APEX-Glove: An Actuated, Open-Source, Hand-Exoskeleton Glove for Finger Motion Tracking and Kinesthetic 3D Force Feedback
Nicolas Kosanovic, Jean Chagas Vaz
AI summary
Problem
Existing wearable haptic devices cannot simultaneously provide accurate finger motion tracking and multidimensional force feedback, which severely limits complex robotic hand teleoperation and immersive VR control.
Approach
The authors designed a dorsal-mounted, 3D-printed exoskeleton driven by low-cost torque-controlled servos, using data-driven dynamic compensation and biomechanically-informed inverse kinematics to estimate hand pose and render 3D forces in real time.
Key results
- 300 Hz finger joint angle estimation with 18.5° average RMSE versus industrial datagloves
- Active 3D force feedback generation up to 0.8 N, 0.7 N, and 1.4 N per finger
- Successful motion retargeting and haptic teleoperation demonstrated on simulated and real humanoid hands
- Complete open-source hardware and software stack released for under $700
Why it matters
Provides researchers and developers with an affordable, high-fidelity platform to advance contact-rich robotic teleoperation, VR interaction, and embodied AI training.
Abstract
Accurate motion tracking and haptics are pivotal to building platforms for immersive Virtual Reality, dexterous robotic hand teleoperation, or embodied AI data collection. Existing technologies fail to provide accurate finger motion tracking and multidimensional force feedback simultaneously, complicating robotic hand control. This work develops the APEX-Glove: the world’s first dorsal-mounted wearable hand exoskeleton yielding both accurate finger motion tracking and active kinesthetic 3D force feedback. Data-driven modeling of the exoskeleton and its Dynamixel XL330 actuators compensates gravity, Coriolis, and friction forces to improve transparency and comfort. Biomechanically-informed analytical inverse kinematics estimates human finger joint angles at 300 Hz with an average Root Mean Squared Error of 18.5◦when compared to industrial-grade datagloves (MANUS Quantum Metagloves). Stationary testing finds that the APEX- Glove can generate up to 0.8 N, 0.7 N, and 1.4 N of force feedback in the x, y, and z directions, on average. Motion retargeting to humanoid robot hands is also detailed, with hardware experimentation demonstrating haptic hand teleoperation. Lastly, we open-source3 the APEX-Glove’s cost- effective (< 700 USD) design to disseminate its motion capture and force feedback capabilities to the community.