Structuring of tactile sensory information for category formation in robotics palpation
- PDF / 3,019,535 Bytes
- 17 Pages / 595.276 x 790.866 pts Page_size
- 46 Downloads / 154 Views
Structuring of tactile sensory information for category formation in robotics palpation Luca Scimeca1
· Perla Maiolino1 · Ed Bray1 · Fumiya Iida1
Received: 3 April 2019 / Accepted: 9 July 2020 © The Author(s) 2020
Abstract This paper proposes a framework to investigate the influence of physical interactions to sensory information, during robotic palpation. We embed a capacitive tactile sensor on a robotic arm to probe a soft phantom and detect and classify hard inclusions within it. A combination of PCA and K-Means clustering is used to: first, reduce the dimensionality of the spatiotemporal data obtained through the probing of each area in the phantom; second categorize the re-encoded data into a given number of categories. Results show that appropriate probing interactions can be useful in compensating for the quality of the data, or lack thereof. Finally, we test the proposed framework on a palpation scenario where a Support Vector Machine classifier is trained to discriminate amongst different types of hard inclusions. We show the proposed framework is capable of predicting the best-performing motion strategy, as well as the relative classification performance of the SVM classifier, solely based on unsupervised cluster analysis methods. Keywords Robotic palpation · Tactile sensing · Physical sensing · Sensory–motor coordination
1 Introduction In the last decades, substantial efforts have been made in enhancing the sensing capabilities of robots by providing them with a sense of touch (Dahiya et al. 2010; Drimus et al. 2014). Haptic sensing differs from other modalities, such as vision, in virtue of its tight coupling with, and need of, physical interactions. Haptic sensing requires direct physical contacts with sensing targets, inducing spatio-temporal force patterns on the contact surface, which may or may not be the consequence of motor behaviors of the robots. FurtherThis work was funded by the UK Agriculture and Horticulture Development Board and by The United Kingdom Engineering and Physical Sciences Research Council (EPSRC) MOTION Grant [EP/N03211X/2]. Electronic supplementary material The online version of this article (https://doi.org/10.1007/s10514-020-09931-y) contains supplementary material, which is available to authorized users.
B
Luca Scimeca [email protected] Perla Maiolino [email protected]
1
Bioinspired Robotic Lab, Engineering Department, University of Cambridge, Cambridge, UK
more, force patterns are significantly related to the shape and mechanical properties of sensing surfaces (e.g. stiffness) and the target objects (Scimeca et al. 2018; Iida and Nurzaman 2016). In medical palpation diagnosis, for example, given the nature of soft tissues in the human body, haptic perception plays a fundamental role (Puangmali et al. 2008). Here, practitioners necessitate the use of different palpation strategies according to the task, whether this is an organ to examine, finding cancerous inclusions or investigating their characteristics. In this context, contacts and physical interactions are the ba
Data Loading...
