Agent-Centric Relation Graph for Object Visual Navigation
This work addresses the problem of enabling agents to navigate toward target objects based on visual observations, which is incremental as it builds on existing navigation methods with a new graph-based approach.
The paper tackles object visual navigation by introducing an Agent-Centric Relation Graph (ACRG) to learn visual representations based on environmental relationships, and it demonstrates that ACRG significantly outperforms state-of-the-art methods in unseen testing environments in AI2-THOR.
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.