Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Dorbala, Vishnu Sashank, Mullen Jr., James F., Manocha, Dinesh
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916203831754752
author Dorbala, Vishnu Sashank
Mullen Jr., James F.
Manocha, Dinesh
author_facet Dorbala, Vishnu Sashank
Mullen Jr., James F.
Manocha, Dinesh
contents We present LGX (Language-guided Exploration), a novel algorithm for Language-Driven Zero-Shot Object Goal Navigation (L-ZSON), where an embodied agent navigates to a uniquely described target object in a previously unseen environment. Our approach makes use of Large Language Models (LLMs) for this task by leveraging the LLM's commonsense reasoning capabilities for making sequential navigational decisions. Simultaneously, we perform generalized target object detection using a pre-trained Vision-Language grounding model. We achieve state-of-the-art zero-shot object navigation results on RoboTHOR with a success rate (SR) improvement of over 27% over the current baseline of the OWL-ViT CLIP on Wheels (OWL CoW). Furthermore, we study the usage of LLMs for robot navigation and present an analysis of various prompting strategies affecting the model output. Finally, we showcase the benefits of our approach via \textit{real-world} experiments that indicate the superior performance of LGX in detecting and navigating to visually unique objects.
format Preprint
id arxiv_https___arxiv_org_abs_2303_03480
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation
Dorbala, Vishnu Sashank
Mullen Jr., James F.
Manocha, Dinesh
Robotics
Artificial Intelligence
Computation and Language
We present LGX (Language-guided Exploration), a novel algorithm for Language-Driven Zero-Shot Object Goal Navigation (L-ZSON), where an embodied agent navigates to a uniquely described target object in a previously unseen environment. Our approach makes use of Large Language Models (LLMs) for this task by leveraging the LLM's commonsense reasoning capabilities for making sequential navigational decisions. Simultaneously, we perform generalized target object detection using a pre-trained Vision-Language grounding model. We achieve state-of-the-art zero-shot object navigation results on RoboTHOR with a success rate (SR) improvement of over 27% over the current baseline of the OWL-ViT CLIP on Wheels (OWL CoW). Furthermore, we study the usage of LLMs for robot navigation and present an analysis of various prompting strategies affecting the model output. Finally, we showcase the benefits of our approach via \textit{real-world} experiments that indicate the superior performance of LGX in detecting and navigating to visually unique objects.
title Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigation
topic Robotics
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2303.03480