Agent-Centric Relation Graph for Object Visual Navigation

TL;DR

This paper introduces an agent-centric relation graph (ACRG) that enhances object visual navigation by modeling horizontal and distance relationships, leading to improved performance in unseen environments.

Contribution

The paper proposes a novel ACRG structure combining horizontal and distance relationship graphs to improve visual navigation accuracy.

Findings

ACRG outperforms state-of-the-art methods in AI2-THOR environments.

The use of depth and vertical cues improves environment perception.

Significant generalization to unseen environments was achieved.

Abstract

Object visual navigation aims to steer an agent toward a target object based on visual observations. It is highly desirable to reasonably perceive the environment and accurately control the agent. In the navigation task, we introduce an Agent-Centric Relation Graph (ACRG) for learning the visual representation based on the relationships in the environment. ACRG is a highly effective structure that consists of two relationships, i.e., the horizontal relationship among objects and the distance relationship between the agent and objects . On the one hand, we design the Object Horizontal Relationship Graph (OHRG) that stores the relative horizontal location among objects. On the other hand, we propose the Agent-Target Distance Relationship Graph (ATDRG) that enables the agent to perceive the distance between the target and objects. For ATDRG, we utilize image depth to obtain the target distance and imply the vertical location to capture the distance relationship among objects in the vertical direction. With the above graphs, the agent can perceive the environment and output navigation actions. Experimental results in the artificial environment AI2-THOR demonstrate that ACRG significantly outperforms other state-of-the-art methods in unseen testing environments.