Can LLMs plan paths in the real world?

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Wanyi, Su, Meng-Wen, Mehjabin, Nafisa, Cummings, Mary L.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916502354001920
author Chen, Wanyi
Su, Meng-Wen
Mehjabin, Nafisa
Cummings, Mary L.
author_facet Chen, Wanyi
Su, Meng-Wen
Mehjabin, Nafisa
Cummings, Mary L.
contents As large language models (LLMs) increasingly integrate into vehicle navigation systems, understanding their path-planning capability is crucial. We tested three LLMs through six real-world path-planning scenarios in various settings and with various difficulties. Our experiments showed that all LLMs made numerous errors in all scenarios, revealing that they are unreliable path planners. We suggest that future work focus on implementing mechanisms for reality checks, enhancing model transparency, and developing smaller models.
format Preprint
id arxiv_https___arxiv_org_abs_2411_17912
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Can LLMs plan paths in the real world?
Chen, Wanyi
Su, Meng-Wen
Mehjabin, Nafisa
Cummings, Mary L.
Artificial Intelligence
Robotics
As large language models (LLMs) increasingly integrate into vehicle navigation systems, understanding their path-planning capability is crucial. We tested three LLMs through six real-world path-planning scenarios in various settings and with various difficulties. Our experiments showed that all LLMs made numerous errors in all scenarios, revealing that they are unreliable path planners. We suggest that future work focus on implementing mechanisms for reality checks, enhancing model transparency, and developing smaller models.
title Can LLMs plan paths in the real world?
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2411.17912