Machine Learning-Driven Polymer Composite Smart Skin for Integrated Sensing in Soft Robotic Systems

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 14 | 01 | Page :
    By

    Harish Reddy Gantla,

  • Radha Seelaboyina,

  • M. Sreenivasulu,

  • S. Sagar Imambi,

  • Sanjeev Kumar,

  • Muthukumar Subramanian,

  1. Associate Professor, Department of Computer Science and Engineering, Vignan Institute of Technology and Science, Telangana, India
  2. Associate Professor, Department of Computer Science and Engineering, Geethanjali College of Engineering & Technology, Hyderabad, Telangana, India
  3. Associate Professor, Department of Electrical and Communication Engineering, Kishkindha University, Mount View Campus, Balkari-Siruguppa Road, Karnataka, India
  4. Professor, Department of Computer Science and Engineering, Koneru Lakakshmaih Education and Foundation, Vaddeswaram, Guntur, Andhra Pradesh, India
  5. Associate Professor, Department of Electrical and Communication Engineering, Aditya University, Surampalem, Andhra Pradesh, India
  6. Professor, Department of Computer Science and Engineering, Hindustan Institute of Technology & Science (Deemed to Be University), Chennai, Tamil Nadu, India

Abstract

Soft robotics has grown rapidly, but its progress is still constrained by the limitations of current sensing skins. Most polymer-based sensors provide either flexibility or sensitivity, yet they struggle to deliver real-time communication and adaptive intelligence when deployed in complex robotic environments. This disconnect between material performance and system-level responsiveness forms a critical bottleneck for practical deployment. Existing approaches often treat tactile sensing and wireless communication as separate problems. As a result, signal delays, noise accumulation, and restricted adaptability remain common, especially when robots must operate continuously in dynamic or human-interactive settings. To address this gap, we present a polymer-based smart skin that integrates carbon nanotube–graphene composites with a 6G-enabled ISAC module and a machine learning pipeline. The framework unifies sensing, communication, and adaptive control in a single stretchable layer. CNN–LSTM architectures were used to interpret tactile signals, while reinforcement learning optimized trade-offs between accuracy, capacity, and power efficiency. Experiments confirmed that the proposed skin achieved 94.7% recognition accuracy and maintained communication capacity above 22 Gbps under strain. Latency was reduced to below 6 ms, nearly halving values reported in earlier ISAC prototypes. Energy consumption fell by more than 20% through adaptive control. These results suggest that polymer composites, when embedded with ML-driven ISAC, can move beyond laboratory prototypes and into practical robotic systems. The work opens pathways toward low-latency, intelligent skins for soft robotics with implications for healthcare, collaborative manufacturing, and networked autonomous systems.

Keywords: Tactile sensing, nanocomposites, CNN–LSTM, reinforcement learning, 6G-enabled ISAC, machine learning, polymer-based smart skin, soft robotics.

How to cite this article:
Harish Reddy Gantla, Radha Seelaboyina, M. Sreenivasulu, S. Sagar Imambi, Sanjeev Kumar, Muthukumar Subramanian. Machine Learning-Driven Polymer Composite Smart Skin for Integrated Sensing in Soft Robotic Systems. Journal of Polymer & Composites. 2026; 14(01):-.
How to cite this URL:
Harish Reddy Gantla, Radha Seelaboyina, M. Sreenivasulu, S. Sagar Imambi, Sanjeev Kumar, Muthukumar Subramanian. Machine Learning-Driven Polymer Composite Smart Skin for Integrated Sensing in Soft Robotic Systems. Journal of Polymer & Composites. 2026; 14(01):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=235724


References

  1. Liu, E. Alsusa, A. Al‐Dweik, and N. Ali, “A CSI-Anomaly-Based Approach to ISaC,” Jan. 2025, doi: 10.36227/techrxiv.173699800.09149938/v1.
  2. Feliu-Talegón, Y. A. Adamu, A. T. Mathew, A. Y. Alkayas, and F. Renda, “Advancing Soft Robot Proprioception Through 6D Strain Sensors Embedding,” Soft robotics, Jan. 2025, doi: 10.1089/soro.2024.0017.
  3. Lv, W. Hao, F. Xiao, P.-Y. Chen, Z. Liu, and Y. Wang, “Soft pneumatic actuator from particle reinforced silicone rubber: Simulation and experiments,” Journal of Applied Polymer Science, vol. 139, no. 33, Jul. 2022, doi: 10.1002/app.52795.
  4. E. Okere and V. Balyan, “Sixth Generation Enabling Technologies and Machine Learning Intersection: A Performance Optimization Perspective,” Future Internet, vol. 17, no. 2, p. 50, Jan. 2025, doi: 10.3390/fi17020050.
  5. Meng, C. Masouros, K. Wong, A. P. Petropulu, and L. Hanzo, “Integrated Sensing and Communication Meets Smart Propagation Engineering: Opportunities and Challenges,” IEEE Network, p. 1, Jan. 2025, doi: 10.1109/mnet.2025.3527130.
  6. S. Sam, A. Dey, and S. Ramanath, “Learning-Based Sensing Mode Selection for ISAC in Intelligent Transportation Systems”, doi: 10.1109/comsnets63942.2025.10885559.
  7. Jin et al., “Finite element analysis, machine learning, and digital twins for soft robots: state-of-arts and perspectives,” Smart Materials and Structures, Jan. 2025, doi: 10.1088/1361-665x/adadcd.
  8. Wang et al., “Cooperative Integrated Sensing and Communication in 6G: from Operators Perspective”, doi: 10.1109/mwc.010.2400063.
  9. -W. Hsieh and C.-Y. Chien, “Wearable Capacitive Tactile Sensor Based on Porous Dielectric Composite of Polyurethane and Silver Nanowire,” Polymers, Sep. 2023, doi: 10.3390/polym15183816.
  10. Kim, S. Lee, A. A. Melvin, and J.-W. Choi, “Stimuli-Responsive Polymer Actuator for Soft Robotics,” Polymers, vol. 16, no. 18, p. 2660, Sep. 2024, doi: 10.3390/polym16182660.
  11. Yang, H. Zhu, J. J. Liu, H. Lu, Y. Ren, and M. Y. Wang, “A Proprioceptive Soft Robot Module Based on Supercoiled Polymer Artificial Muscle Strings,” Polymers, vol. 14, no. 11, p. 2265, Jun. 2022, doi: 10.3390/polym14112265.
  12. Sun, “Rotatable and Movable Antenna-Enabled Near-Field Integrated Sensing and Communication,” Jan. 2025, doi: 10.48550/arxiv.2501.04490.
  13. Zolfagharian, M. R. Khosravani, H. D. Vu, M. K. Nguyen, A. Z. Kouzani, and M. Bodaghi, “AI-Based Soft Module for Safe Human–Robot Interaction towards 4D Printing,” Polymers, vol. 14, no. 16, p. 3302, Aug. 2022, doi: 10.3390/polym14163302.
  14. Liu et al., “Perception and Recognition of Proximity and Contact Processes via Parallel Double‐Transistor Configuration,” Advanced Functional Materials, Jan. 2025, doi: 10.1002/adfm.202422733.
  15. Wang et al., “Ultra-stretchable, self-healing, bonding, and skin-inspired conductive triple network hydrogel for wearable strain sensors and friction nanogenerators,” Polymer, May 2024, doi: 10.1016/j.polymer.2024.127169.
  16. Xu, H. Nguyen, S. H. Jeong, and K. Hjort, “Miniaturized Soft Pneumatic Actuator Matrix with Multiplexing Control,” Jan. 2025, doi: 10.1002/adrr.202400015.”
  17. Selleri et al., “Self-Sensing Soft Skin Based on Piezoelectric Nanofibers,” Polymers, vol. 15, no. 2, p. 280, Jan. 2023, doi: 10.3390/polym15020280.
  18. Ayrilmis N, Kanat G, Yildiz Avsar E, Palanisamy S, Ashori A. Utilizing waste manhole covers and fibreboard as reinforcing fillers for thermoplastic composites. Journal of Reinforced Plastics and Composites. 2024;44(17-18):1108-1118. doi:10.1177/07316844241238507
  19. Ma et al., “Additive manufacturing of polymer composite millimeter‐wave components: Recent progress, novel applications, and challenges,” Polymer Composites, Aug. 2024, doi: 10.1002/pc.28985.
  20. Zheng, D. Guo, W. Yang, and H. Liu, “A Large-Area Robotic Skin for Intelligent Tactile Interaction of Collaborative Robots,” IEEE-ASME Transactions on Mechatronics, pp. 1–11, Jan. 2025, doi: 10.1109/tmech.2024.3520953.
  21. Honciuc, A. M. Solonaru, and M. Teodorescu, “Flexible Composites with Variable Conductivity and Memory of Deformation Obtained by Polymerization of Polyaniline in PVA Hydrogel,” Polymers, vol. 14, no. 21, p. 4638, Oct. 2022, doi: 10.3390/polym14214638.
  22. Zeng et al., “Ferroelectric/Electric-Double-Layer-Modulated Synaptic Thin Film Transistors toward an Artificial Tactile Perception System,” ACS Applied Materials & Interfaces, Jan. 2025, doi: 10.1021/acsami.4c19092.
  23. Saxena and K. Patra, “Fabrication and characterization of human finger ridge‐inspired soft elastomeric pressure sensor with liquid metal‐embedded microchannels,” Polymer International, Jul. 2024, doi: 10.1002/pi.6676.
  24. Wu et al., “Autonomous Self‐Healing Magnetoelectric I‐Skin from Self‐Bonded Deep Eutectic Polymer,” Small methods, Jan. 2025, doi: 10.1002/smtd.202402190.
  25. W. Alam et al., “Recent Progress, Challenges, and Trends in Polymer-Based Sensors: A Review,” Polymers, vol. 14, no. 11, p. 2164, May 2022, doi: 10.3390/polym14112164.
  26. Luo et al., “Knitting Elastic Conductive Fibers of MXene/Natural Rubber for Multifunctional Wearable Sensors,” Polymers, vol. 16, no. 13, p. 1824, Jun. 2024, doi: 10.3390/polym16131824.
  27. Donato, M. Lo Preti, L. Beccai, and E. Falotico, “Sensorimotor Control Strategies for Tactile Robotics,” Jan. 2025, doi: 10.48550/arxiv.2501.09468.
  28. Li, S. Zhang, Y. Ge, and C. Yuen, “STAR-RIS Aided Dynamic Scatterers Tracking for Integrated Sensing and Communications,” Jan. 2025, doi: 10.48550/arxiv.2501.03793.
  29. M. Mateos-Ramos, C. Häger, M. F. Keskin, L. Le Magoarou, and H. Wymeersch, “Model-Based End-to-End Learning for Multi-Target Integrated Sensing and Communication under Hardware Impairments,” IEEE Transactions on Wireless Communications, p. 1, Jan. 2025, doi: 10.1109/twc.2024.3522667.
  30. Palanisamy, S.; Kalimuthu, M.; Santulli, C.; Palaniappan, M.; Nagarajan, R.; Fragassa, C. Tailoring Epoxy Composites with Acacia caesia Bark Fibers: Evaluating the Effects of Fiber Amount and Length on Material Characteristics. Fibers 2023, 11, 63. https://doi.org/10.3390/fib11070063

 

Ahead of Print Subscription Original Research
Volume 14
01
Received 28/10/2025
Accepted 06/11/2025
Published 07/01/2026
Publication Time 71 Days
94

Login


My IP

PlumX Metrics