Hostname: page-component-7dd5485656-wxk4p Total loading time: 0 Render date: 2025-10-30T04:39:19.522Z Has data issue: false hasContentIssue false
  • English
  • Français

Neural Network Design for Manipulator Collision Detection Based Only on the Joint Position Sensors

Published online by Cambridge University Press:  27 June 2019

Abdel-Nasser Sharkawy Open the ORCID record for Abdel-Nasser Sharkawy [Opens in a new window] ,
Panagiotis N. Koustoumpardis  and
Nikos Aspragathos
Abdel-Nasser Sharkawy*
Affiliation:
Mechanical Engineering Department, Faculty of Engineering, South Valley University, Qena 83523, Egypt Department of Mechanical Engineering and Aeronautics, University of Patras, Rio 26504, Greece. E-mails: koust@mech.upatras.gr, asprag@mech.upatras.gr
Panagiotis N. Koustoumpardis
Affiliation:
Department of Mechanical Engineering and Aeronautics, University of Patras, Rio 26504, Greece. E-mails: koust@mech.upatras.gr, asprag@mech.upatras.gr
Nikos Aspragathos
Affiliation:
Department of Mechanical Engineering and Aeronautics, University of Patras, Rio 26504, Greece. E-mails: koust@mech.upatras.gr, asprag@mech.upatras.gr
*
*Corresponding author. E-mail: eng.abdelnassersharkawy@gmail.com
Get access Rights & Permissions [Opens in a new window]

Summary

In this paper, a multilayer feedforward neural network (NN) is designed and trained, for human–robot collisions detection, using only the intrinsic joint position sensors of a manipulator. The topology of one NN is designed considering the coupled dynamics of the robot and trained, with and without external contacts, by Levenberg–Marquardt algorithm to detect unwanted collisions of the human operator with the manipulator and the link that is collided. The proposed approach could be applied to any industrial robot, where only the joint position signals are available. The designed NN is compared quantitatively and qualitatively with an NN, where both the intrinsic joint position and the torque sensors of the manipulator are used. The proposed method is evaluated experimentally with the KUKA LWR manipulator, which is considered as an example of the collaborative robots, using two of its joints in a planar horizontal motion. The results illustrate that the developed system is efficient and fast to detect the collisions and identify the collided link.

Keywords

Joints dynamicsRobot collision detectionCollided link identificationNeural networksIntrinsic sensors

Information

Type
Articles
Information
Robotica , Volume 38 , Special Issue 10: Human–Robot Interaction (HRI) , October 2020 , pp. 1737 - 1755
Copyright
Copyright © Cambridge University Press 2019

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Article purchase

Temporarily unavailable

References

Mohammed, A., Schmidt, B. and Wang, L., “Active collision avoidance for human—robot collaboration driven by vision sensors,” Int. J. Comput. Integr. Manuf. 30(9), 970–980 (2017).CrossRefGoogle Scholar
Flacco, F., Kroeger, T., De Luca, A. and Khatib, O., “A depth space approach for evaluating distance to objects with application to human-robot collision avoidance,” J. Intell. Rob. Syst. 80(Suppl. 1), S7–S22 (2015).CrossRefGoogle Scholar
Schiavi, R., Bicchi, A. and Flacco, F., “Integration of Active and Passive Compliance Control for Safe Human-robot Coexistence,” 2009 IEEE International Conference on Robotics and Automation, Kobe, Japan (2009) pp. 259–264.CrossRefGoogle Scholar
Lam, T. L., Yip, H.W., Qian, H. and Xu, Y., “Collision Avoidance of Industrial Robot Arms Using an Invisible Sensitive Skin,” 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, Algarve, Portugal (2012) pp. 4542–4543.Google Scholar
Balan, L. and Bone, G. M., “Real-time 3D Collision Avoidance Method for Safe Human and Robot Coexistence,” Proceedings of the 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems, Beijing (2006) pp. 276–282.CrossRefGoogle Scholar
Duguleana, M., Barbuceanu, F. G., Teirelbar, A. and Mogan, G., “Obstacle avoidance of redundant manipulators using neural networks based reinforcement learning,” Rob. Comput. Integr. Manuf. 28(2), 132–146 (2012).Google Scholar
Haddadin, S., Albu-Schäffer, A., De Luca, A. and Hirzinger, G., “Collision Detection and Reaction: A Contribution to Safe Physical Human-robot Interaction,” 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, Nice, France (2008) pp. 3356–3363.CrossRefGoogle Scholar
Cho, C., Kim, J., Lee, S. and Song, J., “Collision detection and reaction on 7 DOF service robot arm using residual observer,” J. Mech. Sci. Technol. 26(4), 1197–1203 (2012).CrossRefGoogle Scholar
Jung, B., Choi, H. R., Koo, J. C. and Moon, H., “Collision Detection Using Band Designed Disturbance Observer,” 8th IEEE International Conference on Automation Science and Engineering, Seoul, Korea (2012) pp. 1080–1085.Google Scholar
De Luca, A., Albu-Schäffer, A., Haddadin, S. and Hirzinger, G., “Collision detection and safe reaction with the DLR-III lightweight manipulator arm,” IEEE International Conference on Intelligent Robots and Systems, Beijing (2006) pp. 1623–1630.Google Scholar
Morinaga, S. and Kosuge, K., “Collision Detection System for Manipulator Based on Adaptive Impedance Control Law,” Proceedings of the 2003 IEEE International Conference on Robotics & Automation, Taipei, Taiwan (2003) pp. 1080–1085.Google Scholar
Lu, S., Chung, J. H. and Velinsky, S. A., “Human-robot Collision Detection and Identification Based onWrist and Base Force/Torque Sensors,” Proceedings of the 2005 IEEE International Conference on Robotics and Automation, Barcelona, Spain (2005) pp. 796–801.Google Scholar
Dimeas, F., Avenda, L. D., Nasiopoulou, E. and Aspragathos, N., “Robot Collision Detection based on Fuzzy Identification and Time Series Modelling,” Proceedings of the RAAD 2013, 22nd International Workshop on Robotics in Alpe-Adria-Danube Region, Slovenia (2013).Google Scholar
Dimeas, F., Avendano-Valencia, L. D. and Aspragathos, N., “Human—robot collision detection and identification based on fuzzy and time series modelling,” Robotica 33(9), 1886–1898 (2014).CrossRefGoogle Scholar
Iwata, H. and Sugano, S., “Human–robot-contact-state identification based on tactile recognition,” IEEE Trans. Ind. Electron. 52(6), 1468–1477 (2005).CrossRefGoogle Scholar
Sharkawy, A.-N. and Aspragathos, N., “Human-robot collision detection based on neural networks,” Int. J. Mech. Eng. Rob. Res. 7(2), 150–157 (2018).Google Scholar
Sharkawy, A.-N., Koustoumpardis, P. N. and Aspragathos, N., “Manipulator Collision Detection and Collided Link Identification Based on Neural Networks,” In: Advances in Service and Industrial Robotics. RAAD 2018, Mechanisms and Machine Science (Nikos, A., Panagiotis, K., and Vassilis, M., eds.) (Springer, Cham, 2018) pp. 3–12.Google Scholar
Murray, R. M., Li, Z. and Sastry, S. S., A Mathematical Introduction to Robotic Manipulation (CRC Press, Florida, USA, 1994).Google Scholar
Haykin, S., Neural Networks and Learning Machines, Third Edn. (Pearson, New Jersey, USA, 2009).Google Scholar
Nielsen, M. A., Neural Networks and Deep Learning (Determination Press, San Francisco, USA, 2015).Google Scholar
Smith, A. C. and Hashtrudi-Zaad, K., “Application of Neural Networks in Inverse Dynamics based Contact Force Estimation,” Proceedings of the 2005 IEEE Conference on Control Applications, Toronto, Ontario (2005) pp. 1021–1026.Google Scholar
Patiño, H. D., Carelli, R. and Kuchen, B. R., “Neural networks for advanced control of robot manipulators,” IEEE Trans. Neural Networks 13(2), 343–354 (2002).CrossRefGoogle Scholar
Goldberg, K. Y. and Pearlmutter, B. A., “Using a neural network to learn the dynamics of the CMU directdrive arm II,” In: NIPS*88 (Pittsburgh, Pennsylvania, 1988) pp. 356–363.Google Scholar
KUKA. FastResearchInterface 1.0, KUKA System Technology (KST), no. version 2. D-86165 (Augsburg, Germany, 2011).Google Scholar
Horváth, G., “Neural Networks in System Identification,” In: Neural Networks for Instrumentation, Measurement and Related Industrial Applications. Nato Science Series, III: Computer and Systems Sciences (Ablameyko, S., Goras, L., Gori, M. and Piuri, V., eds.) (IOS Press, Amsterdam, Netherlands, 2003) pp. 43–78.Google Scholar
Ferrari, S. and Stengel, R. F., “Smooth function approximation using neural networks,” IEEE Trans. Neural Networks 16(1), 24–38 (2005).Google Scholar
Hornik, K., Stinchcombe, M. and White, H., “Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks,” Neural Networks 3(5), 551–560 (1990).CrossRefGoogle Scholar
Du, K.-L. and Swamy, M. N. S., Neural Networks in a Softcomputing Framework (Springer, London, 2006).Google Scholar
Ren, X., Rad, A. B. and Lewis, F. L., “Neural Network-based Compensation Control of Robot Manipulators with Unknown Dynamics,” Proceedings of the 2007 American Control Conference, New York City, USA (2007) pp. 13–18.Google Scholar
He, W., David, A. O., Yin, Z. and Sun, C., “Neural network control of a robotic manipulator with input deadzone and output constraint,” IEEE Trans. Syst. Man, Cybern. Syst. 46(6), 759–770 (2016).CrossRefGoogle Scholar
Jiang, Y., Yang, C., Na, J., Li, G., Li, Y. and Zhong, J., “A brief review of neural networks based learning and control and their applications for robots,” Complexity 2017, 1895897 (2017).Google Scholar
Vemuri, A. T. and Polycarpou, M. M., “Neural-network-based robust fault diagnosis in robotic systems,” IEEE Trans. Neural Networks 8(6), 1410–1420 (1997).CrossRefGoogle Scholar
Du, K. and Swamy, M. N. S., Neural Networks and Statistical Learning (Springer-Verlag, London, 2014).CrossRefGoogle Scholar
Marquardt, D. W., “An algorithm for least-squares estimation of nonlinear parameters,” J. Soc. Ind. Appl. Math. 11(2), 431–441 (1963).CrossRefGoogle Scholar
Hagan, M. T. and Menhaj, M. B., “Training feedforward networks with the Marquardt algorithm,” IEEE Trans. Neural Networks 5(6), 2–6 (1994).CrossRefGoogle Scholar
Fumagalli, M., Gijsberts, A., Ivaldi, S., Jamone, L., Metta, G., Natale, L., Nori, F. and Sandini, G., “Learning to Exploit Proximal Force Sensing: A Comparison Approach,” In: From Motor Learning to Interaction Learning in Robots. (Sigaud, O. and Peters, J., eds.), vol. 264 (Springer, Berlin, Heidelberg, 2010) pp.149–167.CrossRefGoogle Scholar
Schmidhuber, J., “Deep learning in neural networks: An overview,” Neural Networks 61, 85–117 (2015).CrossRefGoogle Scholar
Chester, D. L., “Why two hidden layers are better than one,” International Joint Conference on Neural Networks, San Diego, USA, (1990) pp. 265–268.Google Scholar
Thomas, A. J., Walters, S. D., Petridis, M., Gheytassi, S. M. and Morgan, R. E., “Accelerated Optimal Topology Search for Two-Hidden-Layer Feedforward Neural Networks,” In: Engineering Applications of Neural Networks, EANN 2016. Communications in Computer and Information Science (Jayne, C. and Iliadis, L., eds.), vol. 629 (Springer, Cham, 2016) pp. 253–266.Google Scholar
“ISO/TS 15066, Robots and robotic devices – Collaborative robots,” First Edition: February 2016, CH-1214 Vernier, Geneva, Switzerland, www.iso.org.Google Scholar

Sharkawy et al. supplementary material

Sharkawy et al. supplementary material 1

Download Sharkawy et al. supplementary material(Video)
Video 38.7 MB