Ashish Gad ¹*

¹ The Engineering College
Monk Ferry, Birkenhead, CH41 5LH, United Kingdom
* Corresponding author. E-mail: a.gad@theengineeringcollege.co.uk

Robotica & Management, Vol. 31, No. 1, pp. 04-09
DOI: https://doi.org/10.24193/rm.2026.1.1

Abstract: Soft robotic manipulators are increasingly utilized in minimally invasive surgery. They are compliant and provide safe operation in proximity to delicate tissues. However, the inherent nonlinear dynamics of soft materials, combined with the presence of noisy signals originating from surgical camera systems, compromise the reliability of conventional PID controllers, which frequently results in the manifestation of “derivative kick” vibrations. This paper introduces a robust, lightweight Adaptive Neural-PID controller implemented within the Scilab environment. This controller employs a Delta-rule learning algorithm for the real-time adjustment of PID gains, which is coupled with a rudimentary exponential moving average filter applied to the state data.
Keywords: Soft Robotics, Adaptive Neural control, Low-Pass Filtering, Trajectory Tracking, Sensor Noise Mitigation.

Full text

References

[1] Chen Z. et al.: “Hysteresis-Aware Neural Network Modeling and Whole-Body Reinforcement Learning Control of Soft Robots”, IEEE Robotics and Automation Letters, 2025, p. 1. doi: 10.1109/lra.2025.3615025.

[2] Kunčar A.: “Basic Techniques for Filtering Noise Out of Accelerometer Data”, Annals of DAAAM for … & proceedings of the International DAAAM Symposium, DAAAM International Vienna, 2016, p. 1122. doi: 10.2507/26th.daaam.proceedings.158.

[3] Poza-Luján J.-L., Uribe-Chavert P., Posadas-Yagüe J.-L.: “Low-cost modular devices for on-road vehicle detection and characterisation”, Design Automation for Embedded Systems, Vol. 27, 2023, p. 85. doi: 10.1007/s10617-023-09270-y.

[4] Bachhuber S., Pawluchin A., Pal A., Boblan I., Seel T.: “A Soft Robotic System Automatically Learns Precise Agile Motions Without Model Information”, arXiv (Cornell University), 2024. doi: 10.48550/arxiv.2408.03754.

[5] Yan Y., Ding Q., Li M., Yan J., Cheng S. S.: “Refined Motion Compensation with Soft Laser Manipulators using Data-Driven Surrogate Models”, arXiv (Cornell University), 2024. doi: 10.48550/arxiv.2407.01891.

[6] Fu X.: “Modeling and Control of Continuum Appendages”, Deep Blue (University of Michigan), 2024. doi: 10.7302/23029.

[7] Manzano S. A. et al.: “Toward smart composites: Small-scale, untethered prediction and control for soft sensor/actuator systems”, Journal of Composite Materials, Vol. 56, No. 26, 2022, p. 4025. doi: 10.1177/00219983221129691.

[8] “Polynomial Recurrent Neural Network-Based Adaptive PID Controller With Stable Learning Algorithm”. doi: 10.1007/s11063-022-10989-1.

[9] Meng P.-P., Jin X., Niu Y., Kong W. I., Xi Y.: “Design of a surgical robot servo control system based on RBF neural network adaptive PID”, Research Square (Research Square), 2024. doi: 10.21203/rs.3.rs-5232481/v1.

[10] Nguyet N. T. M., Ba D. X.: “A neural flexible PID controller for task-space control of robotic manipulators”, Frontiers in Robotics and AI, Vol. 9, 2023. doi: 10.3389/frobt.2022.975850.

[11] Hénaff P.: “Bio-inspired control and genesis of rhythmic movements in robotics”, HAL (Le Centre pour la Communication Scientifique Directe), 2011. Accessed: Oct. 2025. [Online]. Available: https://tel.archives-ouvertes.fr/tel-00667651

[12] Robinson P. J.: “A Novel Learning Rule in Intuitionistic Fuzzy Artificial Neural Network and its Applications to MAGDM Support System”, Research Square (Research Square), 2023. doi: 10.21203/rs.3.rs-3692501/v1.

[13] Vigne M.: “Estimation and control of the deformations of an exoskeleton using inertial sensors”, HAL (Le Centre pour la Communication Scientifique Directe), 2021. Accessed: Mar. 2025. [Online]. Available: https://pastel.archives-ouvertes.fr/tel-03559553

[14] Wood K., Roberts S. J., Zohren S.: “DeePM: Regime-Robust Deep Learning for Systematic Macro Portfolio Management”, arXiv (Cornell University), 2026. doi: 10.48550/arxiv.2601.05975.

[15] Zhang X., HosseinNia S. H.: “Enhancing Reset Control Phase with Lead Shaping Filters: Applications to Precision Motion Systems”, arXiv (Cornell University), 2025. doi: 10.48550/arxiv.2503.15020.

[16] Oguten S., Kabaş B.: “PID Controller Optimization for Low-cost Line Follower Robots”, arXiv (Cornell University), 2022. doi: 10.48550/arxiv.2111.04149.

[17] “Which is the best PID variant for pneumatic soft robots an experimental study”. doi: 10.1109/jas.2020.1003045.

[18] Yuan K., Li Z.: “Multi-expert synthesis for versatile locomotion and manipulation skills”, Frontiers in Robotics and AI, Vol. 9, 2022. doi: 10.3389/frobt.2022.970890.

[19] Okelola M. O., Aborisade D., Adewuyi P. A.: “Performance and Configuration Analysis of Tracking Time Anti-Windup PID Controllers”, Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, Vol. 6, No. 2, 2021, p. 20. doi: 10.26555/jiteki.v6i2.18867.

[20] Nohooji H. R., Voos H.: “Nussbaum Function Based Approach for Tracking Control of Robot Manipulators”, arXiv (Cornell University), 2024. doi: 10.48550/arxiv.2403.00970.

[21] Shachar A.: “Introduction to Algogens”, arXiv (Cornell University), 2024. doi: 10.48550/arxiv.2403.01426.

[22] Verma S., Lai B., Bernstein D. S.: “Adaptive Real-Time Numerical Differentiation with Variable-Rate Forgetting and Exponential Resetting”, arXiv (Cornell University), 2023. doi: 10.48550/arxiv.2309.16159.

[23] Zhang B., Lan X., Wang G., Pang Z., Zhang X., Sun Z.: “A noise-suppressing neural network approach for upper limb human-machine interactive control based on sEMG signals”, Frontiers in Neurorobotics, Vol. 16, 2022. doi: 10.3389/fnbot.2022.1047325.

[24] Oveisi A.: “System Identification and Model-based Robust Nonlinear Disturbance Rejection Control”, arXiv (Cornell University), 2022. doi: 10.48550/arxiv.2106.06816.

[25] Penas R.: “Models of dissipative bushings in multibody dynamics”, HAL (Le Centre pour la Communication Scientifique Directe), 2021. Accessed: Apr. 2025. [Online]. Available: https://hal.archives-ouvertes.fr/tel-03612187

[26] Elsayed M., Lan Q., Lyle C., Mahmood A. R.: “Weight Clipping for Deep Continual and Reinforcement Learning”, arXiv (Cornell University), 2024. doi: 10.48550/arxiv.2407.01704.