Multimodal Generative AI for Vehicular Applications at Edge

Year : 2025 | Volume : 16 | Issue : 01 | Page : 27 34
    By

    Sundaresan Poovalingam,

  • Bhoomi Shah,

  • Rani Malhotra,

  • Nikhil Nandanwar,

  1. Distinguished Technologist, Advanced Engineering Group, Infosys Limited, Bengaluru, Karnataka, India.
  2. Constultant, Advanced Engineering Group, Infosys Limited, Bengaluru, Karnataka, India.
  3. Lead Constultant, Advanced Engineering Group, Infosys Limited, Bengaluru, Karnataka, India.
  4. Lead Constultant, Advanced Engineering Group, Infosys Limited, Bengaluru, Karnataka, India.

Abstract

This paper explores how the rapid advancements in vehicular technology, including autonomous driving and intelligent transportation systems, have driven the need for real-time data processing and decision-making. Multimodal generative AI, when deployed at the edge, offers a powerful solution for vehicular applications by leveraging diverse data sources such as video, audio, sensor inputs, and environmental data. This paper explores the integration of multimodal generative AI with edge computing in vehicular networks, particularly for use cases like autonomous platooning, predictive maintenance, anomaly detection, and enhanced security. By processing data locally at the edge using AI chips, vehicles can respond instantly to critical events without relying on distant cloud servers, reducing latency and improving safety. Furthermore, vehicular ad hoc networks (VANETs) play a
crucial role in supporting decentralized, low-latency communication between vehicles and infrastructure. This fusion of multimodal AI and edge computing unlocks the potential for more intelligent, efficient, and resilient vehicular systems, paving the way for next-generation transportation and smart city infrastructures.

Keywords: VANETs, AI chips, Platooning, multimodal AI, networks, traffic conditions

[This article belongs to Journal of Control & Instrumentation ]

How to cite this article:
Sundaresan Poovalingam, Bhoomi Shah, Rani Malhotra, Nikhil Nandanwar. Multimodal Generative AI for Vehicular Applications at Edge. Journal of Control & Instrumentation. 2024; 16(01):27-34.
How to cite this URL:
Sundaresan Poovalingam, Bhoomi Shah, Rani Malhotra, Nikhil Nandanwar. Multimodal Generative AI for Vehicular Applications at Edge. Journal of Control & Instrumentation. 2024; 16(01):27-34. Available from: https://journals.stmjournals.com/joci/article=2024/view=191079


References

1. Liu G, Van Huynh N, Du H, Hoang DT, Niyato D, Zhu K, et al. Generative AI for unmanned vehicle swarms: Challenges, applications and opportunities. [Preprint]. arXiv. 2024 Feb 28. Available from: https://doi.org/10.48550/arXiv.2402.18062.
2. Xie G, Xie R, Zhang X, Nie J, Tang Q, Lim WYB, et al. GIoV: Achieving generative AI services in Internet of Vehicles via collaborative edge intelligence. 2024 IEEE Wireless Communications and Networking Conference (WCNC), Dubai, United Arab Emirates. 2024. p. 1–6. doi:10.1109/WCNC57260.2024.10571334.
3. Ameur AI, Lakas A, Yagoubi MB, Oubbati OS. Peer-to-peer overlay techniques for vehicular ad hoc networks: Survey and challenges. Veh Commun. 2022;34:100455. doi:10.1016/j.vehcom.2022. 100455.
4. Marks N. (2024). In It for the Long Haul: Waabi Pioneers Generative AI to Unleash Fully Driverless Autonomous Trucking. [online] NVIDIA Blog. Available from: https://blogs.nvidia.com/blog/ waabi-autonomous-trucking/.
5. Intel. (2024). Software-defined vehicle transformation starts with Intel. [Online]. Available from: https://download.intel.com/newsroom/2024/automotive/Intel-SDV-Demo-Fact-Sheet.pdf
6. Stappen L, Dillmann J, Striegel S, Vögel HJ, Flores-Herr N, Schuller BW. Integrating generative artificial intelligence in intelligent vehicle systems. 2023 IEEE 26th International Conference on Intelligent Transportation Systems (ITSC), Bilbao, Spain. 2023. p. 5790–7. doi:10.1109/ITSC57777.2023.10422003.
7. Xu M, Niyato D, Chen J, Zhang H, Kang J, Xiong Z, et al. Generative AI-empowered simulation for autonomous driving in vehicular mixed reality metaverses. IEEE J Sel Top Signal Process. 2023;17:1064–79. doi:10.1109/JSTSP.2023.3293650.
8. Xu M, Niyato D, Zhang H, Kang J, Xiong Z, Mao S, et al. Joint foundation model caching and inference of generative AI services for edge intelligence. GLOBECOM 2023 – 2023 IEEE Global Communications Conference, Kuala Lumpur, Malaysia. 2023. p. 3548–53. doi:10.1109/GLOBE COM54140.2023.10436771.
9. Desai B, Patil K. Secure and scalable multi-modal vehicle systems: A cloud-based framework for real-time LLM-driven interactions. Innov Comput Sci J. 2023;9:1–1.
10. World Economic Forum. Autonomous Trucks: An Opportunity to Make Road Freight Safer, Cleaner and More Efficient. Cologny/Geneva: World Economic Forum; 2021. Available from: https://www.weforum.org/publications/autonomous-trucks-an-opportunity-to-make-road-freightsafer-cleaner-and-more-efficient/
11. Ivanovic B, Leung K, Schmerling E, Pavone M. Multimodal deep generative models for trajectory prediction: A conditional variational autoencoder approach. IEEE Robot Autom Lett. 2021;6:295–302. doi:10.1109/LRA.2020.3043163.

Regular Issue Subscription Review Article
Volume 16
Issue 01
Received 09/12/2024
Accepted 14/12/2024
Published 27/12/2024
Publication Time 18 Days
384

Login


My IP

PlumX Metrics