Simple Synthetic Memories of Robotic Touch
Pages 3 - 15
Abstract
It has been previously demonstrated in robots that the mimicking of functional characteristics of biologic memory can be beneficial for providing accurate learning and recognition in circumstances of social human-robot-interaction. The effective encoding of social and physical salient features has been demonstrated through the use of Bayesian Latent Variable Models as abstractions of memories (Simple Synthetic Memories). In this work, we explore the capabilities of formation and recall of tactile memories associated to the encoding of geometric and spatial qualities. Compression and pattern separation are evaluated against the use of raw data in a nearest neighbour regression model, obtaining a substantial improvement in accuracy for prediction of geometric properties of the stimulus. Additionally, pattern completion is assessed with the generation of ‘imagined touch’ streams of data showing similarities to real world tactile observations. The use of this model for tactile memories offers the potential for robustly perform sensorimotor tasks in which the sense of touch is involved.
References
[1]
Aquilina, K., Barton, D.A., Lepora, N.F.: Principal components of touch. In: Proceedings - IEEE International Conference on Robotics and Automation, pp. 4071–4078. Institute of Electrical and Electronics Engineers Inc., September 2018.
[2]
Boorman LW, Damianou AC, Martinez-Hernandez U, and Prescott TJ Wilson SP, Verschure PFMJ, Mura A, and Prescott TJ Extending a hippocampal model for navigation around a maze generated from real-world data Biomimetic and Biohybrid Systems 2015 Cham Springer 441-452
[3]
Chorley, C., Melhuish, C., Pipe, T., Rossiter, J.: Development of a tactile sensor based on biologically inspired edge encoding. In: 2009 International Conference on Advanced Robotics, ICAR 2009 (2009)
[4]
Damianou A, Ek CH, Boorman L, Lawrence ND, and Prescott TJ Wilson SP, Verschure PFMJ, Mura A, and Prescott TJ A top-down approach for a synthetic autobiographical memory system Biomimetic and Biohybrid Systems 2015 Cham Springer 280-292
[5]
Evans MH, Fox CW, and Prescott TJ Duff A, Lepora NF, Mura A, Prescott TJ, and Verschure PFMJ Machines learning - towards a new synthetic autobiographical memory Biomimetic and Biohybrid Systems 2014 Cham Springer 84-96
[6]
GPy: GPy: A Gaussian process framework in PyThon (2014). http://github.com/SheffieldML/GPy
[7]
Lawrence N Probabilistic non-linear principal component analysis with gaussian process latent variable models J. Mach. Learn. Res. 2005 6 1783-1816
[8]
Lawrence, N.D.: Gaussian process latent variable models for visualisation of high dimensional data. In: Advances in Neural Information Processing Systems (2004)
[9]
Lepora NF, Aquilina K, and Cramphorn L Exploratory tactile servoing with active touch IEEE Robot. Autom. Lett. 2017 2 2 1156-1163
[10]
Mann, H.B., Whitney, D.R.: On a test of whether one of two random variables is stochastically larger than the other. Ann. Math. Stat. 18(1), 50–60 (1947). http://www.jstor.org/stable/2236101
[11]
Martinez-Hernandez, U., Damianou, A., Camilleri, D., Boorman, L.W., Lawrence, N., Prescott, T.J.: An integrated probabilistic framework for robot perception, learning and memory. In: 2016 IEEE International Conference on Robotics and Biomimetics, ROBIO 2016, pp. 1796–1801 (2016).
[12]
Prescott TJ, Camilleri D, Martinez-Hernandez U, Damianou A, and Lawrence ND Memory and mental time travel in humans and social robots Philos. Trans. Roy. Soc. B Biol. Sci. 2019 374 1771 20180025
[13]
Sakata, H., Shibutani, H., Kawano, K.: Neural correlates of space perception in the parietal association cortex of the monkey. In: Brain and Behaviour, Pergamon, pp. 291–298, January 1981.
[14]
Salazar PJ and Prescott TJ Cañamero L, Gaussier P, Wilson M, Boucenna S, and Cuperlier N Deep Gaussian processes for angle and position discrimination in active touch sensing From Animals to Animats 16 2022 Cham Springer 41-51
[15]
Salazar PJ and Prescott TJ Pacheco-Gutierrez S, Cryer A, Caliskanelli I, Tugal H, and Skilton R Tactile and proprioceptive online learning in robotic contour following Towards Autonomous Robotic Systems 2022 Cham Springer 166-178
[16]
Stone, E.A., Lepora, N.F., Barton, D.A.: Learning to live life on the edge: online learning for data-efficient tactile contour following. In: IEEE International Conference on Intelligent Robots and Systems, pp. 9854–9860. Institute of Electrical and Electronics Engineers Inc., September 2020. arXiv:1909.05808
[17]
Tanaka, D., Matsubara, T., Ichien, K., Sugimoto, K.: Object manifold learning with action features for active tactile object recognition. In: IEEE International Conference on Intelligent Robots and Systems, pp. 608–614. IEEE, September 2014.
[18]
Titsias MK and Lawrence ND Bayesian Gaussian process latent variable model J. Mach. Learn. Res. 2010 9 844-851 JMLR Workshop and Conference Proceedings
Index Terms
- Simple Synthetic Memories of Robotic Touch
Index terms have been assigned to the content through auto-classification.
Recommendations
Communication Cues in a Human-Robot Touch Interaction
HAI '16: Proceedings of the Fourth International Conference on Human Agent InteractionHaptic interaction is a key capability for social robots that closely interact with people in daily environments. Such human communication cues as gaze behaviors make haptic interaction look natural. Since the purpose of this study is to increase human-...
Observing Robot Touch in Context: How Does Touch and Attitude Affect Perceptions of a Robot's Social Qualities?
HRI '18: Proceedings of the 2018 ACM/IEEE International Conference on Human-Robot InteractionThe complex role of touch is an increasingly appreciated horizon for HRI research. The explicit and implicit registers of touch, both human-to-robot and robot-to-human, have opened up pressing questions in design and HRI ethics about embodiment, ...
To touch or not to touch?: comparing 2D touch and 3D mid-air interaction on stereoscopic tabletop surfaces
SUI '13: Proceedings of the 1st symposium on Spatial user interactionRecent developments in touch and display technologies have laid the groundwork to combine touch-sensitive display systems with stereoscopic three-dimensional (3D) display. Although this combination provides a compelling user experience, interaction with ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Jul 2023
476 pages
ISBN:978-3-031-38856-9
DOI:10.1007/978-3-031-38857-6
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 01 August 2023
Author Tags
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 16 Dec 2024