arXiv cs.AI· Martin B\"uchner, Adrian R\"ofer, Tim Engelbracht, Tim Welschehold, Zuria Bauer, Hermann Blum, Marc Pollefeys, Abhinav Valada·· 3 天前AI 评分29
MoMa-SG：面向开放世界移动操作的铰接式 3D 场景图
Articulated 3D Scene Graphs for Open-World Mobile Manipulation
AI 导读
MoMa-SG 是一个构建铰接场景语义-运动学 3D 场景图的框架，通过遮挡鲁棒的点跟踪与统一 twist 估计，在单次优化中稳健估计旋转和移动关节参数。研究同时发布 Arti4D-Semantic 数据集，涵盖 62 段真实 RGB-D 序列、600 次物体交互及三种观测范式，并提供容器与内含物体的父子关系标注。在四足机器人和移动操作平台上的真实实验验证了其对日常家居铰接物体的稳健操作能力。
正文 · 原文
Abstract:Semantic scene understanding has enabled robots to reason and perform affordance-driven object interaction. Despite this, real-world manipulation remains fundamentally limited by the inability to predict how objects move and are articulated. 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 containing multiple object articulations, we temporally segment object interactions and infer object motion using occlusion-robust point tracking. We lift point trajectories to 3D and estimate articulation models using a novel unified twist estimation formulation that robustly estimates revolute and prismatic joint parameters in a single optimization pass. Next, we associate objects with articulations and detect contained objects by reasoning over parent-child relations at identified opening states. We also introduce the Arti4D-Semantic dataset, which provides parent-child relation annotations between container and contained objects together with object axis annotations across 62 in-the-wild RGB-D sequences containing 600 object interactions and three distinct observation paradigms. We extensively evaluate the performance of MoMa-SG on two datasets and ablate key design choices of our approach. In addition, real-world experiments on both a quadruped and a mobile manipulator demonstrate robust manipulation of articulated objects in everyday home environments. We provide code and data at: this https URL.
| Comments: | 10th Conference on Robot Learning (CoRL 2026) |
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2602.16356 [cs.RO] |
| (or arXiv:2602.16356v2 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2602.16356 arXiv-issued DOI via DataCite |
Submission history
From: Martin Alexander Büchner [view email]
[v1]
Wed, 18 Feb 2026 10:40:35 UTC (21,322 KB)
[v2]
Mon, 12 Oct 2026 21:08:07 UTC (34,519 KB)
来源：arXiv cs.AI · arxiv.org