IEEE

AQGP-UKF: Adaptive Quaternion Gaussian Process Unscented Kalman Filter for Robust Nonlinear Gait Phase Estimation

Abstract: This study proposes an Adaptive Quaterniondriven Gaussian Process Unscented Kalman Filter (AQGPUKF) framework, optimized for nonlinear gait dynamics, motion velocity sensitivity, and ...
IEEE

Context-Aware Gaussian Process for Physics-Informed Reinforcement Learning With Heterogeneous Data

Abstract: Reinforcement learning (RL) with physics-informed dynamics models leverages known environments’ physics to improve data efficiency. Recently, we have introduced Gaussian Process ...