Structuring of tactile sensory information for category formation in robotics palpation

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.

Deep Movement Primitives: toward Breast Cancer Examination Robot

“…Breast palpation movements is hard to program and is needed for ARBP (Scimeca et al 2020;Herzig et al 2018). Our proposed method can address the existing challenges in motion planning for Breast Palpation, such as (1) variations across different palpation executions; (2) variability across different palpation paths; (3) relation between the visual information and demonstrated trajectories.…”

“…Therefore, our survey shows autonomous robotic BP (ARBP) is of great interest to both clinicians and patients (Houghton et al 2021) ARBP reduces the burden on the general healthcare system for clinical BP, improves the accessibility of the ser-vice and precision of early breast cancer detection. Although there are many studies for robotic tissue palpation for tumour detection (Scimeca et al 2020;Herzig et al 2018;Kobayashi et al 2009;Nichols and Okamura 2015;Keshavarz and Mojra 2015), most of them focus on tissue stiffness classification and developing a suitable robot finger/hand for palpation. Hence, the problem of efficient path/motion planning for autonomous robotic palpation remains vastly unexplored.…”

Online Morphological Adaptation for Tactile Sensing Augmentation

“…The Silhouette is a measure which considers the trade-off between the intra-cluster distance of sensor values for objects belonging to the same class, and the nearest-cluster distance between clusters of objects belonging to different classes. This measure has previously been successfully used for the analysis of tactile information in discrimination tasks (Scimeca et al, 2020a). The silhouette score s(i) for cluster i can be computed as:…”

Action Augmentation of Tactile Perception for Soft-Body Palpation

“…In the past, there have been notable attempts to better understand palpation by using robotics technologies. [10][11][12][13] One of the pioneering works in this area, the WAPRO-4 system, is capable of performing simple breast palpation to identify relatively large inclusions. 14 The use of probes with variable mechanical impedance has been found to improve lumps and tumor detection, 15 and the importance of sensory-motor coordination has also been shown across a number of medical applications.…”