Success Classification for Object Navigation
Name
Yue-ayue-meng-eecs-2022-thesis.pdf
Description
Thesis PDF
Size
9.32 MB
Format
Adobe PDF
Checksum (MD5)
671c3884ce22ab9b3a4815c63dfbfc5b
Author(s)
Yue, Albert
Advisor(s)
Agrawal, Pulkit
Date Issued
May 2022
Publisher
Massachusetts Institute of Technology
Abstract
Object navigation is the embodied task of navigating to an instance of a specified object in unseen environments. Previous work has made impressive progress on the problem, but there remains much room for improvement with current state-of-the-art methods reaching a success rate of less than one in three. In this work, we evaluate a state-of-the-art approach, identifying false positives in object detection as the main point of failure. We propose introducing a new module to verify success when the agent attempts to stop. We introduce a learning-based classifier that learns and compares embeddings for visual observations and object categories and find that it works well at predicting success, outperforming both naive baselines and a heuristic-based classifier. We also find no improvement when using a ensemble model for semantic segmentation, although we believe there is more to be tested before arriving at a conclusive judgement.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
