Salvato in:
Dettagli Bibliografici
Autori principali: Terashima, Kouki, Iwata, Daiki, Tanaka, Kanji
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2409.14899
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914955159142400
author Terashima, Kouki
Iwata, Daiki
Tanaka, Kanji
author_facet Terashima, Kouki
Iwata, Daiki
Tanaka, Kanji
contents This work explores the potential of brief inter-agent knowledge transfer (KT) to enhance the robotic object goal navigation (ON) in unseen and unfamiliar environments. Drawing on the analogy of human travelers acquiring local knowledge, we propose a framework in which a traveler robot (student) communicates with local robots (teachers) to obtain ON knowledge through minimal interactions. We frame this process as a data-free continual learning (CL) challenge, aiming to transfer knowledge from a black-box model (teacher) to a new model (student). In contrast to approaches like zero-shot ON using large language models (LLMs), which utilize inherently communication-friendly natural language for knowledge representation, the other two major ON approaches -- frontier-driven methods using object feature maps and learning-based ON using neural state-action maps -- present complex challenges where data-free KT remains largely uncharted. To address this gap, we propose a lightweight, plug-and-play KT module targeting non-cooperative black-box teachers in open-world settings. Using the universal assumption that every teacher robot has vision and mobility capabilities, we define state-action history as the primary knowledge base. Our formulation leads to the development of a query-based occupancy map that dynamically represents target object locations, serving as an effective and communication-friendly knowledge representation. We validate the effectiveness of our method through experiments conducted in the Habitat environment.
format Preprint
id arxiv_https___arxiv_org_abs_2409_14899
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle CON: Continual Object Navigation via Data-Free Inter-Agent Knowledge Transfer in Unseen and Unfamiliar Places
Terashima, Kouki
Iwata, Daiki
Tanaka, Kanji
Robotics
Computer Vision and Pattern Recognition
Machine Learning
This work explores the potential of brief inter-agent knowledge transfer (KT) to enhance the robotic object goal navigation (ON) in unseen and unfamiliar environments. Drawing on the analogy of human travelers acquiring local knowledge, we propose a framework in which a traveler robot (student) communicates with local robots (teachers) to obtain ON knowledge through minimal interactions. We frame this process as a data-free continual learning (CL) challenge, aiming to transfer knowledge from a black-box model (teacher) to a new model (student). In contrast to approaches like zero-shot ON using large language models (LLMs), which utilize inherently communication-friendly natural language for knowledge representation, the other two major ON approaches -- frontier-driven methods using object feature maps and learning-based ON using neural state-action maps -- present complex challenges where data-free KT remains largely uncharted. To address this gap, we propose a lightweight, plug-and-play KT module targeting non-cooperative black-box teachers in open-world settings. Using the universal assumption that every teacher robot has vision and mobility capabilities, we define state-action history as the primary knowledge base. Our formulation leads to the development of a query-based occupancy map that dynamically represents target object locations, serving as an effective and communication-friendly knowledge representation. We validate the effectiveness of our method through experiments conducted in the Habitat environment.
title CON: Continual Object Navigation via Data-Free Inter-Agent Knowledge Transfer in Unseen and Unfamiliar Places
topic Robotics
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2409.14899