Hierarchical Object-to-Zone Graph for Object Navigation

TL;DR

This paper introduces a hierarchical object-to-zone graph to improve object navigation in unseen environments, enabling better guidance and decision-making through a coarse-to-fine planning approach and online learning.

Contribution

It presents a novel hierarchical graph structure and an online learning mechanism to enhance navigation accuracy and adaptability in unseen environments.

Findings

The method outperforms baseline models on AI2-Thor in SR and SPL metrics.

The proposed SAE metric effectively measures action efficiency.

Online updating of the HOZ graph improves navigation success.

Abstract

The goal of object navigation is to reach the expected objects according to visual information in the unseen environments. Previous works usually implement deep models to train an agent to predict actions in real-time. However, in the unseen environment, when the target object is not in egocentric view, the agent may not be able to make wise decisions due to the lack of guidance. In this paper, we propose a hierarchical object-to-zone (HOZ) graph to guide the agent in a coarse-to-fine manner, and an online-learning mechanism is also proposed to update HOZ according to the real-time observation in new environments. In particular, the HOZ graph is composed of scene nodes, zone nodes and object nodes. With the pre-learned HOZ graph, the real-time observation and the target goal, the agent can constantly plan an optimal path from zone to zone. In the estimated path, the next potential zone is regarded as sub-goal, which is also fed into the deep reinforcement learning model for action prediction. Our methods are evaluated on the AI2-Thor simulator. In addition to widely used evaluation metrics SR and SPL, we also propose a new evaluation metric of SAE that focuses on the effective action rate. Experimental results demonstrate the effectiveness and efficiency of our proposed method.