Contact onset and grip evolution are under-captured
Most capture setups miss touch timing, pressure trends, and the subtle grip adjustments that decide contact-rich tasks.
Tactile capture hardware for the next generation of dexterous robots — gloves that feel, and custom skin molded to robot hands.
Robots have five senses. We are building the sixth.
Most capture setups miss touch timing, pressure trends, and the subtle grip adjustments that decide contact-rich tasks.
Standalone sensors and DIY recording scripts fall down on calibration, synchronization, and the reliability real capture demands.
Robot-learning teams want to record their own demonstrations on day one, not spend months sourcing sensors, wiring rigs, and debugging sync.
For contact-rich tasks, the next performance gains come from better multimodal demonstrations, not model scale alone.
Hardware, sync, calibration, packaging — one stack, four stages. You capture your own demonstrations and get aligned episodes, not raw folders.
High-rate contact and pressure-aligned streams with per-channel calibration — where touch matters for the task.
First-person RGB aligned to what the demonstrator sees — stable exposure for long household runs.
Per-frame depth aligned to ego timebase for geometry, reach, and clutter around the hands.
Articulated hand state and grasp phases for contact-rich manipulation — not just 2D boxes in frame.
Linear acceleration, angular rates, and movement cues that characterize inertia, rhythm, and effort during the task.
Secondary viewpoints for occlusion recovery, tool use, and context beyond the ego cone (roadmap / program-dependent).
Task and subtask boundaries, contact phases, QC flags — plus optional timestamped, frame-aligned text narration paired to video for richer training supervision.
Binary or graded success, failure modes, and segment-level tags for imitation and evaluation.
We document where each signal is reliable, how drift is handled, and what should never be treated as ground-truth force.
Pressure proxies, contact timing, and failure flags are defined so policy teams know exactly what each dimension means.
Episodes land in the formats your trainers expect, with QC metrics and assumptions — not a dump of raw sensor folders.