Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM69030
Volume:
10 |
11 |
Nov 2026
Pages:
1-4
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Electronics and Computer Engineering
Aditya College of Engineering and Technology

Electronics and Computer Engineering
Aditya College Of Engineering and Technology

Electronics and Computer Engineering
Aditya College Of Engineering and Technology

Electronics and Computer Engineering
Aditya College Of Engineering and Technology

Electronics and Computer Engineering
Aditya College Of Engineering and Technology
Railway safety still leans heavily on human attention, and spotting an object on the track early enough to react to it remains difficult. This paper describes a miniature driverless train built to explore how low-cost AI and IoT components can help with that problem. A front-mounted camera supplies frames to a YOLO detector running alongside OpenCV, an ultrasonic sensor confirms how far away an object is, and infrared sensors follow marker positions on the track. An ESP32 microcontroller combines these inputs and drives the DC motors through a motor driver, slowing or stopping the train when its path is blocked. Each detection is saved as an image, listed on a Django web dashboard, and sent to the operator as a Telegram message. The model was assembled and tested on a small track as an academic project, and the paper explains its design, its working sequence, and the observations recorded during testing . The work shows that detection, sensing, control, and remote reporting can be integrated on affordable hardware, and it offers a base for further study of autonomous rail systems.
KEYWORDS
This paper presented a miniature driverless train in which a YOLO and OpenCV vision module, ultrasonic and infrared sensing, and an ESP32 controller work together to detect obstacles and manage movement. A Django dashboard, stored images, and Telegram alerts keep an operator informed from a distance. The project shows that these technologies can be combined on low-cost hardware and gives us a platform for studying railway automation. As a small-scale model tested in a controlled setting, it is a starting point rather than a finished railway product. Our next steps are testing under varied lighting and track conditions, training the detector on rail-specific data, adding more sensors, and measuring reliability over longer runs.
[1] J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real-Time Object Detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779–788. [2] Z. Zhang, P. Chen, Y. Huang, L. Dai, F. Xu, and H. Hu, “Railway obstacle intrusion warning mechanism integrating YOLO-based detection and risk assessment,” Journal of Industrial Information Integration, vol. 38, Art. no. 100571, 2024. [3] J. Wei and Y. Song, “Passive Wireless Sensor Network-Based In-Transit Health Status Monitoring for Railway Transportation,” Journal of Sensors, vol. 2021, Art. no. 3789699, 2021. [4] A. Armijo and D. Zamora-Sánchez, “Integration of Railway Bridge Structural Health Monitoring into the Internet of Things with a Digital Twin: A Case Study,” Sensors, vol. 24, no. 7, Art. no. 2115, 2024.
Publication Date
11/16/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
1
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...