← Back to Benchmarks
simmediummanipulation-datametric · varies

Articulated 3D Scene Graphs for Open-World Mobile Manipulation

Description

Semantics has enabled 3D scene understanding and affordance-driven object interaction. However, robots operating in real-world environments face a critical limitation: they cannot anticipate how objects move. Long-horizon mobile manipulation requires closing the gap between semantics, geometry, and kinematics. In this work, we present MoMa-SG, a novel framework for building semantic-kinematic 3D scene graphs of articulated scenes containing a myriad of interactable objects. Given RGB-D sequences

Source

http://arxiv.org/abs/2602.16356v1