Bottle Picking
Collecting demonstrations enriched with fine-grained tactile information is critical for dexterous manipulation, particularly in contact-rich tasks that require precise force control and physical interaction. While prior works primarily focus on teleoperation or video-based retargeting, they often suffer from kinematic mismatches and the absence of real-time tactile feedback, hindering the acquisition of high-fidelity tactile data. To mitigate this issue, we propose KineDex, a hand-over-hand kinesthetic teaching paradigm in which the operator's motion is directly transferred to the dexterous hand, enabling the collection of physically grounded demonstrations enriched with accurate tactile feedback. To resolve occlusions from human hand, we apply inpainting technique to preprocess the visual observations. Based on these demonstrations, we then train a visuomotor policy using tactile-augmented inputs and implement force control during deployment for precise contact-rich manipulation. We evaluate KineDex on a suite of challenging contact-rich manipulation tasks, including particularly difficult scenarios such as squeezing toothpaste onto a toothbrush, which require precise multi-finger coordination and stable force regulation. Across these tasks, KineDex achieves an average success rate of 74.4%, representing a 57.7% improvement over the variant without force control. Comparative experiments with teleoperation and user studies further validate the advantages of KineDex in data collection efficiency and operability. Specifically, KineDex collects data over twice as fast as teleoperation across two tasks of varying difficulty, while maintaining a near-100% success rate, compared to under 50% for teleoperation.
KineDex collects tactile-enriched demonstrations via kinesthetic teaching, where visual occlusions from the operator's hand are removed through inpainting before policy training. The learned policy takes visual and tactile inputs to predict joint positions and contact forces, which are executed with force control for robust manipulation.
Kinesthetic demonstrations effectively support visuomotor policy learning across a wide range of daily manipulation tasks, owing to their natural alignment with human behavior and the availability of accurate tactile and force feedback.
Visualization of predicted and sensed forces at the thumb during task execution, comparing the force-informed policy and the variant without force control.
Some failure cases when removing force control.
Comparison of demonstration collection time between KineDex and teleoperation on the Bottle Picking and Syringe Pressing.
Summary of user study results. Five participants used both the teleoperation system and KineDex to collect demonstrations. Pie charts summarize their feedback on key evaluation criteria.
@misc{zhang2025kinedexlearningtactileinformedvisuomotor,
title={KineDex: Learning Tactile-Informed Visuomotor Policies via Kinesthetic Teaching for Dexterous Manipulation},
author={Di Zhang and Chengbo Yuan and Chuan Wen and Hai Zhang and Junqiao Zhao and Yang Gao},
year={2025},
eprint={2505.01974},
archivePrefix={arXiv},
primaryClass={cs.RO},
url={https://arxiv.org/abs/2505.01974},
}