X Square Robot's TwinDEX Wearable Collector Boosts Dexterous Data Throughput 5.3x
FellMentKE · x · 2026-09-02
Data collection is a major bottleneck in dexterous robot learning: on-robot teleoperation yields high-quality demos but is expensive, slow to reset, and requires the robot every time. Chinese startup X Square Robot's TwinDEX instead uses a wearable robotic end-effector to collect demonstrations from humans, then deploys the learned policy on a matched robot hand. Crucially it's not just motion tracking — the wearable and hand are co-designed to match kinematics, contact geometry, appearance, sensing, and timing. In evaluation, TwinDEX delivered up to 5.3x the effective throughput of on-robot teleoperation — an interesting route to scaling dexterous data.
Related event: X Square's TwinDEX: Wearable Data Capture Boosts Dexterous Robot Training(4 posts)→
More from Embodied
- Three Ultra bots coordinate box-building and packing at a live 3PL warehouse site — PTrubey · 2026-09-02
- LimX's semi-humanoid Tron2 pairs industrial arms with humanoid base for high-altitude work — CyberRobooo · 2026-09-02
- Yacine: Training Cross-Robot Generalist Models Is the Easiest Path to Sim2Real — yacineMTB · 2026-09-02
- DexForce W1 Pro wheeled humanoid shows off popcorn-scooping service skills — CyberRobooo · 2026-09-02
- MIT's CW-Net Explains Self-Driving Decisions Using Human-Readable Concepts — MIT News AI · 2026-09-02
- 2021's CABiNet beats YOLO26-sem on UAVid: +2.7 mIoU at 3x lower latency — Naive-Explanation940 · 2026-09-02