In Search of a Lightweight "Good Enough" Offline Generative AI for Mobile Robots: Performance Benchmarking

We present a novel benchmarking methodology for evaluating offline Large Language Models (LLMs) in resource-constrained mobile robotics applications. Using an Nvidia Jetson Nano platform with 4GB RAM limitation, we demonstrate the feasibility of deploying tuned ChatGPT4All for robotic control tasks....

Full description

Saved in:
Bibliographic Details
Main Authors: Yegin Genc, Gonca Altuger-Genc, Akin Tatoglu
Format: Article
Language:English
Published: LibraryPress@UF 2025-05-01
Series:Proceedings of the International Florida Artificial Intelligence Research Society Conference
Subjects:
Online Access:https://journals.flvc.org/FLAIRS/article/view/138943
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850138079653789696
author Yegin Genc
Gonca Altuger-Genc
Akin Tatoglu
author_facet Yegin Genc
Gonca Altuger-Genc
Akin Tatoglu
author_sort Yegin Genc
collection DOAJ
description We present a novel benchmarking methodology for evaluating offline Large Language Models (LLMs) in resource-constrained mobile robotics applications. Using an Nvidia Jetson Nano platform with 4GB RAM limitation, we demonstrate the feasibility of deploying tuned ChatGPT4All for robotic control tasks. The model, trained on 22,000+ ICRA proceedings papers, achieves 82% similarity to ChatGPT responses while maintaining sub-second inference time. Our evaluation framework combines TF-IDF similarity scoring and LDA topic coherence analysis across several thousand test cases. Results show consistent performance within hardware constraints, with 92% of responses exceeding 0.80 similarity threshold and 98% completing within one second. This study establishes viability of lightweight LLMs for offline mobile robotics applications, providing a foundation for future resource-aware AI deployments.
format Article
id doaj-art-9346dd97e3464092ab8148ae6a7eb6bd
institution OA Journals
issn 2334-0754
2334-0762
language English
publishDate 2025-05-01
publisher LibraryPress@UF
record_format Article
series Proceedings of the International Florida Artificial Intelligence Research Society Conference
spelling doaj-art-9346dd97e3464092ab8148ae6a7eb6bd2025-08-20T02:30:39ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622025-05-0138110.32473/flairs.38.1.138943In Search of a Lightweight "Good Enough" Offline Generative AI for Mobile Robots: Performance Benchmarking Yegin Genc0Gonca Altuger-Genc1Akin Tatoglu2Pace UniversityFarmingdale State CollegeUniversity of HartfordWe present a novel benchmarking methodology for evaluating offline Large Language Models (LLMs) in resource-constrained mobile robotics applications. Using an Nvidia Jetson Nano platform with 4GB RAM limitation, we demonstrate the feasibility of deploying tuned ChatGPT4All for robotic control tasks. The model, trained on 22,000+ ICRA proceedings papers, achieves 82% similarity to ChatGPT responses while maintaining sub-second inference time. Our evaluation framework combines TF-IDF similarity scoring and LDA topic coherence analysis across several thousand test cases. Results show consistent performance within hardware constraints, with 92% of responses exceeding 0.80 similarity threshold and 98% completing within one second. This study establishes viability of lightweight LLMs for offline mobile robotics applications, providing a foundation for future resource-aware AI deployments. https://journals.flvc.org/FLAIRS/article/view/138943RoboticsOffline LLMResource ConstraintsPerformance BenchmarkingEdge Computing
spellingShingle Yegin Genc
Gonca Altuger-Genc
Akin Tatoglu
In Search of a Lightweight "Good Enough" Offline Generative AI for Mobile Robots: Performance Benchmarking
Proceedings of the International Florida Artificial Intelligence Research Society Conference
Robotics
Offline LLM
Resource Constraints
Performance Benchmarking
Edge Computing
title In Search of a Lightweight "Good Enough" Offline Generative AI for Mobile Robots: Performance Benchmarking
title_full In Search of a Lightweight "Good Enough" Offline Generative AI for Mobile Robots: Performance Benchmarking
title_fullStr In Search of a Lightweight "Good Enough" Offline Generative AI for Mobile Robots: Performance Benchmarking
title_full_unstemmed In Search of a Lightweight "Good Enough" Offline Generative AI for Mobile Robots: Performance Benchmarking
title_short In Search of a Lightweight "Good Enough" Offline Generative AI for Mobile Robots: Performance Benchmarking
title_sort in search of a lightweight good enough offline generative ai for mobile robots performance benchmarking
topic Robotics
Offline LLM
Resource Constraints
Performance Benchmarking
Edge Computing
url https://journals.flvc.org/FLAIRS/article/view/138943
work_keys_str_mv AT yegingenc insearchofalightweightgoodenoughofflinegenerativeaiformobilerobotsperformancebenchmarking
AT goncaaltugergenc insearchofalightweightgoodenoughofflinegenerativeaiformobilerobotsperformancebenchmarking
AT akintatoglu insearchofalightweightgoodenoughofflinegenerativeaiformobilerobotsperformancebenchmarking