AI-Powered Streaming Data Pipelines for Real-Time Vehicle Decision-Making
DOI:
https://doi.org/10.15680/amqt9f90Keywords:
Streaming data pipelines, Real-time vehicle decision-making, Autonomous vehicles, Sensor fusion, AI and machine learning, Low-latency processing, V2X communication, Predictive analytics, Anomaly detection, Online learningAbstract
Real-time decision-making is critical for autonomous and connected vehicles to ensure safety, efficiency, and adaptability in dynamic traffic environments. The massive volume and velocity of streaming sensor and contextual data pose significant challenges in processing, analyzing, and acting upon information within stringent latency constraints. This paper proposes an AI-powered streaming data pipeline designed to enable real-time vehicle decision-making by integrating high-throughput data ingestion, low-latency processing, and intelligent analytics. The pipeline incorporates state-of-the-art stream processing frameworks coupled with advanced machine learning models optimized for real-time inference. The architecture supports multi-modal sensor data fusion—including lidar, radar, cameras, and V2X communication—ensuring a comprehensive understanding of the surrounding environment. Key features include scalable data ingestion, anomaly detection, predictive modeling, and context-aware decision modules that dynamically adjust vehicle behaviors. The proposed pipeline is deployed and evaluated on a real-world autonomous driving dataset, demonstrating superior performance in latency reduction and decision accuracy compared to traditional batch or near-real-time systems. Experimental results highlight the system’s ability to respond to critical events such as obstacle avoidance, lane changes, and traffic signal interpretation with sub-second latency. The pipeline's modular design facilitates integration with existing vehicle control systems and supports continuous learning through online model updates. This work bridges the gap between raw streaming data and actionable vehicle decisions, addressing the challenges of big data velocity and complexity inherent to autonomous vehicle environments. By harnessing AI-powered streaming analytics, this pipeline enhances the safety, reliability, and responsiveness of autonomous driving systems, advancing the state-of-the-art in real-time vehicular intelligence.
References
1. Thrun, S., Burgard, W., & Fox, D. (2006). Probabilistic Robotics. MIT Press.
2. Poovaiah, S. A. D. (2022). Benchmarking provable resilience in convolutional neural networks: A study with Beta-CROWN and ERAN.
3. Devaraju, S., Katta, S., Donuru, A., & Devulapalli, H. Comparative Analysis of Enterprise HR Information System (HRIS) Platforms: Integration Architecture, Data Governance, and Digital Transformation Effectiveness in Workday, SAP SuccessFactors, Oracle HCM Cloud, and ADP Workforce Now.
4. Chen, L., Yang, X., & Li, H. (2017). Deep learning for autonomous vehicle perception: Approaches and challenges. IEEE Transactions on Intelligent Transportation Systems, 18(10), 2922-2934.
5. Kim, J., & Canny, J. (2017). Interpretable learning for self-driving cars by visualizing causal attention. Proceedings of the IEEE International Conference on Computer Vision.
6. Kreps, J., Narkhede, N., & Rao, J. (2011). Kafka: A distributed messaging system for log processing. Proceedings of the NetDB.
7. G Jaikrishna, Sugumar Rajendran, Cost-effective privacy preserving of intermediate data using group search optimisation algorithm, International Journal of Business Information Systems, Volume 35, Issue 2, September 2020, pp.132-151.
8. Hajarath, K. C. R., & Vummadi, J. R. Rebuilding Trust in Global Supply Chains: Strategic Supplier Collaboration in a Post-COVID World. ES 2025, 19 (1), 43-49.
9. Gonepally, S., Amuda, K. K., Kumbum, P. K., Adari, V. K., & Chunduru, V. K. (2023). Addressing supply chain administration challenges in the construction industry: A TOPSIS-based evaluation approach. Data Analytics and Artificial Intelligence, 3(1), 152–164.
10. Carbone, P., Katsifodimos, A., Ewen, S., Markl, V., Haridi, S., & Tzoumas, K. (2015). Apache Flink: Stream and batch processing in a single engine. IEEE Data Engineering Bulletin, 38(4), 28-38.
11. Devaraju, Sudheer. " Optimizing Data Transformation in Workday Studio for Global Retailers Using Rule-Based Automation."Journal of Emerging Technologies and Innovative Research 7 (4), 69 – 74
12. Lekkala, C. (2019). Strategies for Effective Partitioning Data at Scale in Large-scale Analytics. European Journal of Advances in Engineering and Technology, 6(11), 49–55.
13. Ma, X., Liu, H., & Zhang, Y. (2020). Real-time streaming data analytics for autonomous driving using deep learning and Apache Flink. IEEE Transactions on Intelligent Vehicles, 5(4), 691-701.
14. Zhang, T., Sun, Y., & Qi, H. (2021). End-to-end pedestrian detection pipeline for autonomous vehicles using streaming analytics. IEEE Access, 9, 16245-16256.
15. Kumbum, P. K., Adari, V. K., Chunduru, V. K., Gonepally, S., & Amuda, K. K. (2023). Navigating digital privacy and security effects on student financial behavior, academic performance, and well-being. Data Analytics and Artificial Intelligence, 3(2), 235–246.
16. Campolo, C., Molinaro, A., Scopigno, R., & Molinaro, A. (2015). Vehicular ad hoc networks: Standards, solutions, and research. Springer.
17. Pareek, C. S. FROM PREDICTION TO TRUST: EXPLAINABLE AI TESTING IN LIFE INSURANCE.
18. K. Anbazhagan, R. Sugumar (2016). A Proficient Two Level Security Contrivances for Storing Data in Cloud. Indian Journal of Science and Technology 9 (48):1-5.
19. S. Devaraju, HR Information Systems Integration Patterns, Independently Published, ISBN: 979-8330637850, DOI: 10.5281/ZENODO.14295926, 2021.
20. Li, Y., Chen, L., & Liu, J. (2019). Anomaly detection in vehicular networks using recurrent neural networks. IEEE Transactions on Intelligent Transportation Systems, 20(8), 3017-3026.
