Prior research on learning from humans often requires real human demonstrations. But advances in video generation models offer a new paradigm: we can now prompt these generators to make synthetic videos of the task. On the plus side, these synthetic videos take place in the robot's current environment, and do not requi...
Yin-Long Dai, Homanga Bharadhwaj, Dylan P. Losey· 0 citations
Overall, the results suggest that scaling ego-centric data brings agent modeling close to its limit while leaving its effects on the world far behind, and that closing this gap will depend on how models are trained, not only on how much data they see.
Jia-Hua Dong, Anurag Bagchi, Yash Jangir et al.· 0 citations
Human videos contain rich causal evidence for robot manipulation: they reveal how hand motion induces object motion and produces task-relevant changes in object state. In this work, we study articulated objects such as doors, drawers, cabinets, laptops, ovens, and hinged containers that are ubiquitous in daily life and...
This work studies how to learn anticipation of how objects move during human-object interaction from ordinary monocular videos of human-object interaction, and shows that it can efficiently re-purpose video priors into explicit geometric forecasts for embodied intelligence.
