Tactile Active Inference Reinforcement Learning for Efficient Robotic Manipulation Skill Acquisition

no code implementations • 19 Nov 2023 • Zihao Liu, Xing Liu, Yizhai Zhang, Zhengxiong Liu, Panfeng Huang

In this study, we propose a novel method for skill learning in robotic manipulation called Tactile Active Inference Reinforcement Learning (Tactile-AIRL), aimed at achieving efficient training.

reinforcement-learning Reinforcement Learning (RL)

Data-Driven Optimal Control of Tethered Space Robot Deployment with Learning Based Koopman Operator

no code implementations • 15 Jul 2023 • Ao Jin, Fan Zhang, Panfeng Huang

To avoid complex constraints of the traditional nonlinear method for tethered space robot (TSR) deployment, this paper proposes a data-driven optimal control framework with an improved deep learning based Koopman operator that could be applied to complex environments.

Data-driven Moving Horizon Estimation for Angular Velocity of Space Noncooperative Target in Eddy Current De-tumbling Mission

no code implementations • 13 Jan 2023 • Xiyao Liu, Haitao Chang, Zhenyu Lu, Panfeng Huang

In this paper, a Data-driven Moving Horizon Estimation method is proposed to estimate the angular velocity of the noncooperative target with de-tumbling torque.

LEMMA