ROBOTERA XHAND 1 Pro combines 21 active degrees of freedom with a fully actuated architecture and tactile sensing distributed across the entire hand surface. This combination of joint-level control and dense contact sensing supports complex grasping, in-hand manipulation, and reinforcement learning research. These applications require both precise motion control and rich feedback about physical contact.
Collecting demonstrations for a hand with this level of dexterity requires a human interface capable of providing comparable input resolution. MANUS gloves track fingertip position and rotation, and MANUS Core processes this into a 25 degrees of freedom anatomical hand skeleton, made available for integration into teleoperation and demonstration-data collection pipelines.
The XHAND 1 Pro joint layout is sufficiently similar to the MANUS anatomical hand model for flexion and spread values to be mapped directly to the corresponding robot joint targets. This joint-angle-based approach is intuitive and can reduce the need for additional inverse kinematics calculations.
Where a finger’s joint count or axes differ from the MANUS' hand model, fingertip position and rotation can be used as endpoint targets instead. An inverse kinematics layer then calculates a suitable robot configuration while keeping the fingertip pose consistent with the operator’s intended movement.
The resulting retargeting pipeline combines direct joint mapping with endpoint-based control according to the mechanical structure and capabilities of each finger.
Tactile measurements from XHAND 1 Pro can also be incorporated into a bilateral teleoperation architecture using MANUS Metagloves Pro Haptic. Contact signals detected by the robot hand can be mapped to haptic feedback on the operator’s corresponding fingers, with feedback intensity representing the strength of the detected contact. This allows the operator to perceive information such as initial contact, changes in grip, and variations in pressure while manipulating an object.
By combining XHAND 1 Pro with MANUS hand tracking, research teams can build teleoperation systems that capture not only how the human hand moves, but also how the operator responds to physical contact throughout a manipulation task.
