CogExplore: Contextual Exploration with Language-Encoded Environment Representations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Biggie, Harel, Cooper, Patrick, Albin, Doncey, Such, Kristen, Heckman, Christoffer
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910500220043264
author Biggie, Harel
Cooper, Patrick
Albin, Doncey
Such, Kristen
Heckman, Christoffer
author_facet Biggie, Harel
Cooper, Patrick
Albin, Doncey
Such, Kristen
Heckman, Christoffer
contents Integrating language models into robotic exploration frameworks improves performance in unmapped environments by providing the ability to reason over semantic groundings, contextual cues, and temporal states. The proposed method employs large language models (GPT-3.5 and Claude Haiku) to reason over these cues and express that reasoning in terms of natural language, which can be used to inform future states. We are motivated by the context of search-and-rescue applications where efficient exploration is critical. We find that by leveraging natural language, semantics, and tracking temporal states, the proposed method greatly reduces exploration path distance and further exposes the need for environment-dependent heuristics. Moreover, the method is highly robust to a variety of environments and noisy vision detections, as shown with a 100% success rate in a series of comprehensive experiments across three different environments conducted in a custom simulation pipeline operating in Unreal Engine.
format Preprint
id arxiv_https___arxiv_org_abs_2406_17180
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CogExplore: Contextual Exploration with Language-Encoded Environment Representations
Biggie, Harel
Cooper, Patrick
Albin, Doncey
Such, Kristen
Heckman, Christoffer
Robotics
I.2.9
Integrating language models into robotic exploration frameworks improves performance in unmapped environments by providing the ability to reason over semantic groundings, contextual cues, and temporal states. The proposed method employs large language models (GPT-3.5 and Claude Haiku) to reason over these cues and express that reasoning in terms of natural language, which can be used to inform future states. We are motivated by the context of search-and-rescue applications where efficient exploration is critical. We find that by leveraging natural language, semantics, and tracking temporal states, the proposed method greatly reduces exploration path distance and further exposes the need for environment-dependent heuristics. Moreover, the method is highly robust to a variety of environments and noisy vision detections, as shown with a 100% success rate in a series of comprehensive experiments across three different environments conducted in a custom simulation pipeline operating in Unreal Engine.
title CogExplore: Contextual Exploration with Language-Encoded Environment Representations
topic Robotics
I.2.9
url https://arxiv.org/abs/2406.17180