Gaussian Process Regression for a Biomimetic Tactile Sensor

详细信息    查看全文

• 关键词：Tactile sensors ; Gaussian process regression ; Bayesian perception
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9793
• 期：1
• 页码：393-399
• 全文大小：889 KB
• 参考文献：1.Johansson, R.S., Flanagan, J.R.: Coding and use of tactile signals from the fingertips in object manipulation tasks. Nat. Rev. Neurosci. 10(5), 345–359 (2009)CrossRef
  2.Lepora, N.F., Ward-Cherrier, B.: Superresolution with an optical tactile sensor. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 2686–2691, September 2015
  3.Lepora, N.F.: Biomimetic active touch with fingertips and whiskers. IEEE Trans. Haptics 9(2), 170–183 (2016)CrossRef
  4.Rasmussen, C., Williams, C.: Gaussian Processes for Machine Learning. Adaptative Computation and Machine Learning Series. University Press Group Limited, New Era Estate (2006)MATH
  5.Chorley, C., Melhuish, C., Pipe, T., Rossiter, J.: Development of a tactile sensor based on biologically inspired edge encoding. In: International Conference on Advanced Robotics, ICAR 2009, pp. 1–6, June 2009
  6.Gegenfurtner, K.R., Kiper, D.C.: Color vision. Annu. Rev. Neurosci. 26(1), 181–206 (2003)CrossRef
  7.Baddeley, R.J., Hancock, P.J.B.: A statistical analysis of natural images matches psychophysically derived orientation tuning curves. Proc. R. Soc. Lond. B: Biol. Sci. 246(1317), 219–223 (1991)CrossRef
  8.Koh, K., Meyer, D.E.: Function learning: induction of continuous stimulus-response relations. J. Exp. Psychol. Learn. Mem. Cogn. 17(5), 811 (1991)CrossRef
  9.Griffiths, T.L., Lucas, C., Williams, J., Kalish, M.L.: Modeling human function learning with gaussian processes. In: Koller, D., Schuurmans, D., Bengio, Y., Bottou, L. (eds.) Advances in Neural Information Processing Systems 21, pp. 553–560. Curran Associates Inc. (2009)
  10.Ward-Cherrier, B., Cramphorn, L., Lepora, N.F.: Exploiting sensor symmetry to generalize biomimetic touch. In: Ohwada, H., Yoshida, K. (eds.) Living Machines 2016. LNCS, vol. 9793, pp. 540–544. Springer, Switzerland (2016)
  11.Nguyen-Tuong, D., Peters, J.: Local gaussian process regression for real-time model-based robot control. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2008, pp. 380–385, September 2008
  
• 作者单位：Kirsty Aquilina (19) (20)
  David A. W. Barton (19) (20)
  Nathan F. Lepora (19) (20)
  
  19. Department of Engineering Mathematics, University of Bristol, Bristol, UK
  20. Bristol Robotics Laboratory, University of Bristol, Bristol, UK
  
• 丛书名：Biomimetic and Biohybrid Systems
• ISBN：978-3-319-42417-0
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9793

文摘

The aim of this paper is to investigate a new approach to decode sensor information into spatial information. The tactile fingertip (TacTip) considered in this work is inspired from the operation of dermal papillae in the human fingertip. We propose an approach for interpreting tactile data consisting of a preprocessing dimensionality reduction step using principal component analysis and subsequently a regression model using a Gaussian process. Our results are compared with a classification method based on a biomimetic approach for Bayesian perception. The proposed method obtains comparable performance with the classification method whilst providing a framework that facilitates integration with control strategies, for example to perform controlled manipulation.