Nonlinear Tactile Estimation Model Based on Perceptibility of Mechanoreceptors Improves Quantitative Tactile Sensing

Abstract

Tactile sensing has attracted significant attention as a tactile quantitative evaluation method because the tactile sensation is an important factor while evaluating consumer products. Although the human tactile perception mechanism has nonlinearity, previous studies have often developed linear regression models. In contrast, this study proposes a nonlinear tactile estimation model that can estimate sensory evaluation scores from physical measurements. We extracted features from the vibration data obtained by a tactile sensor based on the perceptibility of mechanoreceptors. In parallel, a sensory evaluation test was conducted using 10 evaluation words. Then, the relationship between the extracted features and the tactile evaluation results was modeled using linear/nonlinear regressions. The best model was concluded by comparing the mean squared error between the model predictions and the actual values. The results imply that there are multiple evaluation words suitable for adopting nonlinear regression models, and the average error was 43.8% smaller than that of building only linear regression models.

Conditional Generative Adversarial Network-Based Tactile Stimulus Generation for Ultrasonic Tactile Display

“…To reproduce tactile sensations, technologies to quantify the tactile sensation of an object and to display tactile sensations using a tactile display are necessary. To quantify tactile sensation, it has been suggested that focusing on vibration information at the time of object touch is an effective approach given the human tactile perception mechanism [8], [9], [10], [11]. Tactile displays…”

“…Therefore, haptic rendering via tactile sensation, that is, the conversion from sensed vibration to tactile sensation and from tactile sensation to input to an ultrasonic tactile display, is needed. For this tactile rendering, previous studies have addressed the conversion from sensed vibration to tactile sensation [8], [9], [10], [11]. This study considers the conversion from tactile sensation to display input, and focuses on conditional generative adversarial networks (CGANs) [16], [17], which are a type of generative adversarial network (GAN) [18], [19], as the conversion method.…”

Neural-Network-Based Tactile Perception System Using Ultrahigh-Resolution Tactile Sensor

“…Various research results have been reported towards the development of a regression system for tactile perception. The information to use for regression can be broadly classified into the following two approaches: a model that uses information that can be measured with existing equipment, such as material constants [1] and surface shape [2], [3], and systems that use vibrations obtained from sliding on the target surface using tactile sensors [4], [5], [6], [7]. Regression methods can be broadly classified into those using linear regression [1], [2], [3], [4], [5], [8] or This work was carried out with funding support from the JST-CREST research funding program [grant numbers JPMJCR1531 and JPMJCR20C2] Y. Maeda is with Kagawa University and the National Institute of Technology (KOSEN), Kagawa College, Japan (e-mail: maeda-y@t.kagawanct-ac.jp).…”

“…nonlinear regression such as machine learning [6], [7]. The latest research showed that a tactile perception system combining tactile sensors and a fully connected neural network can predict 68.2% of sensory evaluation scores caused by shape differences in a uniform material, even for unknown samples [7].…”