Task-Driven Graph Attention for Hierarchical Relational Object Navigation

TL;DR

This paper introduces a task-driven graph attention method for hierarchical relational object navigation, enabling embodied AI agents to efficiently find objects in large, complex scenes by reasoning about object relations using scene graphs and graph neural networks.

Contribution

It proposes a novel approach combining scene graphs, graph neural networks, and task-driven attention for improved hierarchical object navigation in large environments.

Findings

Scene graphs outperform images and maps for this task.

The proposed method shows better scalability and learning efficiency.

Experimental results demonstrate superior performance over baselines.

Abstract

Embodied AI agents in large scenes often need to navigate to find objects. In this work, we study a naturally emerging variant of the object navigation task, hierarchical relational object navigation (HRON), where the goal is to find objects specified by logical predicates organized in a hierarchical structure - objects related to furniture and then to rooms - such as finding an apple on top of a table in the kitchen. Solving such a task requires an efficient representation to reason about object relations and correlate the relations in the environment and in the task goal. HRON in large scenes (e.g. homes) is particularly challenging due to its partial observability and long horizon, which invites solutions that can compactly store the past information while effectively exploring the scene. We demonstrate experimentally that scene graphs are the best-suited representation compared to conventional representations such as images or 2D maps. We propose a solution that uses scene graphs as part of its input and integrates graph neural networks as its backbone, with an integrated task-driven attention mechanism, and demonstrate its better scalability and learning efficiency than state-of-the-art baselines.