PiHand is a physics‑based framework that learns latent hand‑object interaction priors for dexterous manipulation. It first trains expert policies to track motion capture demonstrations, then distills these into a goal‑conditioned VAE that captures coupled hand‑object motion. Using bounded residual exploration in this latent space, PiHand produces general tabletop manipulation policies that generalize to unseen objects and trajectories, outperforming baselines across multiple tasks.
By Niklas Berndt, Xianghui Xie, Enes Duran, Yixiao Wang, Gerard Pons-Moll
arXiv:2608.22449v1 Announce Type: cross
Abstract: Forecasting dexterous hand motions from egocentric observations is fundamental to intelligent interactive systems. Existing VLM-based methods typical...
By Wen Wang, Ruibing Hou, Hong Chang, Shiguang Shan, Xilin Chen
AdaDex is a goal‑conditioned reinforcement learning framework that transforms a short hand‑object trajectory—captured via mocap or in‑the‑wild RGB(D) video—into an adaptable dexterous skill. It trains a shared policy on two parallel environment populations: motion‑tracking environments that embed human priors and generalization environments that enforce robustness to noisy states and goals. The resulting policies achieve diverse, functional dexterous behaviors such as grasping, re‑posing, in‑hand reorientation, and dynamic throw‑and‑catch, outperforming baselines in generalization and demonstrating transfer from simulation to the real world.
By Yuxuan Kuang, Jiashun Wang, Yixuan Sun, Yufei Ye, Sungjae Park, Umar Iqbal, Katerina Fragkiadaki, Shubham Tulsiani
Retargeting human object interaction demonstrations to physics based simulation requires reproducing not only body motion but also the object motion and contacts that make manipulation succeed. However, position only hand trajectories do not specify the contact forces needed to manipulate objects, and directly tracking them can overconstrain contact rich finger behavior.
arXiv:2606. 10614v1 Announce Type: cross Abstract: Robotic foundation models pre-trained on human demonstration videos have shown promise, but a significant embodiment gap remains when the resulting policies are deployed on real robots.
By Beomjun Kim, Seong Hyeon Park, Seunghoon Sim, Seungjun Moon, Sanghyeok Lee, Jinwoo Shin
arXiv:2610.14691v2 Announce Type: cross
Abstract: Recent advances in 3D hand-object interaction (HOI) perception have opened new opportunities for learning dexterous robotic skills from human videos....
By Zihan Gao, Yuhong Zhang, Mengzhe Wang, Kaisheng Liu, Shengpeng Li, Siyao Xiao, Runqing Cheng, Xiao Lin, Zhifang Liu, Haoqian Wang