Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/135905
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | ForeSI: Success-Aware Visual Navigation Agent |
Author: | Kazemi Moghaddam, M. Abbasnejad, E. Wu, Q. Qinfeng Shi, J. Van Den Hengel, A. |
Citation: | Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2022), 2022, pp.3401-3410 |
Publisher: | IEEE |
Publisher Place: | Online |
Issue Date: | 2022 |
Series/Report no.: | IEEE Winter Conference on Applications of Computer Vision |
ISBN: | 9781665409155 |
ISSN: | 2472-6737 |
Conference Name: | IEEE/CVF Winter Conference on Applications of Computer Vision (WACV) (4 Jan 2022 - 8 Jan 2022 : Waikoloa, Hawaii) |
Statement of Responsibility: | Mahdi Kazemi Moghaddam, Ehsan Abbasnejad, Qi Wu, Javen Qinfeng shi and Anton Van Den Hengel |
Abstract: | In this work, we present a method to improve the efficiency and robustness of the previous model-free Reinforcement Learning (RL) algorithms for the task of object-goal visual navigation. Despite achieving state-of-the-art results, one of the major drawbacks of those approaches is the lack of a forward model that informs the agent about the potential consequences of its actions, i.e., being model-free. In this work, we augment the model-free RL with such a forward model that can predict a representation of a future state, from the beginning of a navigation episode, if the episode were to be successful. Furthermore, in order for efficient training, we develop an algorithm to integrate a replay buffer into the model-free RL that alternates between training the policy and the forward model. We call our agent ForeSI; ForeSI is trained to imagine a future latent state that leads to success. By explicitly imagining such a state, during the navigation, our agent is able to take better actions leading to two main advantages: first, in the absence of an object detector, ForeSI presents a more robust policy, i.e., it leads to about 5% absolute improvement on the Success Rate (SR); second, when combined with an off the-shelf object detector to help better distinguish the target object, our method leads to about 3% absolute improvement on the SR and about 2% absolute improvement on Success weighted by inverse Path Length (SPL), i.e., presents higher efficiency. |
Keywords: | Vision for Robotics Multimedia Applications; Vision and Languages; Vision Systems and Applications; Visual Reasoning; Analysis and Understanding |
Rights: | ©2021 IEEE |
DOI: | 10.1109/WACV51458.2022.00346 |
Published version: | https://ieeexplore.ieee.org/xpl/conhome/9706406/proceeding |
Appears in Collections: | Australian Institute for Machine Learning publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.