Touch-JEPA is a framework that learns tactile representations from hand‑object videos using limited tactile supervision. It first trains a self‑supervised model that predicts masked visual features at hand‑surface locations, capturing latent contact dynamics. The model is then jointly fine‑tuned on a small labeled subset, improving contact discrimination and tactile magnitude estimation on human‑hand benchmarks and transferring to robotic hands without robot tactile data.
By Minseong Kweon, Qiao Feng, Yiming Huang, Lingjie Liu
arXiv:2610.10288v1 Announce Type: new
Abstract: Large-scale egocentric human interaction data is becoming an important source of physical supervision for embodied learning, yet video alone leaves the...
By Dayou Li, Hao Wang, Qianqian Yang, Zihao Zhu, Haoquan Fang, Ziyao Zeng, Yan Han, Zihan Wang, Yan Wang, Baoru Huang, Dilin Wang, Kenji Shimada, Yiyue Luo, Manling Li, Teresa Lv, Mustafa Mukadam, Rakesh Ranjan, Ruohan Zhang, Qi He, Changliu Liu, Xu Chen, Marco Pavone, Bangya Liu, Jiachen Li, Masayoshi Tomizuka, Zhiwen Fan
arXiv:2608.15060v2 Announce Type: replace
Abstract: Touch is fundamental to dexterous manipulation, yet most egocentric human data increasingly used for robot learning lacks tactile information. Dire...
By Wenkang Zhang, Chengbo Yuan, Zicheng Zhang, Zhengxue Cheng, Yang Gao
arXiv:2609.34182v2 Announce Type: replace-cross
Abstract: Dexterous manipulation requires tactile feedback. However, robot tactile demonstrations are difficult to scale,because dexterous-hand teleope...
By Wenqiao Li, Qianyou Zhao, Jiawen Hao, Xuezhou Zhu, Tengyu Liu, Kaifeng Zhang, Chuan Wen, Siyuan Huang
DexTouch-WM is an action‑conditioned world model that learns from scalable human touch to predict future RGB observations and bilateral tactile dynamics for dexterous robot manipulation. By using compatible piezoresistive arrays on both human and robot hands and retargeting human motion into the robot action space, the model can be supervised with human interaction data while keeping a fixed amount of real‑robot supervision. Experiments show that adding up to 100 hours of human interaction improves robot‑domain visual, geometric, and contact prediction, and the model can serve as a surrogate environment for policy evaluation and synthetic trajectory generation.
By Yan Qin, Yue Chen, Wenwei Lin, Shujia Liu, Chuqiao Lyu, Kailun Su, Chenze Yu, Ping Luo, Wenbo Ding, Tianxing Chen, Renjing Xu
arXiv:2610.10283v1 Announce Type: cross
Abstract: Humans can grasp everyday objects with almost perfect success rates using fingertip tactile feedback, yet much of the robotic grasping literature emp...
By Ken Nakahara, Aleksei Buvailik, Prokhor Kotov, Roberto Calandra
arXiv:2610.33685v1 Announce Type: cross
Abstract: Vision-Language-Action (VLA) models are bottlenecked by the scarcity of robot data. Egocentric human manipulation videos offer an abundant, diverse,...
By Qingyuan Cai, Bo Zhang, Yongzhen Huang, Jianyu Chen
ControlTac is a two‑stage framework that generates realistic tactile images conditioned on a single reference image, contact force, and contact pose. By incorporating these physical priors, it produces realistic samples across different sensors and captures task‑relevant variations. Experiments in object insertion, imitation learning, and object weighting show that datasets augmented with ControlTac consistently improve performance in dynamic real‑world settings.
By Dongyu Luo, Kelin Yu, Amir-Hossein Shahidzadeh, Cornelia Ferm\"uller, Yiannis Aloimonos, Ruohan Gao
arXiv:2608.29601v2 Announce Type: replace-cross
Abstract: We present $N_0$-Foundation, a paradigm for tactile-enabled embodied manipulation, which integrates tactile sensing hardware, large-scale mul...
By NeoteAI Team, Fudan TEAI Team
TACROSS is a low‑cost, scalable system that enables robots to learn from human touch by aligning tactile streams at the level of contact events rather than raw sensor values. It combines a $10.86 piezoresistive glove with 285 sensing points and a temporal Transformer that maps heterogeneous signals into a shared 256‑dimensional latent space. The approach uses robot demonstrations for action supervision while human demonstrations aid tactile representation learning, achieving a 3.5‑fold efficiency improvement and a 95.7% reduction in demonstration equipment cost across four manipulation tasks.
By Bo Chen, Huanzhang Hu, Junyang Ma, Bo Yue, Fangdi Yu, Haijier Chen, Xianxin Lai, Shuyu Pan, Zhen Yang, Xiaoquan Sun, Wenze Cui, Zhongliang Jiang, Shaopeng Liu, Jiayu Chen
DreamTacVLA is a Vision‑Language‑Action framework that incorporates high‑resolution tactile images alongside wrist‑camera and third‑person vision to enable robots to anticipate and react to contact dynamics. It uses a Hierarchical Spatial Alignment loss to align tactile tokens with visual counterparts and a tactile world model to predict future tactile signals, trained on a hybrid dataset from digital twins and real experiments. The approach achieves up to 95% success on contact‑rich manipulation tasks, outperforming existing VLA baselines.
By Guo Ye, Zexi Zhang, Xu Zhao, Shang Wu, Haoran Lu, Shihan Lu, Han Liu
arXiv:2607. 03723v1 Announce Type: cross Abstract: Visual policies learned from human videos, teleoperation, and robot demonstrations offer scalable motion priors, but often fail in contact-rich manipulation, where success significantly depends on local force and contact geometry.
By Kelin Yu, Haode Zhang, Harish Ravichandar, Yunhai Han, Ruohan Gao