Tag Map: A Text-Based Map for Spatial Reasoning and Navigation with Large Language Models


Loading...

Date

2025

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Large Language Models (LLM) have emerged as a tool for robots to generate task plans using common sense reasoning. For the LLM to generate actionable plans, scene context must be provided, often through a map. Recent works have shifted from explicit maps with fixed semantic classes to implicit open vocabulary maps based on queryable embeddings capable of representing any semantic class. However, embeddings cannot directly report the scene context as they are implicit, requiring further processing for LLM integration. To address this, we propose an explicit text-based map that can represent thousands of semantic classes while easily integrating with LLMs due to their text-based nature by building upon large-scale image recognition models. We study how entities in our map can be localized and show through evaluations that our text-based map localizations perform comparably to those from open vocabulary maps while using two to four orders of magnitude less memory. Real-robot experiments demonstrate the grounding of an LLM with the text-based map to solve user tasks.

Publication status

published

Book title

Proceedings of The 8th Conference on Robot Learning

Volume

270

Pages / Article No.

2120 - 2146

Publisher

PMLR

Event

8th Conference on Robot Learning (CoRL 2024)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Scene Understanding; Grounded Navigation; Large Language Models

Organisational unit

09570 - Hutter, Marco / Hutter, Marco check_circle
02284 - NFS Digitale Fabrikation / NCCR Digital Fabrication

Notes

Funding

Related publications and datasets