From Detect and Repair to Predict and Prevent: Assessing the Viability of Real-Time AI Nudges in Reducing Fleet Accident Rates
DOI:
https://doi.org/10.63282/3050-922X.IJERET-V5I2P112Keywords:
Fleet Management, Accident Prevention, Artificial Intelligence, Driver Safety, Real-Time Feedback, Behavioral Nudges, Telematics, Predictive Analytics, Commercial Vehicles, Transportation SafetyAbstract
Fleet accidents cost the transportation industry billions of dollars each year. Traditional safety programs focus on analyzing crashes after they happen and retraining drivers. This reactive approach misses opportunities to prevent accidents before they occur. We examined whether real-time AI systems can reduce fleet accident rates by providing immediate feedback to drivers during risky situations. Our study tracked 340 commercial vehicles across six months, comparing accident rates between drivers who received AI-generated safety nudges and a control group using standard telematics. The intervention group showed a 31% reduction in preventable accidents and a 44% decrease in near-miss incidents. We also found that driver acceptance of the system improved significantly after the first two weeks of use. The economic analysis suggests potential savings of $8,400 per vehicle annually when accounting for reduced insurance claims, vehicle downtime, and liability costs. However, the system raised concerns about driver privacy and workplace monitoring that need addressing before widespread adoption. This research demonstrates that predictive AI can shift fleet safety from a reactive to proactive model.
References
[1] Blincoe, L., Miller, T. R., Wang, J. S., Swedler, D., Coughlin, T., Lawrence, B., ... & Spicer, K. (2023). The Economic and Societal Impact of Motor Vehicle Crashes, 2019 (Revised). National Highway Traffic Safety Administration Technical Report DOT HS 813 403.
[2] Chen, C., & Huang, H. (2023). Real-Time Risk Assessment for Commercial Vehicle Safety Using Deep Learning. Transportation Research Part C: Emerging Technologies, 148, 104026.
[3] Federal Motor Carrier Safety Administration. (2023). Large Truck and Bus Crash Facts 2022. U.S. Department of Transportation.
[4] Vanama SKR. Architecture Led Cloud Modernization: A Framework for Enterprise Migration from VMware to OpenShift and AWS. IJERET [Internet]. 2024 Mar. 3;5(1):117-125. https://doi.org/10.63282/3050-922X.IJERET-V5I1P114
[5] Gaspar, J. G., Brown, T. L., Schwarz, C. W., Lee, J. D., Kang, J., & Higgins, J. S. (2017). Evaluating Driver Drowsiness Countermeasures. Traffic Injury Prevention, 18(sup1), S58-S63.
[6] Hallmark, S., Veneziano, D., Falb, S., Pawlovitch, M., & Mantravadi, S. (2022). Evaluation of Real-Time Driver Feedback Systems in Commercial Vehicles. Transportation Research Record, 2676(11), 523-535.
[7] Kahneman, D., & Tversky, A. (1979). Prospect Theory: An Analysis of Decision under Risk. Econometrica, 47(2), 263-291.
[8] Lee, J. D., McGehee, D. V., Brown, T. L., & Reyes, M. L. (2002). Collision Warning Timing, Driver Distraction, and Driver Response to Imminent Rear-End Collisions in a High-Fidelity Driving Simulator. Human Factors, 44(2), 314-334.
[9] National Safety Council. (2023). Injury Facts: Motor Vehicle Safety Issues. Retrieved from https://injuryfacts.nsc.org/motor-vehicle/
[10] Thaler, R. H., & Sunstein, C. R. (2008). Nudge: Improving Decisions About Health, Wealth, and Happiness. Yale University Press.
[11] American Transportation Research Institute. (2023). An Analysis of the Operational Costs of Trucking: 2023 Update. Arlington, VA.
[12] Insurance Institute for Highway Safety. (2023). Large Trucks: Crash Statistics and Prevention. Retrieved from https://www.iihs.org/topics/large-trucks
[13] Vanama SKR. Integrating Site Reliability Engineering SRE Principles into Enterprise Architecture for Predictive Resilience. IJETCSIT [Internet]. 2023 Oct. 30;4(3):164-170. https://doi.org/10.63282/3050-9246.IJETCSIT-V4I3P117
