Hierarchical Object-to-Zone Graph for Object Navigation
- URL: http://arxiv.org/abs/2109.02066v2
- Date: Thu, 9 Sep 2021 08:59:23 GMT
- Title: Hierarchical Object-to-Zone Graph for Object Navigation
- Authors: Sixian Zhang, Xinhang Song, Yubing Bai, Weijie Li, Yakui Chu, Shuqiang
Jiang
- Abstract summary: In the unseen environment, when the target object is not in egocentric view, the agent may not be able to make wise decisions.
We propose a hierarchical object-to-zone (HOZ) graph to guide the agent in a coarse-to-fine manner.
Online-learning mechanism is also proposed to update HOZ according to the real-time observation in new environments.
- Score: 43.558927774552295
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- 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.
Related papers
Err
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.