# Relationship-Aware Hierarchical 3D Scene Graph for Task Reasoning

Source: [Relationship-Aware Hierarchical 3D Scene Graph for Task Reasoning](<https://www.sota2.com/research/paper/69818202a8b01e76cc8e2a15>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-04T05:00:24.095Z

Authors: Albert Gassol Puigjaner, Angelos Zacharia, Kostas Alexis

Published: 2026-02-02T18:47:02.000Z

## Abstract

Representing and understanding 3D environments in a structured manner is crucial for autonomous agents to navigate and reason about their surroundings. While traditional Simultaneous Localization and Mapping (SLAM) methods generate metric reconstructions and can be extended to metric-semantic mapping, they lack a higher level of abstraction and relational reasoning. To address this gap, 3D scene graphs have emerged as a powerful representation for capturing hierarchical structures and object relationships. In this work, we propose an enhanced hierarchical 3D scene graph that integrates open-vocabulary features across multiple abstraction levels and supports object-relational reasoning. Our approach leverages a Vision Language Model (VLM) to infer semantic relationships. Notably, we introduce a task reasoning module that combines Large Language Models (LLM) and a VLM to interpret the scene graph's semantic and relational information, enabling agents to reason about tasks and interact with their environment more intelligently. We validate our method by deploying it on a quadruped robot in multiple environments and tasks, highlighting its ability to reason about them.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Open-Vocabulary Object Retrieval on HM3DSem 25](<https://www.sota2.com/research/sota/open-vocabulary-object-retrieval-on-hm3dsem-25.md>): Open-Vocabulary Object Retrieval; HM3DSem 25; Accuracy@5: 37.72.

- [Open-Vocabulary Object Retrieval on Replica 26](<https://www.sota2.com/research/sota/open-vocabulary-object-retrieval-on-replica-26.md>): Open-Vocabulary Object Retrieval; Replica 26; Acc@5: 53.99.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2602.02456>)

[PDF](<https://arxiv.org/pdf/2602.02456.pdf>)