Citation:

Naveen Kumar Bonagiri, 2026. "Leveraging Retrieval-Augmented Generation (RAG) AI for Transforming Automotive Design, Manufacturing, and In-Vehicle Experiences", ESP Journal of Engineering & Technology Advancements  6(1): 18-29.

Abstract:

The automotive industry is undergoing a paradigm shift driven by the exponential growth of data from connected vehicles and evolving customer expectations. This transformation introduces both opportunities and challenges, compelling manufacturers to adopt advanced AI technologies. Retrieval-Augmented Generation (RAG) emerges as a pivotal enabler in this context, offering capabilities that span product development, manufacturing optimization, predictive maintenance, and hyper-personalized in-vehicle experiences. This paper explores the integration of RAG-based AI agents into automotive workflows, highlighting their role in accelerating design decisions through intelligent retrieval of engineering standards, historical models, and regulatory documentation. Furthermore, RAG facilitates cross-domain collaboration by harmonizing constraints across mechanical, electrical, and software domains, thereby improving product quality and reducing defects. In manufacturing, RAG-powered assistants streamline access to technical documentation, enhance operational efficiency, and enable predictive analytics for equipment health monitoring. Beyond production, RAG unlocks next-generation customer experiences through context-aware personalization, adaptive cabin configurations, and augmented reality interfaces. By synthesizing real-time sensor data with historical records, RAG also supports predictive maintenance strategies, reducing downtime and improving reliability. The paper concludes by discussing strategic pathways for automotive manufacturers to develop proprietary RAG-based AI solutions or leverage them as services, positioning RAG as a cornerstone for future automotive innovation.

References:

[1] Y. Gao, Y. Xiong, X. Gao, K. Jia, J. Pan, Y. Bi, Y. Dai, J. Sun, H. Wang, and H. Wang, “Retrieval-augmented generation for large language models: A survey,” arXiv preprint arXiv:2312.10997, vol. 2, no. 1, 2023.

[2] X. Ma, Y. Gong, P. He, N. Duan et al., “Query rewriting in retrieval-augmented large language models,” 2023.

[3] Chaitanya Shinde and Divya Garikapati, “Gen AI in Automotive: Applications, Challenges, and Opportunities with a Case study on In-Vehicle Experience”, https://arxiv.org/html/2511.00026v1

[4] Aayush Jamalamadaka, “Comprehensive Research Into All Possible Use Cases Of Agentic AI In Automotive Domains” Volume 27, Issue 4, Ser. 3 (July. – August. 2025)

[5] Y. Gao, Y. Xiong, M. Wang, and H. Wang, “Modular rag: Trans-forming rag systems into lego-like reconfigurable frameworks,” https://arxiv.org/html/2407.21059v1, 2024, accessed: 2025-02-17.

[6] I. Ilin, “Advanced rag techniques-an illustrated overview (2023),” Dostupne´ z: https://pub. towardsai.net/advanced-ragtechniques-an-illustrated-overview-04d193d8fec6, 2023

Keywords:

Automotive Product Development, Artificial Intelligence, Retrieval-Augmented Generation, Predictive Maintenance, Manufacturing Optimization, Connected Vehicle Data.