Autonomous robot for launching and collecting paddle tennis balls for sports training
DOI:
https://doi.org/10.17979/ja-cea.2025.46.12263Keywords:
Artificial Vision, Artificial Neural Networks, Autonomous Robots, Mechatronic Systems, Intelligent Control, Robotics in SportsAbstract
This work presents the development of an autonomous robotic system for the detection, collection and launching of balls, with application in sports environments. The architecture combines a Raspberry Pi 5 for artificial vision processing with a ESP32 microcontroller in charge of distributed control, optimising computational efficiency and response speed. The detection is based on the YOLOv8 model, selected for its high real-time accuracy. For efficient execution on embedded platforms, the ncnn framework is used, allowing a stable rate of 6 fps to be achieved on the Raspberry Pi. The control system uses visual information - position and distance of the ball - to generate movement commands, executed by means of Mecanum wheels that provide omnidirectional manoeuvrability. In addition, a state machine is implemented to manage the operation modes: pick-up, manual and launch. The developed solution is robust, flexible and low-cost, constituting a promising basis for applications in autonomous sports or assistive robotics.
References
Deepa, R., Tamilselvan, E., Abrar, E., Sampath, S., April 2019. Comparison of yolo, ssd, faster rcnn for real time tennis ball tracking for action decision networks. In: 2019 International Conference on Advances in Computing and Communication Engineering (ICACCE). pp. 1–4. DOI: 10.1109/ICACCE46606.2019.9079965
Feng, X., Jiang, Y., Yang, X., Du, M., Li, X., 2019. Computer vision algorithms and hardware implementations: A survey. Integration 69, 309–320. URL: https://www.sciencedirect.com/science/article/pii/S0167926019301762 DOI: https://doi.org/10.1016/j.vlsi.2019.07.005
H.A.R. Eletrabi, X. W., 4 2024. Autonomous tennis assistant systems. URL: https://patents.google.com/patent/US11944876B2/en Jocher, G., Chaurasia, A., Qiu, J., 2023. Ultralytics yolov8. URL: https://github.com/ultralytics/ultralytics
Marin, 2025. Rapid rise of pickleball and padel: Opportunities in the booming u.s. racquet sports market. https://spainuschamber.com/en/rapid-rise-of-pickleball-and-padel-opportunities-inthe-booming-u-s-racquet-sports-market/.
Nathan, 2025. Tennis ball detection dataset. https://universe.roboflow.com/nathan-4tlqa/tennis-ball-detection-vksde, accessed: 2025-05-31.
Ni, H., ncnn contributors, T., 2017. ncnn: High-performance neural network inference framework. URL: https://github.com/Tencent/ncnn
Peng, T., Qian, J., Zi, B., Liu, J.,Wang, X., 2016. Mechanical design and control system of an omni-directional mobile robot for material conveying. Procedia CIRP 56, 412–415, the 9th International Conference on Digital Enterprise Technology – Intelligent Manufacturing in the Knowledge Economy Era. URL: https://www.sciencedirect.com/science/article/pii/S2212827116310605 DOI: https://doi.org/10.1016/j.procir.2016.10.068
Pereira, N., Ribeiro, F., Lopes, G., Whitney, D., Lino, J., Jan 2012. Autonomous golf ball picking robot design and development. Industrial Robot: An International Journal 39 (6), 541–550. DOI: https://doi.org/10.1108/01439911211268660
Qian, J., Zi, B., Wang, D., Ma, Y., Zhang, D., 2017. The design and development of an omni-directional mobile robot oriented to an intelligent manufacturing system. Sensors 17 (9). URL: https://www.mdpi.com/1424-8220/17/9/2073 DOI: 10.3390/s17092073
Statista, 2024. Ranking de federaciones deportivas con m´as licencias federativas en España en 2023. https://es.statista.com/estadisticas/ 1051888/ranking-de-federaciones-con-mas-deportistasfederados-espana/.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Francisco Fuentes, Daniel Rubio, Helio Tejada, William Chicaiza, Juan Manuel Escaño
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
