AI-Driven Multi-Agent Generative Pipelines for Cooperative Autonomous Driving with Image Denoising Using Microservices
Main Article Content
Abstract
The rapid evolution of autonomous driving demands collaborative, intelligent frameworks capable of handling complex driving environments in real time. This paper proposes an AI-driven multi-agent generative pipeline for cooperative autonomous driving, incorporating image denoising techniques to enhance perception accuracy under varying environmental conditions. The framework leverages microservices and containerization to ensure modularity, scalability, and efficient deployment across heterogeneous vehicular and edge-cloud systems. Multi-agent generative models enable cooperative decision-making, path planning, and adaptive behavior among autonomous vehicles, while AI-driven image denoising improves sensor data quality for robust object detection and navigation. Experimental results demonstrate that the proposed approach significantly enhances traffic coordination, reduces perception errors, and supports real-time collaboration among vehicles. This study highlights the integration of generative AI, microservices, and image processing as a foundation for scalable, cooperative autonomous driving ecosystems.
Article Details
Section
How to Cite
References
1. Shalev-Shwartz, S., Shammah, S., & Shashua, A. (2016). Safe, Multi-Agent Reinforcement Learning for Autonomous Driving. arXiv preprint arXiv:1604.07316.
2. Arul Raj .A.M and Sugumar R.,” Monitoring of the social Distance between Passengers in Real-time through video Analytics and Deep learning in Railway stations for Developing highest Efficiency” , March 2023 International Conference on Data Science, Agents and Artificial Intelligence, ICDSAAI 2022, ISBN 979- 835033384-8, March 2023, Chennai , India ., DOI 10.1109/ICDSAAI55433.2022.10028930.
3. Gonepally, S., Amuda, K. K., Kumbum, P. K., Adari, V. K., & Chunduru, V. K. (2021). The evolution of software maintenance. Journal of Computer Science Applications and Information Technology, 6(1), 1–8. https://doi.org/10.15226/2474-9257/6/1/00150
4. Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, O., & Mordatch, I. (2017). Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments. Advances in Neural Information Processing Systems (NeurIPS).
5. Arulraj AM, Sugumar, R., Estimating social distance in public places for COVID-19 protocol using region CNN, Indonesian Journal of Electrical Engineering and Computer Science, 30(1), pp.414-424, April 2023
6. Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative Adversarial Nets. Advances in Neural Information Processing Systems.
7. Cherukuri, Bangar Raju. "Microservices and containerization: Accelerating web development cycles." (2020).
8. Chatterjee, P. (2023). AI-Powered Payment Gateways: Accelerating Transactions and Fortifying Security in Real-Time Financial Systems. Accelerating Transactions and Fortifying Security in Real-Time Financial Systems (June 20, 2023). International Journal of Scientific Research in Science and Technology,[10.32628/IJSRST23113268].
9. Lu, N., Cheng, N., Zhang, N., Shen, X., & Mark, J. W. (2014). Connected Vehicles: Solutions and Challenges. IEEE Internet of Things Journal, 1(4), 289-299.
10. S. T. Gandhi, "Context Sensitive Image Denoising and Enhancement using U-Nets," Computer Science (MS), Computer Science (GCCIS), Rochester Institute of Technology, 2020. [Online]. Available: https://repository.rit.edu/theses/10588/
11. Sugumar, R. (2022). Estimation of Social Distance for COVID19 Prevention using K-Nearest Neighbor Algorithm through deep learning. IEEE 2 (2):1-6.
12. Chellu, R. (2023). AI-Powered intelligent disaster recovery and file transfer optimization for IBM Sterling and Connect:Direct in cloud-native environments. International Journal on Recent
13. Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., & Koltun, V. (2017). CARLA: An Open Urban Driving Simulator. Proceedings of the 1st Annual Conference on Robot Learning.