Stanford Research: Robot Learns New Tasks via Single Demo with BPP
Haoyu_Xiong_ · x · 2026-08-27
Researchers from Stanford and UC Berkeley released Behavior Prompting Policy (BPP), enabling robots to perform new tasks at inference time using a single human demonstration without fine-tuning.
Core Contributions:
- BPP Architecture: An in-context visuomotor policy translating behavior prompts (demo sequences) and observations into actions.
- iPhUMI: A handheld manipulation interface for collecting diverse behavior prompts.
Key Findings:
- Task diversity drives prompting capability more than the number of demos per task.
- Behavior prompts act as dense sub-goal conditioning.
Open Source & Eval:
- Released BPP code, iPhUMI code, and simulation benchmarks.
- Introduced DrawAnything and LIBERO-Gen benchmarks to evaluate test-time adaptation.
More from Embodied
- Chinese startup DexForce trains humanoid robots with virtual data to slash costs — pstAsiatech · 2026-10-15
- EmbodiedEvo tops RoboDojo at 38.95% success by letting robots inherit failed practice — thetripathi58 · 2026-10-15
- VR dev's one line stuns a Quest 3 owner who played 3 games for 12 months ignoring mixed reality — Aiden_Tech_Ai · 2026-10-15
- ROBIB robotics meetup #3 lands in Ghent on Nov 19 with academic and industry speakers — MarwaEldiwiny · 2026-10-15
- How 3D Gaussian Splatting gives robots spatial memory of what's out of view — TheTuringPost · 2026-10-15
- RTX Spark closes the gap with M5 Macs, ushering in an "age of preference" for PC buyers — BenBajarin · 2026-10-15