Spherical Robot Control: Classical and Intelligent Approaches

https://doi.org/10.58571/CNCA.AMCA.2025.015

Resumen: Spherical robots offer omnidirectional mobility and mechanical robustness, making them ideal for exploration and surveillance in unstructured environments. However, their control is challenging due to their non-linear and coupled dynamics. This paper presents the design, modelling and control of a spherical robot with an internal pendulum. The approach combines realistic simulations in CoppeliaSim, experimental validation using a visual tracking platform, and advanced control strategies based on Deep Reinforcement Learning (DQN and DDPG) and traditional approaches. Results from both simulation and real-world experiments demonstrate the effectiveness of model-free learning techniques in achieving stable and accurate position control.

¿Cómo citar?

Fabregas, E., Montenegro, G., Schröder, K., Escorza, O., Garcia, G. & Farias, G. (2025). Spherical Robot Control: Classical and
Intelligent Approaches. Memorias del Congreso Nacional de Control Automático 2025, pp. 86-91. https://doi.org/10.58571/CNCA.AMCA.2025.015

Palabras clave

Robótica Móvil; Control Clásico; Redes Neuronales.

• Diouf, A., Belzile, B., Saad, M., and St-Onge, D. (2024). Spherical rolling robots—design, modeling, and control: A systematic literature review. Robotics and Autonomous Systems, 175, 104657.
• Escorza, O., Garcia, G., Fabregas, E., Velastin, S.A., Eskandarian, A., and Farias, G. (2025). Deep reinforcement learning applied to a spherical robot for target tracking. IEEE Transactions on Industrial Electronics, 1–10.
• Fabregas, E., Farias, G., Aranda-Escol´astico, E., Garcia, G., Chaos, D., Dormido-Canto, S., and Dormido, S. (2020). Simulation and experimental results of a new control strategy for point stabilization of nonholonomic mobile robots. IEEE Transactions on Industrial Electronics, 67(8), 6679–6687.
• Gonzalez-Villela, V., Parkin, R., Para, M., and Dorador-Gonzalez, J. (2004). A wheeled mobile robot with obstacle avoidance capability. Mech. Technologia, 1, 150–159.
• Greitans, M. (2025). Automatic control and computer sciences: A multidisciplinary platform for robotics and control systems. Automatic Control and Computer Sciences, 58(8).
• Kelly, J.F. (2014). 3D modeling and printing with Tinkercad: create and print your own 3D models. Que Publishing.
• Lin, R., Huo, J., Yang, X., Wang, Q., Yang, R., and Xu, J. (2024). XK-III: A spherical robot with redundant degrees of freedom. Journal of Intelligent & Robotic Systems, 110(104).
• Mnih, V., Badia, A., Mirza, M., Graves, A., Harley, T., Silver, D., and Kavukcuoglu, K. (2016). Asynchronous methods for deep reinforcement learning. International Conference on Machine Learning, 1928–1937.
• Montenegro, G., Chac´on, R., Fabregas, E., et al. (2022). Modeling and control of a spherical robot in the coppeliasim simulator. Sensors, 22(16), 6020.
• Schröder, K., Garcia, G., Chac´on, R., et al. (2023). Development and control of a real spherical robot. Sensors, 23(8), 3895.
• Sharma, N., Pandey, J.K., and Mondal, S. (2023). A review of mobile robots: Applications and future prospect. International Journal of Precision Engineering and Manufacturing, 24, 1695–1706.
• Siegwart, R., Nourbakhsh, I.R., and Scaramuzza, D. (2011). Introduction to Autonomous Mobile Robots. MIT Press.
• Sumiea, E.H., Abdulkadir, S.J., Alhussian, H.S., Al-Selwi, S.M., Alqushaibi, A., Ragab, M.G., and Fati, S.M. (2024). Deep deterministic policy gradient algorithm: A systematic review. Heliyon.
• Verma, G. (2018). Autodesk fusion 360 black book. BPB Publications.
• Vidaña, J.E.V., Garcia-Hernandez, R., Alvarez-Macias, C., and Murillo-Garcia, O.F. (2024). Pid control for a spherical robot applied as a solar tracking system. In 2024 XXVI Robotics Mexican Congress (COMRob), 123–128. IEEE.
• Wang, Y., Wang, Y., Liu, Y., Guan, X., Hu, T., Zhang, Z., Hao, J., and Li, G. (2023). New riccati velocity controller of the spherical robot. Journal of Intelligent & Robotic Systems, 108(3), 51.