CDF-Glove: A Cable-Driven Force Feedback Glove for Dexterous Teleoperation
Huayue Liang, Ruochong Li, Yaodong Yang, Long Zeng, Yuanpei Chen and Xueqian Wang
AI summary
Problem
High-quality expert demonstration data is critical for imitation learning in dexterous manipulation, yet existing teleoperation gloves are often bulky, expensive, and lack precise haptic feedback.
Approach
The authors designed a lightweight, cable-driven glove that tracks 20 finger degrees of freedom (16 active, 4 coupled) and provides real-time vibrotactile and kinesthetic force feedback to enable precise, closed-loop operator control.
Key results
- 0.4° distal-joint repeatability with ~200 ms force-feedback latency
- 4× improvement in task success rate with haptic feedback versus no feedback
- 55% higher policy success rate and 47.2% faster task completion compared to kinesthetic teaching
- Open-source design costing approximately $230
Why it matters
Enables researchers and developers to efficiently collect high-quality dexterous manipulation data for training robust imitation learning policies without prohibitive hardware costs.
Abstract
High-quality teleoperated demonstrations are a primary bottleneck for imitation learning (IL) in dexterous manipulation. However, haptic feedback provides operators with real-time contact information, enabling real-time finger- posture adjustments, and thereby improving demonstration quality. Existing dexterous teleoperation platforms typically omit haptic feedback and remain bulky and expensive. We introduce CDF-Glove, a lightweight and low-cost cable-driven force-feedback glove. The real-time state is available for 20 finger degrees of freedom (DoF), of which 16 are directly sensed and 4 are passively coupled (inferred from kinematic con- straints). We develop a kinematic model and control stack for the glove, and validate them across multiple robotic hands with diverse kinematics and DoF. The CDF-Glove achieves distal- joint repeatability of 0.4°, and delivers about 200 ms force- feedback latency, yielding a 4× improvement in task success rate relative to no-feedback teleoperation. We collect two bimanual teleoperation datasets, on which we train and evaluate Diffusion Policy baselines. Compared to kinesthetic teaching, the policies trained in our teleoperated demonstrations increase the average success rate by 55% and reduce the mean completion time by ≈15.2 seconds (a 47.2% relative reduction). In particular, the CDF-Glove costs ≈US$230. The code and designs are released as open source at https://cdfglove.github.io/.