Harnessing the Power of Large Language Models for Automated Code Generation and Verification-Reference-Cited by-同舟云学术

Harnessing the Power of Large Language Models for Automated Code Generation and Verification

Published:2024-09-11 Issue:9 Volume:13 Page:137
ISSN:2218-6581
Container-title:Robotics
language:en
Short-container-title:Robotics

Author:

Antero Unai¹^ORCID,Blanco Francisco¹^ORCID,Oñativia Jon¹^ORCID,Sallé Damien¹^ORCID,Sierra Basilio²^ORCID

Affiliation:

1. Industry and Transport Division, TECNALIA, Basque Research and Technology Alliance (BRTA), 20009 Donostia-San Sebastian, Spain

2. Department of Computer Sciences and Artificial Intelligence, University of the Basque Country (UPV/EHU), 20018 Donostia, Spain

Abstract

The cost landscape in advanced technology systems is shifting dramatically. Traditionally, hardware costs took the spotlight, but now, programming and debugging complexities are gaining prominence. This paper explores this shift and its implications, focusing on reducing the cost of programming complex robot behaviors, using the latest innovations from the Generative AI field, such as large language models (LLMs). We leverage finite state machines (FSMs) and LLMs to streamline robot programming while ensuring functionality. The paper addresses LLM challenges related to content quality, emphasizing a two-fold approach using predefined software blocks and a Supervisory LLM.

Funder

ELKARTEK Research Program of the Basque Government

Fundación TECNALIA Research and Innovation

Publisher

MDPI AG

Link

https://www.mdpi.com/2218-6581/13/9/137/pdf

Reference40 articles.

1. (2024, September 04). IFR Secretariat Blog—AI in Robotics. Available online: https://ifr.org/post/ai-in-robotics-blog.

2. On the Relationship between Software Complexity and Maintenance Costs;Ogheneovo;J. Comput. Commun.,2014

3. Ben-Ari, M. (2018). Finite state machines. Elements of Robotics, Springer.

4. Balogh, R., and Obdržálek, D. (2019). Using Finite State Machines in Introductory Robotics: Methods and Applications for Teaching and Learning. Using Finite State Machines in Introductory Robotics: Methods and Applications for Teaching and Learning, Springer.

5. Zhou, H., Min, H., Lin, Y., and Zhang, S. (2017). A Robot Architecture of Hierarchical Finite State Machine for Autonomous Mobile Manipulator. A Robot Architecture of Hierarchical Finite State Machine for Autonomous Mobile Manipulator, Springer.