Embedded Safety System for Autonomous Vehicles

  • Unique Paper ID: 181507
  • PageNo: 4126-4134
  • Abstract:
  • The research provides a reliable embedded safety system to improve the situational awareness and stability of autonomous vehicles. This project combined real-time object and pedestrian detection using the YOLO algorithm, speed identification, and blind spot monitoring using ultrasonic sensors. These functions are deployed on embedded systems like Raspberry Pi and ESP32, activating advanced control measures such as PWM-based speed control and LED-based risk alerts. The camera module can capture road imagery for detection and classification; the speed limit is observed with image processing and OCR technique and the ultrasonic sensor continuously observes blind areas. OCR model obtains speed limit information and allows real-time vehicle speed control. This prototype testing under various road situations presented high accuracy and consistency in object recognition, speed customization, and blind spot alerts. The project presents minimal delay and informed choices in a real-time environment. Long-term upgrades will be prioritised incorporating sensor fusion, V2X communication, and IMU-based pose correction to improve safety in a challenging traffic environment.

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{181507,
        author = {Jennifer C Saldanha and Prakash S H and Jithesh and Guruprasad and Rachana},
        title = {Embedded Safety System for Autonomous Vehicles},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {4126-4134},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=181507},
        abstract = {The research provides a reliable embedded safety system to improve the situational awareness and stability of autonomous vehicles. This project combined real-time object and pedestrian detection using the YOLO algorithm, speed identification, and blind spot monitoring using ultrasonic sensors. These functions are deployed on embedded systems like Raspberry Pi and ESP32, activating advanced control measures such as PWM-based speed control and LED-based risk alerts. The camera module can capture road imagery for detection and classification; the speed limit is observed with image processing and OCR technique and the ultrasonic sensor continuously observes blind areas. OCR model obtains speed limit information and allows real-time vehicle speed control. This prototype testing under various road situations presented high accuracy and consistency in object recognition, speed customization, and blind spot alerts. The project presents minimal delay and informed choices in a real-time environment. Long-term upgrades will be prioritised incorporating sensor fusion, V2X communication, and IMU-based pose correction to improve safety in a challenging traffic environment.},
        keywords = {Autonomous Vehicles, Pedestrian detection YOLO, Object Detection, OCR, PWM, Raspberry Pi, ESP32, Sensor Fusion, V2X Communication, IMU Pose Correction.},
        month = {June},
        }

Cite This Article

Saldanha, J. C., & H, P. S., & Jithesh, , & Guruprasad, , & Rachana, (2025). Embedded Safety System for Autonomous Vehicles. International Journal of Innovative Research in Technology (IJIRT), 12(1), 4126–4134.

Related Articles