Výsledky vyhledávání

Report

Cross-Embodiment Dexterous Grasping with Reinforcement Learning

Autor: Yuan, Haoqi, Zhou, Bohan, Fu, Yuhui, Lu, Zongqing

Dexterous hands exhibit significant potential for complex real-world grasping tasks. While recent studies have primarily focused on learning policies for specific robotic hands, the development of a universal policy that controls diverse dexterous ha

Externí odkaz: http://arxiv.org/abs/2410.02479

Zobrazit plný text záznamu

Report

Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations

Autor: Zhou, Bohan, Yuan, Haoqi, Fu, Yuhui, Lu, Zongqing

Bimanual dexterous manipulation is a critical yet underexplored area in robotics. Its high-dimensional action space and inherent task complexity present significant challenges for policy learning, and the limited task diversity in existing benchmarks

Externí odkaz: http://arxiv.org/abs/2410.02477

Zobrazit plný text záznamu

Report

Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping

Autor: Huang, Ziye, Yuan, Haoqi, Fu, Yuhui, Lu, Zongqing

Universal dexterous grasping across diverse objects presents a fundamental yet formidable challenge in robot learning. Existing approaches using reinforcement learning (RL) to develop policies on extensive object datasets face critical limitations, i

Externí odkaz: http://arxiv.org/abs/2410.02475

Zobrazit plný text záznamu

Report

Creative Agents: Empowering Agents with Imagination for Creative Tasks

Autor: Zhang, Chi, Cai, Penglin, Fu, Yuhui, Yuan, Haoqi, Lu, Zongqing

We study building embodied agents for open-ended creative tasks. While existing methods build instruction-following agents that can perform diverse open-ended tasks, none of them demonstrates creativity -- the ability to give novel and diverse task s

Externí odkaz: http://arxiv.org/abs/2312.02519

Zobrazit plný text záznamu