MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments
Authors:
- Yirum KimYKYirum Kim
- Jaewoo KimJKJaewoo Kim
- Ue-Hwan KimUKUe-Hwan Kim
Preprint
Abstract
Current 3D scene graph generation (3DSGG) approaches heavily rely on a single-agent assumption and small-scale environments, exhibiting limited scalability to real-world scenarios. In this work, we introduce Multi-Agent 3D Scene Graph Generation (MA3DSG) model, the first framework designed to tackle this scalability challenge using multiple agents. We develop a training-free graph alignment algorithm that efficiently merges partial query graphs from individual agents into a unified global scene graph. Leveraging extensive analysis and empirical insights, our approach enables conventional single-agent systems to operate collaboratively without requiring any learnable parameters. To rigorously evaluate 3DSGG performance, we propose MA3DSG-Bench-a benchmark that supports diverse agent configurations, domain sizes, and environmental conditions-providing a more general and extensible evaluation framework. This work lays a solid foundation for scalable, multi-agent 3DSGG research.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Deep Reinforcement Learning-Based Large-Scale Robot ExplorationIEEE Robotics and Automation Letters, 2024
- Graph Neural Network Methods and Applications in Scene Understanding2024
- Swarm-SLAM: Sparse Decentralized Collaborative Simultaneous Localization and Mapping Framework for Multi-Robot SystemsIEEE Robotics and Automation Letters, 2023
- Multi-Domain Cooperative SLAM: The Enabler for Integrated Sensing and CommunicationsIEEE Wireless Communications, 2023
- Behavioral Assessment of a Humanoid Robot When Attracting Pedestrians in a MallInternational Journal of Social Robotics, 2022
- Learning 3D Semantic Scene Graphs with Instance EmbeddingsInternational Journal of Computer Vision, 2022
- Learning visual relationship and context-aware attention for image captioningPattern Recognition, 2020
- 3D Scene Graph: A Structure for Unified Semantics, 3D Space, and Camera2019
- Collaborative visual SLAM for multiple agents:A brief surveyVirtual Reality & Intelligent Hardware, 2019
- Fifty years of graph matching, network alignment and network comparisonInformation Sciences, 2016