000014962 001__ 14962
000014962 005__ 20241105132935.0
000014962 020__ $$a9781685581855
000014962 037__ $$aCONFERENCE
000014962 039_9 $$a2024-11-05 13:29:35$$b0$$c2024-11-05 11:19:00$$d1000062$$y2024-11-05 09:51:20$$z1000099
000014962 041__ $$aeng
000014962 245__ $$aIntegration of large language models intro control systems for shared appliances
000014962 269__ $$a2024-09
000014962 300__ $$a6 p.
000014962 506__ $$avisible
000014962 520__ $$9eng$$aLarge Language Model (LLM)-powered chatbot agents have proven to be immensely useful in tasks, such as writing and generating essays, code, and academic text. By using frameworks such as LangChain, agents can be equipped with tools to access and analyse custom data, which facilitates bespoke applications, such as customer service agents with access to internal documents and tailored reasoning. While the focus of such applications has mainly centered around textual content, custom toolboxes could also enable agents to act in completely different use cases, for instance control theory. Nevertheless, given the non-deterministic nature of LLMs, merging them with deterministic software implies challenges in applied contexts such as privacy, multi-user interactions, and consistency. To pave the way to reliable LLM usage in various contexts, this work provides the foundation for expanding the use of LLM agents to the domain of control systems and human-centric automation. An agent-based architecture is proposed, which is then implemented within the context of a shared space heating system controlled by three personas. Finally, we evaluate the capacity of the system to deal with scenarios such as normality, erratic user behavior, conflicts of interest, and system limitations. The findings of this study highlight the potential benefits and challenges of using LLMs for appliance control. All code is made public at https://github.com/fredmontet/llm-cps-ac to facilitate further research.
000014962 540__ $$acorrect
000014962 592__ $$aHEIA-FR
000014962 592__ $$biCoSys- Institut d’intelligence artificielle et systèmes complexes
000014962 592__ $$cIngénierie et Architecture
000014962 6531_ $$9eng$$acontrol
000014962 6531_ $$9eng$$alarge language models
000014962 6531_ $$9eng$$ashared appliance
000014962 6531_ $$9eng$$aLangChain
000014962 6531_ $$9eng$$ahuman-robot interaction
000014962 6531_ $$9eng$$asocial robotics
000014962 6531_ $$9eng$$agenerative models
000014962 655_7 $$apublished full paper
000014962 700__ $$aMontet, Frédéric$$uSchool of Engineering and Architecture (HEIA-FR), HES-SO University of Applied Sciences and Arts Western Switzerland
000014962 700__ $$aLöwenmark, Karl$$uLulea University of Technology, Lulea, Sweden
000014962 700__ $$aLiwicki, Marcus$$uLulea University of Technology, Lulea, Sweden
000014962 700__ $$aSandin, Fredrik$$uLulea University of Technology, Lulea, Sweden
000014962 700__ $$aHennebert, Jean$$uSchool of Engineering and Architecture (HEIA-FR), HES-SO University of Applied Sciences and Arts Western Switzerland
000014962 711__ $$aAMBIENT 2024, The Fourteenth International Conference on Ambient Computing, Applications, Services and Technologies$$cVenice, Italy$$d2024-09-29$$m2024-10-03
000014962 773__ $$tProceedings of AMBIENT 2024, The Fourteenth International Conference on Ambient Computing, Applications, Services and Technologies, 29 September-3 October 2024, Venice, Italy$$j2024
000014962 85641 $$zOnline proceedings$$uhttps://www.thinkmind.org/library/AMBIENT/AMBIENT_2024/ambient_2024_1_20_40008.html
000014962 8564_ $$uhttps://arodes.hes-so.ch/record/14962/files/Montet_2024_integration_large_language_models.pdf$$yPublished version$$9082083dc-a7fb-4b99-91f8-3f406c320f52$$s494747
000014962 906__ $$aGOLD
000014962 909CO $$ooai:hesso.tind.io:14962$$pGLOBAL_SET
000014962 950__ $$aaucun
000014962 980__ $$aconference
000014962 981__ $$aconference