Preprint
Oct 2026
Foundation-Model-Driven 3D Scene Graphs for Mobile Manipulation
Geometric and Semantic Foundation models are becoming increasingly popular tools for generating spatial maps for robots. Recent work (e.g., FOUND-IT) has leveraged these tools to construct real-time, task-driven, and open-set 3D scene graphs from a single uncalibrated camera. However, while classical robot mapping tech...
Dominic Maggio, Lorenzo Shaikewitz, A. Naveen et al.
· 0 citations