25, February 2026
AutoWake- AUTOSAR Based Automatic Drowsiness Detection System.
Author(s): 1.Omkar Chinte, 2. Pranav Chopde, 3. Aayush Nerkar
Authors Affiliations:
- Student, Electronics and Telecommunication Engineering, Dr. D Y Patil Institute of Engineering Management and Research, Pune, India
- Student, Electronics and Telecommunication Engineering, Dr. D Y Patil Institute of Engineering Management and Research, Pune, India
- Student, Electronics and Telecommunication Engineering, Dr. D Y Patil Institute of Engineering Management and Research, Pune, India
Abstract
Keywords
Cite this Article/Paper as
References
Driver fatigue and drowsiness are the major safety concerns on the road these days. If someone is sleepy, then their reaction might slow down, they may blink more slowly, and their response times aren't what they should be. This project is all about tackling that with an immediate warning system that kicks in automatically. We're looking forward to create a real-time driver drowsiness detection system that adds to the automotive standard known as AUTOSAR (AUTomotive Open System ARchitecture). The system uses a camera to monitor the driver’s face in real time, focusing particularly on their eyes. STM32, which are the processing unit takes care of the video camera feed. It eventually runs the AI algorithms and detection using computer vision tools such as OpenCV and MediaPipe. The AI checks for signs of drowsiness by examining facial features like face detection, how often the eye blinks (using the eye aspect ratio), and yawning detection (using landmarks around the mouth). Once, system spots a sign of drowsiness through the camera, it sends signal (for ex: drowsy_status = TRUE). This signal then travels from application layer to the BSW through RTE. BSW is nothing but a bridge between the two (AUTOSAR and RTE). BSW sends the signal (drowsy_alert) to the CAN (Controlled Area Network) and activates an Alert Module (preferably a buzzer). It communicates with the car dashboard this way. One advantage of using AUTOSAR is that it is compatible with multiple hardware and one code can be used for multiple micro controllers and this system is the foundation on the layered architecture of AUTOSAR. It smoothly integrates all these components in a dependable and reliable way.
Driver Drowsiness Detection, AUTOSAR, Eye Aspect Ratio, Computer Vision, CAN Bus, ECU Alert System.
Omkar Chinte, Pranav Chopde, Aayush Nerkar, (2026); AutoWake- AUTOSAR Based Automatic Drowsiness Detection System., International Journal for Innovative Research in Multidisciplinary Field, ISSN(O): 2455-0620, Vol-12, Issue-2, Available on – https://www.ijirmf.com/
- Wang, X. Li, and Z. Zhang, “EEG-based driver drowsiness detection,” IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 10, pp. 3646–3655, 2019.
- Ji, Z. Zhu, and P. Lan, “Real-time eye blink detection for fatigue monitoring,” International Journal of Computer Vision, vol. 128, no. 6, pp. 1601–1616, 2020.
- AUTOSAR Consortium, AUTOSAR Architecture Overview, AUTOSAR Release 4.4, Munich, Germany, 2021.
- Chauhan, R. Verma, and S. Gupta, “IoT-based driver fatigue detection system using Raspberry Pi,” IEEE Access, vol. 8, pp. 215098–215107, 2020.
- Kumar and A. Singh, “Implementation of adaptive cruise control using AUTOSAR framework,” International Journal of Automotive Electronics and Systems, vol. 12, no. 3, pp. 267–279, 2022.
- Patel and S. Mehta, “Infrared sensor-based non-contact driver eye monitoring system,” IEEE Sensors Journal, vol. 21, no. 9, pp. 10725–10732, 2021.
- Park, H. Kim, and D. Lee, “Driver drowsiness detection based on facial landmarks and deep learning,” IEEE Transactions on Intelligent Vehicles, vol. 6, no. 4, pp. 682–693, 2021.
- Zhang and X. Wu, “Hybrid CNN–LSTM model for driver fatigue detection using multimodal data,” IEEE Access, vol. 9, pp. 58952–58963, 2021.
- International Organization for Standardization, ISO 26262: Road Vehicles – Functional Safety, Geneva, Switzerland, 2018.