An Embodied Generalist Agent in 3D World

1 code implementation • 18 Nov 2023 • Jiangyong Huang, Silong Yong, Xiaojian Ma, Xiongkun Linghu, Puhao Li, Yan Wang, Qing Li, Song-Chun Zhu, Baoxiong Jia, Siyuan Huang

Leveraging massive knowledge and learning schemes from large language models (LLMs), recent machine learning models show notable successes in building generalist agents that exhibit the capability of general-purpose task solving in diverse domains, including natural language processing, computer vision, and robotics.

3D dense captioning Question Answering +3

Grasp Multiple Objects with One Hand

no code implementations • 24 Oct 2023 • Yuyang Li, Bo Liu, Yiran Geng, Puhao Li, Yaodong Yang, Yixin Zhu, Tengyu Liu, Siyuan Huang

The human hand's complex kinematics allow for simultaneous grasping and manipulation of multiple objects, essential for tasks like object transfer and in-hand manipulation.

Diffusion-based Generation, Optimization, and Planning in 3D Scenes

2 code implementations • CVPR 2023 • Siyuan Huang, Zan Wang, Puhao Li, Baoxiong Jia, Tengyu Liu, Yixin Zhu, Wei Liang, Song-Chun Zhu

SceneDiffuser provides a unified model for solving scene-conditioned generation, optimization, and planning.

Denoising Grasp Generation +2

DexGraspNet: A Large-Scale Robotic Dexterous Grasp Dataset for General Objects Based on Simulation

no code implementations • 6 Oct 2022 • Ruicheng Wang, Jialiang Zhang, Jiayi Chen, Yinzhen Xu, Puhao Li, Tengyu Liu, He Wang

Robotic dexterous grasping is the first step to enable human-like dexterous object manipulation and thus a crucial robotic technology.

GenDexGrasp: Generalizable Dexterous Grasping

1 code implementation • 3 Oct 2022 • Puhao Li, Tengyu Liu, Yuyang Li, Yiran Geng, Yixin Zhu, Yaodong Yang, Siyuan Huang

By leveraging the contact map as a hand-agnostic intermediate representation, GenDexGrasp efficiently generates diverse and plausible grasping poses with a high success rate and can transfer among diverse multi-fingered robotic hands.