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.
@article{arxiv.2410.21926,
title = {Reliable Semantic Understanding for Real World Zero-shot Object Goal Navigation},
author = {Halil Utku Unlu and Shuaihang Yuan and Congcong Wen and Hao Huang and Anthony Tzes and Yi Fang},
journal= {arXiv preprint arXiv:2410.21926},
year = {2024}
}