Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multi-Modal 3D Scene Graph Updater for Shared and Dynamic Environments

Emilio Olivastri, Jonathan Francis, Alberto Pretto, Niko Sünderhauf, Krishan Rana

TL;DR

This work proposes a framework that leverages these multimodal inputs to maintain the consistency of scene graphs during real-time operation, presenting promising initial results and outlining a roadmap for future research.

Abstract

The advent of generalist Large Language Models (LLMs) and Large Vision Models (VLMs) have streamlined the construction of semantically enriched maps that can enable robots to ground high-level reasoning and planning into their representations. One of the most widely used semantic map formats is the 3D Scene Graph, which captures both metric (low-level) and semantic (high-level) information. However, these maps often assume a static world, while real environments, like homes and offices, are dynamic. Even small changes in these spaces can significantly impact task performance. To integrate robots into dynamic environments, they must detect changes and update the scene graph in real-time. This update process is inherently multimodal, requiring input from various sources, such as human agents, the robot's own perception system, time, and its actions. This work proposes a framework that leverages these multimodal inputs to maintain the consistency of scene graphs during real-time operation, presenting promising initial results and outlining a roadmap for future research.

Multi-Modal 3D Scene Graph Updater for Shared and Dynamic Environments

TL;DR

This work proposes a framework that leverages these multimodal inputs to maintain the consistency of scene graphs during real-time operation, presenting promising initial results and outlining a roadmap for future research.

Abstract

The advent of generalist Large Language Models (LLMs) and Large Vision Models (VLMs) have streamlined the construction of semantically enriched maps that can enable robots to ground high-level reasoning and planning into their representations. One of the most widely used semantic map formats is the 3D Scene Graph, which captures both metric (low-level) and semantic (high-level) information. However, these maps often assume a static world, while real environments, like homes and offices, are dynamic. Even small changes in these spaces can significantly impact task performance. To integrate robots into dynamic environments, they must detect changes and update the scene graph in real-time. This update process is inherently multimodal, requiring input from various sources, such as human agents, the robot's own perception system, time, and its actions. This work proposes a framework that leverages these multimodal inputs to maintain the consistency of scene graphs during real-time operation, presenting promising initial results and outlining a roadmap for future research.

Paper Structure

This paper contains 11 sections, 1 equation, 1 figure, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Robot Learning in Non-Stationary Environments
  4. Problem Definition
  5. Methodology
  6. Minimal Required 3D Scene Graph
  7. Muti-Modal Change Detection
  8. Scene Graph Updater
  9. Experimental Setup
  10. Results
  11. Conclusion

Figures (1)

  • Figure 1: High-level overview of the proposed framework. The various modalities proposed for change detection are displayed (top). These modules leverage the latest version of the 3D scene graph to assess whether change has occurred. Update operations on the 3D scene graph (bottom) are applied agnostically, due to the use of a unified language.