Page 22 - IJAMD-1-3

International Journal of AI for
Materials and Design
Smart cockpit design with generative models

current approach to establishing the HDT model relies relationships that could have appeared to influence the
predominantly on vision recognition, which provides a work reported in this paper.
limited perspective of the user’s state and preferences.
This single-channel method fails to incorporate data from Author contributions
other potential sources, such as physiological sensors, Conceptualization: Mengyang Ren
voice recognition, and behavioral analysis, which are Investigation: Mengyang Ren, Junming Fan
essential for creating a comprehensive and accurate digital Methodology: All authors
twin. The lack of multi-modal data integration restricts Writing – original draft: Mengyang Ren
the ability to fully capture and respond to the user’s Writing – review & editing: Junming Fan, Chunyang Yu,
needs, thereby limiting the personalization capabilities of Pai Zheng
the system. Future research should focus on integrating
diverse data channels to build a more holistic and robust Ethics approval and consent to participate
HDT model.
Not applicable.
6. Conclusion Consent for publication

This research proposes a personalized design framework for Not applicable.
smart vehicle cockpits, CockpitGemini, which integrates
generative model-based MAS and HDT technologies. Availability of data
The proposed framework addresses the growing demand
for personalized vehicle experiences by providing unique Data used in this work are available from the corresponding
designs and services tailored to individual user preferences author upon reasonable request.
and states. The framework’s capabilities are demonstrated References
through four key aspects: personalized product design,
personalized interactive interface design, user state 1. Chen L, Li Y, Huang C, et al. Milestones in autonomous
monitoring and personalized regulation, and personalized driving and intelligent vehicles: Survey of surveys. IEEE
driving strategy recommendations. The feasibility and Trans Intell Veh. 2023;8(2):1046-1056.
usability of CockpitGemini are further demonstrated doi: 10.1109/TIV.2022.3223131
through a detailed case study focusing on personalized 2. Li W, Wu L, Wang C, et al. Intelligent cockpit for intelligent
cockpit element design, specifically a personalized vehicle vehicle in metaverse: A case study of empathetic auditory
seat. This study underscores the potential of integrating regulation of human emotion. IEEE Trans Syst Man Cybern
advanced technologies to enhance UX and satisfaction Syst. 2023;53(4):2173-2187.
in smart vehicle cockpits, paving the way for future doi: 10.1109/TSMC.2022.3229021
innovations in personalized design.
3. Stappen L, Dillmann J, Striegel S, Vögel HJ, Flores-Herr N,
Acknowledgments Schuller BW. Integrating Generative Artificial Intelligence in
Intelligent Vehicle Systems. In: IEEE Conference on Intelligent
None. Transportation Systems, Proceedings, (ITSC). United States:
Institute of Electrical and Electronics Engineers Inc.; 2023.
Funding p. 5790-5797.
This research is partially funded by the Collaborative doi: 10.1109/ITSC57777.2023.10422003
Project funded by Design-AI Lab, China Academy of Art, 4. Chen H, Gao R, Fan L, et al. Scenario-function system
China (No.: CAADAI2022A002) and State Key Laboratory for automotive intelligent cockpits: Framework, research
of Intelligent Manufacturing Equipment and Technology, progress and perspectives. IEEE Trans Intell Veh.
Huazhong University of Science and Technology 2024;9:4890-4904.
(No.: IMETKF2024010).
doi: 10.1109/TIV.2024.3382995
Conflict of interest 5. Dou R, Lin D, Nan G, Lei S. A method for product
personalized design based on prospect theory improved
Pai Zheng serves as the Editorial Board Member of the with interval reference. Comput Ind Eng. 2018;125:708-719.
journal but was not in any way involved in the editorial
and peer-review process conducted for this paper, directly doi: 10.1016/j.cie.2018.04.056
or indirectly. Separately, the authors declare that they 6. Cao Y, Li S, Liu Y, et al. A Comprehensive survey of
have no known competing financial interests or personal AI-Generated Content (AIGC): A history of generative AI

Volume 1 Issue 3 (2024) 16 doi: 10.36922/ijamd.4220