

Shared by @ChinaScience ↗Recent foundation image and video generation models offer strong generalization and controllability, but their direct application to embodied scenarios is limited by requirements for multi-view consistency, geometric coherence, and robot embodiment constr
Shared by @chris_j_paxton ↗

TechEBlogBoston Dynamics’ Spot Robot Crosses the Last Fifty Feet to Your Door
With Kushal Kedia and Tyler Lum
Do language models’ strengths transfer to robotics? Can a model perceive a scene, understand a particular robot’s state, and issue actions that reliably effect change in the physical world? We ran tests to find out.


Shared by @chris_j_paxton ↗

Shared by @pmarca ↗

Shared by @chris_j_paxton ↗
Shared by @Scobleizer ↗
thehumanoid.ai6d ago

Shared by @Scobleizer ↗
alibaba-damo-academy.github.io7d agoRobotic manipulation in the open world requires not only recognizing what a scene looks like, but also anticipating how its 3D structure moves under interaction. We argue that synchronized RGB, depth, and optical flow, namely RGB-DF, provide a physically

Shared by @theproof ↗