endowing robots with c…
Unified Meta-Representation and Feedback Calibration for General Disturbance Estimation
Zihan Yang, Jindou Jia, Meng Wang +3
Precise control in modern robotic applications is always an open issue due to unknown time-varying disturbances. Existing meta-learning-based approaches require a shared representa…
Optimizing Control-Friendly Trajectories with Self-Supervised Residual Learning
Kexin Guo, Zihan Yang, Yuhang Liu +2
Real-world physics can only be analytically modeled with a certain level of precision for modern intricate robotic systems. As a result, tracking aggressive trajectories accurately…
Learning-based Observer for Coupled Disturbance
Jindou Jia, Meng Wang, Zihan Yang +4
Achieving high-precision control for robotic systems is hindered by the low-fidelity dynamical model and external disturbances. Especially, the intricate coupling between internal…