Imperial College team raises $40M for Instant Policy, a graph-diffusion imitation learning robot startup
philfung · x · 2026-11-03
A team from Imperial College raised $40M to build Instant Policy, which formulates In-Context Imitation Learning as a graph generation problem solved via a learned diffusion process (ICLR 2025 Oral, Best Paper at the ICLR 2025 Robot Learning Workshop).
- Robots acquire new tasks instantly from just one or two demonstrations
- Trained on simulated pseudo-demonstrations, providing a virtually infinite data pool
- Validated in both simulation and real-world everyday tasks, and can serve as a foundation for cross-embodiment and zero-shot transfer to language-defined tasks
Related event: Imperial College Team Raises $40M for Graph-Based Rapid Imitation Learning(2 posts)→
More from Embodied
- PanoTac: a dense three-axis tactile sensor letting robots feel when a stopper releases — Haoyu_Xiong_ · 2026-11-04
- Ropedia week in review: how human first-person data becomes real robot capability — liuziwei7 · 2026-11-04
- Walden Robotics: full production shifts in factories are shaping its robot development — adnothing · 2026-11-04
- Imperial College team raises $40M for graph-generation fast imitation learning — k7agar · 2026-11-04
- Hugging Face's Reachy Mini robot just got a hoverboard — huggingface · 2026-11-03
- University of Chicago unveils RingIO: an eyes-free ring with touch as both input and output — plopesresearch · 2026-11-03