Artificial Neural Network Based Tactile Sensing Unit for Robotic Hand

  • Dong-Kyo Jeong
  • Dong-Eon Kim
  • Li Ailimg
  • Jang-Myung LeeEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11740)


Unlike the conventional haptic detection with the tactile sensor or Force Sensing Resistor (FSR) sensor, this paper proposes a new algorithm for tactile sensing unit that air pressure sensors are implemented to represent the tactile degree of the robot hand which can play more accurate haptic feedback. Meanwhile, in order to optimize the performance of the tactile sensing unit, several target objects are trained with the help of Artificial Neural Network (ANN) that gives the linear output values according to the constant mass when the robot hand holds different target objects. In addition, Arrival of Time (A.o.T) algorithm is utilized for recognizing the touch points of the robot hand when the target object is compressed by the tactile sensing device. The optimal output positions can be selected through amounts of tests with various grasp positions in the haptic sensing part for the reason that different pressure-points distribution facilitates the optimization mapping. Experiments show that the proposed method can be applied for Human Robot Interaction (HRI) effectively and efficiently.


Artificial neural network Air pressure sensor Tactile sensing unit Grasp positions 



This research is based upon work supported by the Ministry of Trade, Industry & Energy (MOTIE, Korea) under Industrial Technology Innovation Program. No.10073147.


  1. 1.
    Cramphorn, L., Ward-Cherrier, B., Lepora, N.F.: Tactile manipulation with biomimetic active touch. In: 2016 IEEE International Conference on Robotics and Automation (ICRA). IEEE (2016)Google Scholar
  2. 2.
    Nathan, L., Alex, C., Conrad, K., Raia, H., John, L.: From pixels to percepts: highly robust edge perception and contour following using deep learning and an optical biomimetic tactile sensor. IEEE Robot. Autom. Lett. 4(2), 2101–2107 (2019)CrossRefGoogle Scholar
  3. 3.
    Schmitz, A., et al.: Tactile object recognition using deep learning and dropout. In: 2014 IEEE-RAS International Conference on Humanoid Robots. IEEE (2014)Google Scholar
  4. 4.
    Baishya, S.S., Bäuml, B.: Robust material classification with a tactile skin using deep learning. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (2016)Google Scholar
  5. 5.
    Claudio, C., Vikram, R.: A wearable low-cost device based upon force-sensing resistors to detect single-finger forces. In: IEEE RAS & EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) (2014)Google Scholar
  6. 6.
    Bahadır, S.K.: Identification and modeling of sensing capability of force sensing resistor integrated to E-textile structure. IEEE Sens. J. 18(23), 9770–9780 (2018)CrossRefGoogle Scholar
  7. 7.
    Dang, H., Allen, P.K.: Stable grasping under pose uncertainty using tactile feedback. Auton. Robot. 36(4), 309–330 (2014)CrossRefGoogle Scholar
  8. 8.
    Vinicius, F., Thiago, E.O., Katerina, E., Emil, M.P.: Stable grasping and object reorientation with a three-fingered robotic hand. In: IEEE International Symposium on Robotics and Intelligent Sensors (IRIS2017) (2017)Google Scholar
  9. 9.
    Wan, Q., Adams, R.P., Howe, R.D.: Variability and predictability in tactile sensing during grasping. In: IEEE International Conference on Robotics and Automation (ICRA) (2016)Google Scholar
  10. 10.
    Kim, D.E., Kim, K.S., Park, J.H., Ailing, L., Lee, J.M.: Stable grasping of objects using air pressure sensors on a robot hand. In: International Conference on Control, Automation and Systems (ICCAS 2018) (2018)Google Scholar
  11. 11.
    Chang, C.-H.: Deep and shallow architecture of multilayer neural networks. IEEE Transact. Neural Netw. Learn. Syst. 26(10), 2477–2486 (2015)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Gong, M., et al.: A multiobjective sparse feature learning model for deep neural networks. IEEE Transact. Neural Netw. Learn. Syst. 26(12), 3263–3277 (2015)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Păvăloiu, I.B., et al.: Feedforward multilayer phase-based neural networks. In: 12th Symposium on Neural Network Applications in Electrical Engineering (NEUREL). IEEE (2014)Google Scholar
  14. 14.
    Rika, A., Mia, K., Johannes, A.S., Danica, K.: Global search with bernoulli alternation kernel for task-oriented grasping informed by simulation. In: 2nd Conference on Robot Learning (CoRL 2018) (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Dong-Kyo Jeong
    • 1
  • Dong-Eon Kim
    • 1
  • Li Ailimg
    • 1
  • Jang-Myung Lee
    • 2
    Email author
  1. 1.Department of Electrical and Computer EngineeringPusan National UniversityBusanKorea
  2. 2.Department of Electronic EngineeringPusan National UniversityBusanKorea

Personalised recommendations