Design and Implementation of a Vision-based Wheeled Mobile Robot Using HSV Color Segmentation and P-D Control
DOI:
https://doi.org/10.25170/jurnalelektro.v18i1.6892Keywords:
Mobile Robot, Object Detection, Raspberry Pi, OpenCV, PD ControlAbstract
This study presents the design and implementation of a wheeled mobile robot capable of detecting and tracking a ping-pong ball using vision-based processing. The system integrates a Raspberry Pi 3 Model B+ as the main controller, a Raspberry Pi Camera Rev 1.3 for visual input, and DC motors driven by an L298N motor driver for actuation. Object detection is achieved through color segmentation in the HSV color space using the OpenCV library, followed by morphological filtering and contour analysis. A proportional-derivative (PD) control algorithm is employed to adjust motor speeds dynamically based on the ball's horizontal position in the frame. The experimental results demonstrate that the robot can successfully detect and follow a ping-pong ball, although it exhibits limitations in processing speed and motion stability. The average frame rate during operation was 5 FPS, which is sufficient for basic tracking tasks but suboptimal for high-speed applications. This project highlights the feasibility of vision based robotic systems for simple object tracking tasks.
References
[1] D. Dang and H. Bui, "Real-Time Obstacle Avoidance for Mobile Robots Using Semantic Segmentation
and Monocular Camera," Electronics, vol. 12, no. 8, pp. 1932–1945, 2023. [Online]. Available:
https://www.mdpi.com/2079-9292/12/8/1932
[2] W. C. Kao and S. T. Ho, "An Omnidirectional Mobile Robot for Ball-Catching Tasks Using Stereo Vision
and PID Control," Sensors, vol. 21, no. 9, Art. no. 3208, May 2021. [Online]. Available:
https://www.mdpi.com/1424-8220/21/9/3208
[3] Belaidi, H., Demim, F., Mezhary, A., Rouigueb, A., Yahoui, S., Nemra, A. (2024). Enhanced Navigation
Based Obstacle Avoidance and Target Tracking with Raspberry-Pi for Mobile Robots. In: Djamaa, B.,
Boudane, A., Mazari Abdessameud, O., Hosni, A.I.E. (eds) Advances in Computing Systems and
Applications. CSA 2024. Lecture Notes in Networks and Systems, vol 1145. Springer, Cham. [Online].
Available: https://doi.org/10.1007/978-3-031-71848-9_22
[4] “Raspberry Pi Camera Module Rev 1.3,” RS Components, pdf data sheet (A700000007835051), 2013.
[Online]. Available: https://docs.rs-online.com/2888/0900766b8127db0a.pdf
[5] OpenCV.org, “OpenCV Documentation,” [Online]. Available: https://docs.opencv.org/4.x/
[6] S. Hamza and R. Rathod, "Smart Traffic Monitoring Using YOLO and OpenCV," Journal of Information
Systems Engineering and Management, vol. 10, no. 1, 2025. [Online]. Available: https://jisem-
journal.com/index.php/journal/article/view/5765
[7] M. Bagwe, S. Prakash, and A. Deshmukh, "Implementation of Smart Traffic System Using OpenCV and
Python," Electronics, vol. 11, no. 4, Art. no. 67, 2022. [Online]. Available: https://www.mdpi.com/26737590/4/4/67
[8] Raspberry Pi Foundation, “Raspberry Pi 3 Model B+ Product Brief,” datasheets.raspberrypi.com, May
2018. [Online]. Available: https://datasheets.raspberrypi.com/rpi3/raspberry-pi-3-b-plus-productbrief.pdf
[9] N. E. Budiyanta, C. O. Sereati, and L. Lukas, “P‑D controller computer vision and robotics integration
based for student’s programming comprehension improvement,” TELKOMNIKA (Telecommunication,
Computing, Electronics and Control), vol. 18, no. 2, pp. 899-906, 2020,
doi:10.12928/TELKOMNIKA.v18i2.14881.
[10] A. Saravanan, K. Ravi, and S. Shanmugam, "Performance enhancement of PID-controlled DC motor
using Kookaburra and Red Panda optimization algorithms," Scientific Reports, vol. 15, no. 1, pp. 1–13,
2025. [Online]. Available: https://www.nature.com/articles/s41598-025-87607-2
[11] I. C. Yuniar, R. Nurhadi, and B. Setiawan, "Optimization of PID controller parameters using particle
swarm optimization on DC motor speed control," Int. J. of Robotics and Control Systems, vol. 2, no. 2,
pp. 134–142, Jun. 2022. [Online]. Available: https://arxiv.org/abs/2209.09170
