EgoExplorer: 100-hour vision-motion-touch dataset for humanoid loco-manipulation
InternRobotics · hf · 2026-10-14
EgoExplorer is a 100-hour multimodal observatory of human loco-manipulation, capturing egocentric video, whole-body motion, fine-grained finger articulation and tactile signals via a wearable rig, with step-level descriptions focused on professional activities. A Calibrate-Complete-Constrain pipeline handles sparse body sensing, cutting body-point error by 71.9% versus the strongest baseline, with gains in hand stability and contact estimation; preliminary studies cover multimodal generation and humanoid retargeting with whole-body control in simulation.
More from Embodied
- Visor: open-source Android app replaces the Meta AI app on Ray-Ban Meta glasses with your own model — jedisct1 · 2026-10-14
- 304 robotics papers hit arXiv in a single day as the field explodes — DJiafei · 2026-10-14
- NTU's COAP: code replaces LLMs in the robot control loop, hitting 75% on 42 bimanual tasks — liuziwei7 · 2026-10-14
- WAVE-0 adds a 257M world model to VLA, lifting real-world success from 38.3% to 73.3% — Haomin Wang · 2026-10-14
- Robot tablecloth demo works via staged repair loop: rule-based checks plus learned policies — arankomatsuzaki · 2026-10-14
- 99%+ data gap: Sophia Capital partner on embodied-AI investing — 创业邦 · 2026-10-14