SavedAdd your journal

Journals / Cankaya University Journal of Science and Engineering / 2026 / Volume: 23 Issue: 1

Implementation of an Optical Tactile Sensing System with Machine Learning

Yusuf Buğra Günaydın(CANKAYA UNIVERSITY)0009-0004-4520-1284
Elif Safel(CANKAYA UNIVERSITY)0009-0001-7037-6105
Ahmet Gökay Çaliş(CANKAYA UNIVERSITY)0009-0006-8055-0433
Çağlar Arpali(CANKAYA UNIVERSITY)0000-0002-5805-3485
Pages
—
Publication Date
2026-05-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The developed sensing system offers a low-cost and effective solution for applications requiring surface recognition and object classification in automotive, industrial and robotic systems.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study, a cost-effective tactile sensing system based on optical sensing technology was developed.
📊
Key Findings & Data:The proposed system consists of a 4×4 sensor array designed for surface shape detection and force-based signal acquisition under external loading.
💡
Conclusion & Impact:The developed sensing system offers a low-cost and effective solution for applications requiring surface recognition and object classification in automotive, industrial and robotic systems.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Artificial Neural Networks · Machine Learning · Optical Tactile Sensors

Abstract

In this study, a cost-effective tactile sensing system based on optical sensing technology was developed. The proposed system consists of a 4×4 sensor array designed for surface shape detection and force-based signal acquisition under external loading. During operation, the applied force is converted into an optical signal, and the acquired sensor outputs are classified by an artificial neural- network (ANN) model. Variations in surface patterns, such as flat, wavy, and edged structures, produce different optical intensity distributions depending on the applied force, enabling the recognition of surface characteristics. Using only 16 sensors, the developed system achieved effective surface classification with a spatial force sensitivity of 2.15 N/cm². The ANN-based model achieved a surface profile identification accuracy of 94.2%. The developed sensing system offers a low-cost and effective solution for applications requiring surface recognition and object classification in automotive, industrial and robotic systems.

🔖

Cite This Article

Günaydın, Y. B., Safel, E., Çaliş, A. G., Arpali, Ç. (2026). Implementation of an Optical Tactile Sensing System with Machine Learning. Cankaya University Journal of Science and Engineering, Volume: 23 Issue: 1. https://ajindex.com/articles/1468608

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (16)

  1. Z. Kappassov, J.-A. Corrales, and V. Perdereau, “Tactile sensing in dexterous robot hands—Review,” Robot. Auton. Syst., vol. 74, pp. 195–220, Dec. 2015, doi: 10.1016/j.robot.2015.07.015.
  2. Y. Al-Handarish et al., “A survey of tactile-sensing systems and their applications in biomedical engineering,” Adv. Mater. Sci. Eng., vol. 2020, Art. no. 4047937, Jan. 2020, doi: 10.1155/2020/4047937.
  3. C. Chi, X. Sun, N. Xue, T. Li, and C. Liu, “Recent progress in technologies for tactile sensors,” Sensors, vol. 18, no. 4, Art. no. 948, Apr. 2018, doi: 10.3390/s18040948.
  4. C. W. de Silva, Sensors and Actuators: Engineering System Instrumentation, 2nd ed. Boca Raton, FL, USA: CRC Press, 2015.
  5. S. Zhang, Z. Chen, Y. Gao, W. Wan, and H. A. Varol, “Hardware technology of vision-based tactile sensor: A review,” IEEE Sens. J., vol. 22, no. 22, pp. 21410–21427, Nov. 2022, doi: 10.1109/JSEN.2022.3210210.
  6. Q. Sun, B. He, C. Xiong, W. Zhang, and H. A. Varol, “Force measurement technology of vision-based tactile sensor,” Adv. Intell. Syst., Jan. 2025, doi: 10.1002/aisy.202400290.
  7. W. Yuan, S. Dong, and E. H. Adelson, “GelSight: High-resolution robot tactile sensors for estimating geometry and force,” Sensors, vol. 17, no. 12, Art. no. 2762, Dec. 2017, doi: 10.3390/s17122762.
  8. B. Ward-Cherrier et al., “The TacTip family: Soft optical tactile sensors with 3D-printed biomimetic morphologies,” Soft Robot., vol. 5, no. 2, pp. 216–227, Apr. 2018, doi: 10.1089/soro.2017.0052.
  9. M. Lambeta et al., “DIGIT: A novel design for a low-cost compact high-resolution tactile sensor with application to in-hand manipulation,” IEEE Robot. Autom. Lett., vol. 5, no. 3, pp. 3838–3845, Jul. 2020, doi: 10.1109/LRA.2020.2977257.
  10. N. Funk et al., “Evetac: An event-based optical tactile sensor for robotic manipulation,” IEEE Trans. Robot., vol. 40, 2024, doi: 10.1109/TRO.2024.3428430.
  11. K. Sato, K. Kamiyama, N. Kawakami, and S. Tachi, “Finger-shaped GelForce: Sensor for measuring surface traction fields for robotic hand,” IEEE Trans. Haptics, vol. 3, no. 1, pp. 37–47, Jan. 2010, doi: 10.1109/TOH.2009.47.
  12. H. Xie, A. Jiang, L. Seneviratne, and K. Althoefer, “Pixel-based optical fiber tactile force sensor for robot manipulation,” in Proc. IEEE Sensors, Oct. 2012, doi: 10.1109/ICSENS.2012.6411462.
  13. P. Kampmann and F. Kirchner, “A tactile sensing system for underwater manipulation,” in Proc. Workshop on Advances in Tactile Sensing and Touch-Based Human-Robot Interaction (HRI), Boston, MA, USA, Mar. 2012.
  14. L. Massari et al., “Tactile sensing and control of robotic manipulator integrating fiber Bragg grating strain-sensor,” Front. Neurorobot., vol. 13, Art. no. 8, Feb. 2019, doi: 10.3389/fnbot.2019.00008.
  15. Z. Kappassov et al., “Color-coded fiber-optic tactile sensor for an elastomeric robot skin,” in Proc. IEEE Int. Conf. Robot. Autom. (ICRA), May 2019, doi: 10.1109/ICRA.2019.8793262.
  16. J. B. Jeong, H. Kim, and J.-I. Yoo, “Triboelectric touch sensor for position mapping during total hip arthroplasty,” BMC Res. Notes, vol. 13, no. 1, Art. no. 395, Aug. 2020, doi: 10.1186/s13104-020-05238-4.