Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Quanting, Min, So Yeon, Ji, Pengliang, Yang, Yue, Zhang, Tianyi, Xu, Kedi, Bajaj, Aarav, Salakhutdinov, Ruslan, Johnson-Roberson, Matthew, Bisk, Yonatan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912195821961216
author Xie, Quanting
Min, So Yeon
Ji, Pengliang
Yang, Yue
Zhang, Tianyi
Xu, Kedi
Bajaj, Aarav
Salakhutdinov, Ruslan
Johnson-Roberson, Matthew
Bisk, Yonatan
author_facet Xie, Quanting
Min, So Yeon
Ji, Pengliang
Yang, Yue
Zhang, Tianyi
Xu, Kedi
Bajaj, Aarav
Salakhutdinov, Ruslan
Johnson-Roberson, Matthew
Bisk, Yonatan
contents There is no limit to how much a robot might explore and learn, but all of that knowledge needs to be searchable and actionable. Within language research, retrieval augmented generation (RAG) has become the workhorse of large-scale non-parametric knowledge; however, existing techniques do not directly transfer to the embodied domain, which is multimodal, where data is highly correlated, and perception requires abstraction. To address these challenges, we introduce Embodied-RAG, a framework that enhances the foundational model of an embodied agent with a non-parametric memory system capable of autonomously constructing hierarchical knowledge for both navigation and language generation. Embodied-RAG handles a full range of spatial and semantic resolutions across diverse environments and query types, whether for a specific object or a holistic description of ambiance. At its core, Embodied-RAG's memory is structured as a semantic forest, storing language descriptions at varying levels of detail. This hierarchical organization allows the system to efficiently generate context-sensitive outputs across different robotic platforms. We demonstrate that Embodied-RAG effectively bridges RAG to the robotics domain, successfully handling over 250 explanation and navigation queries across kilometer-level environments, highlighting its promise as a general-purpose non-parametric system for embodied agents.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18313
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
Xie, Quanting
Min, So Yeon
Ji, Pengliang
Yang, Yue
Zhang, Tianyi
Xu, Kedi
Bajaj, Aarav
Salakhutdinov, Ruslan
Johnson-Roberson, Matthew
Bisk, Yonatan
Robotics
Artificial Intelligence
Machine Learning
There is no limit to how much a robot might explore and learn, but all of that knowledge needs to be searchable and actionable. Within language research, retrieval augmented generation (RAG) has become the workhorse of large-scale non-parametric knowledge; however, existing techniques do not directly transfer to the embodied domain, which is multimodal, where data is highly correlated, and perception requires abstraction. To address these challenges, we introduce Embodied-RAG, a framework that enhances the foundational model of an embodied agent with a non-parametric memory system capable of autonomously constructing hierarchical knowledge for both navigation and language generation. Embodied-RAG handles a full range of spatial and semantic resolutions across diverse environments and query types, whether for a specific object or a holistic description of ambiance. At its core, Embodied-RAG's memory is structured as a semantic forest, storing language descriptions at varying levels of detail. This hierarchical organization allows the system to efficiently generate context-sensitive outputs across different robotic platforms. We demonstrate that Embodied-RAG effectively bridges RAG to the robotics domain, successfully handling over 250 explanation and navigation queries across kilometer-level environments, highlighting its promise as a general-purpose non-parametric system for embodied agents.
title Embodied-RAG: General Non-parametric Embodied Memory for Retrieval and Generation
topic Robotics
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2409.18313