Glove-Based Dexterous Teleoperation: Hardware Selection and Setup

Why Use Gloves? The Case for Finger-Level Control

Most manipulation tasks — pick-and-place, sorting, simple grasping — do not require gloves. A well-calibrated parallel jaw gripper driven by a leader arm or VR controller produces higher data collection throughput at lower cost. Use gloves only when your task genuinely requires individual finger control.

Tasks that benefit from gloves: in-hand reorientation (rolling a bolt, flipping a card), pinch grasps on irregular objects (crumpled paper, fabric folds), multi-finger coordinated manipulation (tying a knot, threading a needle), and dexterous grasp adaptation to object compliance. If your task requires fewer than 3 fingers to work, a parallel jaw will likely outperform a glove-driven dexterous hand in data quality per hour.

The full glove teleoperation pipeline adds complexity at every level: calibration per operator, higher latency than arm teleoperation, more failure modes, higher operator fatigue, and significantly higher hardware cost. Approach it with eyes open.

Glove Hardware Comparison

The SenseGlove Nova 2 is the recommended choice for most imitation learning research. Its force-resistance feedback allows operators to feel when the robot hand is in contact, improving grasp quality and reducing "floating hand" failures where the hand closes without engaging the object. The Python SDK with ROS2 wrapper has the most community support and is compatible with most robot hand interfaces.

The HaptX G1 provides the most realistic haptics via microfluidic actuators that create skin pressure corresponding to contact geometry. This fidelity is valuable for extremely delicate manipulation (electronics components, biological samples) but the $10K/hand price and 500 g weight limit its practical use.

Robot Hand Compatibility

The Inspire RH56 DFX is the most cost-effective path to dexterous manipulation at $8K. Six actuated DOF (individual finger flexion plus thumb opposition) covers the majority of household manipulation tasks. Paired with a SenseGlove Nova 2, total hand teleoperation cost is ~$12K/hand.

The Leap Hand at $2K is gaining momentum in the research community due to its open-source design and leaphand_ros2 driver. For labs exploring finger-level imitation learning on a budget, it is the entry point.

Calibration Procedure

Every operator requires individual calibration. Gloves do not fit all hands identically, and finger length, knuckle position, and max extension angles vary significantly between operators. Miscalibrated gloves produce systematic bias in all collected data.

• Step 1 — Hand geometry mapping: Measure each operator's finger segment lengths (proximal, medial, distal phalanx) with calipers. Enter into the glove SDK's hand model. SenseGlove provides a calibration wizard; allow 10 minutes per operator.
• Step 2 — Range of motion calibration: Record maximum and minimum flexion angles for each finger by having the operator open fully (0°) and close fully (~90° MCP, ~100° PIP). The SDK stores per-finger min/max and applies normalization.
• Step 3 — Force threshold calibration: With force feedback enabled, gradually increase resistance while the operator reports onset of perception. Set the "contact detected" threshold 20% above noise floor. This prevents false contacts from glove micro-vibrations.
• Step 4 — Robot hand mapping: Map glove DOF to robot hand joint commands. For Inspire RH56, map each finger flexion angle (0–100%) to motor position (0–1000 ticks). Test by commanding each finger independently and confirming visual correspondence.
• Step 5 — End-to-end latency test: Command a rapid finger close (100 ms duration). Measure time from glove sensor reading to observed robot finger motion via wrist camera. Target: <35 ms total.

Latency Analysis

Latency above 50 ms produces perceptible lag that degrades operator coordination. If your measured total exceeds 50 ms, diagnose by adding timestamps at each stage. The most common culprit is ROS2 QoS configuration — set depth=1 and reliability=BEST_EFFORT for sensor topics to eliminate queue buildup.

Common Failure Modes and Mitigations

• Glove slippage during extended sessions: Glove sensors drift when the glove shifts on the hand. Use non-slip glove liners and tighten straps before each session. Re-run calibration every 30 minutes for multi-hour collections.
• IK singularities in finger joint space: When commanded to extreme poses, the robot hand IK may fail or produce jerky motion. Add joint limit constraints 10° inside mechanical limits and velocity damping near limits.
• Force feedback drift after 2+ hours: SenseGlove cable tension mechanisms drift thermally. Baseline the force feedback at session start and re-zero every 60 minutes.
• Finger IK not matching operator intent: This usually indicates hand geometry miscalibration. Rerun Step 1 and Step 2 of calibration. Check that finger segment lengths in the SDK match physical measurements to within 5 mm.
• Robot hand overheating: Dexterous hands running at high duty cycle for 2+ hours can overheat motor controllers. Monitor motor temperatures (Inspire RH56 logs temperatures via SDK). Pause for 5 minutes if any motor exceeds 65°C.

Data Logging Format for Glove Teleoperation

• /glove/finger_angles: Float array [16] — 4 DOF per finger × 4 fingers + thumb (5 DOF). At 100 Hz.
• /glove/fingertip_forces: Float array [5] — estimated normal force at each fingertip tip in Newtons. At 100 Hz.
• /hand/wrist_pose: Float array [7] — 3D position + quaternion of wrist in robot base frame. At 50 Hz.
• /robot_hand/joint_positions: Float array [6–20 depending on hand] — actual commanded/measured joint positions. At 50 Hz.
• /observations/images/cam_wrist: RGB [480×640×3] close-range wrist camera at 60 fps for finger-object contact visibility.
• Store in HDF5 with per-episode grouping. For compatibility with ACT, extract /glove/finger_angles as the action vector and /robot_hand/joint_positions as the observation. See the data formats guide for conversion details.

Glove vs. Alternative Input Methods: When to Use What

The key decision: if your task requires individual finger control, use gloves. If it requires only arm + gripper open/close, use a leader arm or SpaceMouse. Gloves produce 2-3x lower throughput than leader arms, so the higher fidelity must justify the slower collection rate.

Feedback Modalities: Haptic, Visual, and Auditory

Operator performance improves dramatically with multi-modal feedback. Each modality addresses a different information channel:

• Haptic (force feedback): SenseGlove and HaptX provide resistance when robot fingers contact objects. This is the most valuable feedback modality -- operators with haptic feedback produce 30-40% fewer failed grasps than those with visual-only feedback. Force feedback also prevents over-gripping (crushing fragile objects) by letting operators feel the grip force.
• Visual (camera feeds): A wrist camera view showing the robot fingers and object is essential. Use a 60 fps stream for responsive visual feedback. Add a depth overlay (RealSense D405 depth map) to help operators judge distance. Display the stream on a head-mounted display (Quest 3) for immersion, or a large monitor at eye level for reduced fatigue.
• Auditory (contact sounds): Synthesize audio feedback from F/T sensor data: a tone that increases in pitch as contact force increases. This provides force awareness without requiring haptic hardware. Use a simple mapping: frequency = 200 Hz + (force_N * 100 Hz), clamped at 1500 Hz. Play through headphones to avoid disturbing other operators.
• Combined feedback: The highest-quality dexterous data collection uses all three: haptic gloves for force awareness, VR headset for immersive visual, and audio cues for contact confirmation. This triple-modality setup produces data quality comparable to 2x the demonstrations collected with visual-only feedback.

Paxini Tactile Sensor Integration

For teams using Paxini tactile sensors on their dexterous hands, the tactile data enriches demonstration quality significantly:

• Sensor placement: Mount Paxini sensors on the fingertip pads of the robot hand (not the glove). Each sensor provides a 4x4 taxel array with 0.05 N resolution per taxel at 100 Hz.
• Data logging: Add /paxini/taxel_array (Float32MultiArray, 16 values per finger, 5 fingers) at 100 Hz to your HDF5 recording. This provides contact geometry data that policies use for slip detection and grasp force regulation.
• Glove-to-tactile correlation: During calibration, have the operator grasp a series of reference objects (rigid ball, soft sponge, thin card). Record the correlation between glove finger angles and Paxini contact patterns. This calibration data helps validate that the glove-robot mapping produces expected contact behavior.

Related Guides

• Bimanual Teleoperation Setup -- dual-glove bimanual configurations
• Force/Torque Sensor Selection -- wrist F/T sensors that complement glove data
• Data Formats: HDF5, RLDS, and LeRobot -- storing glove + tactile data in standard formats
• How to Set Up a Teleoperation Lab -- physical setup for glove teleoperation stations
• Operator Recruitment and Training -- training operators for glove-based collection
• Teleoperation Solution Buyer's Guide -- cost analysis including glove systems

Work with SVRC

SVRC operates SenseGlove + Inspire RH56 and SenseGlove + Orca Hand systems at our Mountain View and Allston facilities.

• Data Collection Services -- finger-level dexterous manipulation data collection with trained operators
• Hardware Store -- purchase Paxini tactile sensors, Orca Hand, and glove accessories
• Robot Leasing -- lease complete glove teleoperation stations including hand, glove, and compute
• Data Platform -- upload, QA, and convert dexterous manipulation datasets
• Contact Us -- discuss your dexterous manipulation data collection needs