Development and Control of a Neural-Enhanced PD Controller for Serpentron: A Flexible Snake-like Robot with Adaptive Locomotion
Subject Areas : Multimedia Processing, Communications Systems, Intelligent Systems
Masih Sobhani
1
,
Azadeh Zarif Loloei
2
1 - BSc Student, Department of Electrical Engineering, Par.C, Islamic Azad University, Tehran, Iran
2 - Assistant Professor, Department of Electrical Engineering, Par.C, Islamic Azad University, Tehran, Iran
Keywords: Snake-like Robot, Neural Network, PD Controller, Adaptive Locomotion, Hyper-redundant Kinematics, Robotics, Control Systems,
Abstract :
This research introduces Serpentron, a novel snake-like robot with three joints and four links, designed for superior maneuverability in challenging environments. By extending the joint range to 180 degrees and incorporating virtual base rotation, Serpentron achieves a workspace diameter of 0.9 meters, a 50% improvement over traditional designs. A Neural Network-based Proportional-Derivative (NN-PD) controller is developed, dynamically tuning gains to track serpentine trajectories with joint angle errors below 0.02 radians and torques under 5 Nm, even under complex disturbances including Gaussian noise, velocity-dependent friction, and obstacle interactions. Simulations across single-direction, multiple-direction, and movable-direction scenarios demonstrate Serpentron’s adaptability, from planar navigation to dynamic base motion. The NN-PD controller reduces error variance by 50% compared to fixed-gain methods, leveraging a multilayer perceptron for real-time gain tuning. Torque analysis confirms the controller’s robustness against environmental uncertainties, ensuring stable performance within motor limits. Serpentron’s hyper-redundant kinematics and base mobility enable applications in confined-space exploration and volumetric inspection. Simulation results validate the model and control strategy, laying a scalable foundation for a cost-effective prototype using NVIDIA Jetson Nano and Dynamixel XL430 motors, with lightweight aluminum and ABS materials, to bridge the gap between simulation and real-world deployment in unstructured settings.
References [1] Ahmed, M. and Billah, M. M., “Smart material-actuated flexible tendon-based snake robot,” Int. J. Adv. Robot. Syst., Dec. 2015. [Online]. Available: doi:10.5772/62187.
[2] Burgner-Kahrs, J., Rucker, D. C., and Choset, H., “Continuum robots for medical applications: A survey,” IEEE Trans. Robot., vol. 31, no. 6, pp. 1261–1280, Dec. 2015. [Online]. Available: doi:10.1109/TRO.2015.2489500.
[3] Chirikjian, G. S. and Burdick, J. W., “The kinematics of hyper-redundant robot locomotion,” IEEE Trans. Robot. Autom., vol. 11, no. 6, pp. 781–793, Dec. 1995. [Online]. Available: doi:10.1109/70.478426.
[4] Date, H. and Takita, Y., “Adaptive locomotion of a snake-like robot based on curvature derivatives,” in Proc. 2007 IEEE/RSJ Int. Conf. Intell. Robots Syst., San Diego, CA, USA, Oct. 2007, pp. 3554–3559. [Online]. Available: doi:10.1109/IROS.2007.4399635.
[5] Hirose, S., Biologically Inspired Robots: Snake-Like Locomotors and Manipulators. Oxford, UK: Oxford Univ. Press, 1993. [Online]. Available: doi:10.1017/S0263574700017264.
[6] Hirose, S. and Mori, M., “Biologically inspired snake-like robots,” in Proc. 2004 IEEE Int. Conf. Robot. Biomimetics (ROBIO), Shenyang, China, Aug. 2004, pp. 1–7. [Online]. Available: doi:10.1109/ROBIO.2004.1521742.
[7] Ijspeert, J., “Central pattern generators for locomotion control in animals and robots: A review,” Neural Netw., vol. 21, no. 4, pp. 642–653, May 2008. [Online]. Available: doi:10.1016/j.neunet.2008.03.014.
[8] Jang, J.-S. R., Sun, C.-T., and Mizutani, E., Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence. Upper Saddle River, NJ: Prentice Hall, 1997. [Online]. Available: doi:10.1109/TAC.1997.633847.
[9] Karami, E. et al., “Applying of Zhang neural network in time-varying nonlinear function optimization,” J. Multimedia Process. Commun. Syst., Intell. Syst., Jun. 2023. [Online]. Available: doi:10.71856/impcs.2023.903573.
[10] Lewis, F. W., Jagannathan, S., and Yesildirek, A., Neural Network Control of Robot Manipulators and Non-Linear Systems. Boca Raton, FL: CRC Press, 1998. [Online]. Available: doi:10.1201/9781003062714.
[11] Li, N. et al., “A review on the recent development of planar snake robot control and guidance,” Mathematics, vol. 13, no. 2, Jan. 2025. [Online]. Available: doi:10.3390/math13020189.
[12] Liljebäck, P., Pettersen, K. Y., Stavdahl, Ø., and Gravdahl, J. T., Snake Robot Locomotion in Environments with Obstacles. London, UK: Springer, 2012. [Online]. Available: doi:10.1109/TMECH.2011.2159863.
[13] Liljebäck, P., Pettersen, K. Y., Stavdahl, Ø., and Gravdahl, J. T., “A review on modelling, implementation, and control of snake robots,” Robot. Auton. Syst., vol. 60, no. 1, pp. 29–40, Jan. 2012. [Online]. Available: doi:10.1016/j.robot.2011.08.010.
[14] Liljebäck, P., Pettersen, K. Y., and Stavdahl, Ø., “A snake robot with a contact force measurement system for obstacle-aided locomotion,” in Proc. IEEE Int. Conf. Robot. Autom. (ICRA), Anchorage, AK, USA, May 2010, pp. 1–6. [Online]. Available: doi:10.1109/ROBOT.2010.5509839.
[15] Liljebäck, P., Pettersen, K. Y., Stavdahl, Ø., and Gravdahl, J. T., Snake Robots: Modelling, Mechatronics, and Control. London, UK: Springer, 2013. [Online]. Available: doi:10.1007/978-1-4471-2996-7.
[16] Lopez-Arreguin, A. J. R., “Towards bio-inspired robots for underground and surface exploration in planetary environments: An overview and novel developments inspired in sand-swimmers,” Heliyon, vol. 6, no. 6, Jun. 2020. [Online]. Available: doi:10.1016/j.heliyon.2020.e04207.
[17] Mahavarpour, S., “Integrating adaptive reinforcement learning and robotic process automation for real-time decision-making in dynamic environments,” Majlesi J. Telecommun. Devices, Apr. 2025. [Online]. Available: doi:10.71822/mjtd.2025.1189522.
[18] Marvi, H. and Hu, D. L., “Serpentine locomotion of snake robots: Modeling and control,” IEEE Robot. Autom. Mag., vol. 24, no. 3, pp. 88–97, Sep. 2017. [Online]. Available: doi:10.1109/MRA.2017.2719028.
[19] Murphy, R., Disaster Robotics. Cambridge, MA: MIT Press, 2014. [Online]. Available: doi:10.7551/mitpress/9780262027359.001.0001.
[20] Seeja, G. et al., “A survey on snake robot locomotion,” IEEE Access, vol. 10, pp. 111027–111047, Oct. 2022. [Online]. Available: doi:10.1109/ACCESS.2022.3215162.
[21] Siciliano, B. and Khatib, O., Eds., Springer Handbook of Robotics, 2nd ed. Cham, Switzerland: Springer, 2016. [Online]. Available: doi:10.1007/978-3-319-32552-1.
[22] Tanaka, M., Kamegawa, T., and Ariizumi, R., “Special issue on robotics and mechatronics technology for snake-like and hyper-redundant robots,” J. Robot. Mechatron., vol. 36, no. 6, Dec. 2024. [Online]. Available: doi:10.20965/jrm.2024.p1301.
[23] Yang, X. et al., “The snake-inspired robots: A review,” Assem. Autom., vol. 42, no. 4, pp. 567–583, Jul. 2022. [Online]. Available: doi:10.1108/AA-03-2022-0058.
[24] Yildirim, Ş. and Kirakoya, A., “Design and proposed model reference trajectory control of a snake-like robot,” in Snake Robots: Design and Control, Cham, Switzerland: Springer, 2021, pp. 1–20. [Online]. Available: doi:10.1007/978-3-319-60702-3_20.
