Saved in:
Bibliographic Details
Main Authors: Unlu, Halil Utku, Yuan, Shuaihang, Wen, Congcong, Huang, Hao, Tzes, Anthony, Fang, Yi
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.21926
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912093198876672
author Unlu, Halil Utku
Yuan, Shuaihang
Wen, Congcong
Huang, Hao
Tzes, Anthony
Fang, Yi
author_facet Unlu, Halil Utku
Yuan, Shuaihang
Wen, Congcong
Huang, Hao
Tzes, Anthony
Fang, Yi
contents We introduce an innovative approach to advancing semantic understanding in zero-shot object goal navigation (ZS-OGN), enhancing the autonomy of robots in unfamiliar environments. Traditional reliance on labeled data has been a limitation for robotic adaptability, which we address by employing a dual-component framework that integrates a GLIP Vision Language Model for initial detection and an InstructionBLIP model for validation. This combination not only refines object and environmental recognition but also fortifies the semantic interpretation, pivotal for navigational decision-making. Our method, rigorously tested in both simulated and real-world settings, exhibits marked improvements in navigation precision and reliability.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21926
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reliable Semantic Understanding for Real World Zero-shot Object Goal Navigation
Unlu, Halil Utku
Yuan, Shuaihang
Wen, Congcong
Huang, Hao
Tzes, Anthony
Fang, Yi
Robotics
Artificial Intelligence
We introduce an innovative approach to advancing semantic understanding in zero-shot object goal navigation (ZS-OGN), enhancing the autonomy of robots in unfamiliar environments. Traditional reliance on labeled data has been a limitation for robotic adaptability, which we address by employing a dual-component framework that integrates a GLIP Vision Language Model for initial detection and an InstructionBLIP model for validation. This combination not only refines object and environmental recognition but also fortifies the semantic interpretation, pivotal for navigational decision-making. Our method, rigorously tested in both simulated and real-world settings, exhibits marked improvements in navigation precision and reliability.
title Reliable Semantic Understanding for Real World Zero-shot Object Goal Navigation
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2410.21926