Salvato in:
Dettagli Bibliografici
Autori principali: Yuan, Shuaihang, Unlu, Halil Utku, Huang, Hao, Wen, Congcong, Tzes, Anthony, Fang, Yi
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2410.21037
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914993741496320
author Yuan, Shuaihang
Unlu, Halil Utku
Huang, Hao
Wen, Congcong
Tzes, Anthony
Fang, Yi
author_facet Yuan, Shuaihang
Unlu, Halil Utku
Huang, Hao
Wen, Congcong
Tzes, Anthony
Fang, Yi
contents In this paper, we present a novel method for reliable frontier selection in Zero-Shot Object Goal Navigation (ZS-OGN), enhancing robotic navigation systems with foundation models to improve commonsense reasoning in indoor environments. Our approach introduces a multi-expert decision framework to address the nonsensical or irrelevant reasoning often seen in foundation model-based systems. The method comprises two key components: Diversified Expert Frontier Analysis (DEFA) and Consensus Decision Making (CDM). DEFA utilizes three expert models: furniture arrangement, room type analysis, and visual scene reasoning, while CDM aggregates their outputs, prioritizing unanimous or majority consensus for more reliable decisions. Demonstrating state-of-the-art performance on the RoboTHOR and HM3D datasets, our method excels at navigating towards untrained objects or goals and outperforms various baselines, showcasing its adaptability to dynamic real-world conditions and superior generalization capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2410_21037
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring the Reliability of Foundation Model-Based Frontier Selection in Zero-Shot Object Goal Navigation
Yuan, Shuaihang
Unlu, Halil Utku
Huang, Hao
Wen, Congcong
Tzes, Anthony
Fang, Yi
Robotics
In this paper, we present a novel method for reliable frontier selection in Zero-Shot Object Goal Navigation (ZS-OGN), enhancing robotic navigation systems with foundation models to improve commonsense reasoning in indoor environments. Our approach introduces a multi-expert decision framework to address the nonsensical or irrelevant reasoning often seen in foundation model-based systems. The method comprises two key components: Diversified Expert Frontier Analysis (DEFA) and Consensus Decision Making (CDM). DEFA utilizes three expert models: furniture arrangement, room type analysis, and visual scene reasoning, while CDM aggregates their outputs, prioritizing unanimous or majority consensus for more reliable decisions. Demonstrating state-of-the-art performance on the RoboTHOR and HM3D datasets, our method excels at navigating towards untrained objects or goals and outperforms various baselines, showcasing its adaptability to dynamic real-world conditions and superior generalization capabilities.
title Exploring the Reliability of Foundation Model-Based Frontier Selection in Zero-Shot Object Goal Navigation
topic Robotics
url https://arxiv.org/abs/2410.21037