Texture Recognition by Tactile Sensing
نویسندگان
چکیده
Tactile sensing is essential for effective manipulation. A detailed understanding of the surface texture can also be used for industrial tasks such as quality assurance. This paper describes an application of machine learning in tactile sensing. A naive Bayes classifier is used to distinguish textures sensed by bio-inspired artificial finger. The finger has randomly distributed strain gauges and Polyvinylidene Fluoride (PVDF) films embedded in silicone. The data from the finger are preprocessed and the Fourier coefficients of the sensor outputs are used to learn a classifier for different textures. The finger is capable of distinguishing natural textures but in this paper we describe experiments on artificial textures, which we use to calibrate the learner.
منابع مشابه
ViTac: Feature Sharing between Vision and Tactile Sensing for Cloth Texture Recognition
Vision and touch are two of the important sensing modalities for humans and they offer complementary information for sensing the environment. Robots could also benefit from such multi-modal sensing ability. In this paper, addressing for the first time (to the best of our knowledge) texture recognition from tactile images and vision, we propose a new fusion method named Deep Maximum Covariance A...
متن کاملAutonomous tactile perception: A combined improved sensing and Bayesian nonparametric approach
In recent years, autonomous robots have increasingly been deployed in unknown environments and required to manipulate or categorize unknown objects. In order to cope with these unfamiliar situations, improvements must be made both in sensing technologies and in the capability to autonomously train perception models. In this paper, we explore this problem in the context of tactile surface identi...
متن کاملDesign, Modeling, and Construction of a New Tactile Sensor for Measuring Contact-Force
This paper presents the design, modeling, and testing of a flexible tactile sensor and its applications. This sensor is made of polymer materials and can detect the 2D surface texture image and contact-force estimation. The sensing mechanism is based on the novel contact deflection effect of a membrane. We measure the deflection of the membrane with measuring the strain in the membrane with emb...
متن کاملPassive sensing and active sensing of a biomimetic whisker
Rodents demonstrate an outstanding capability of texture discrimination and shape recognition with their whiskers (vibrissae). Many neurophysiological and behavioural studies reported that active whisking plays a critical role on tactile perception. However, the role and limitation of passive sensing has not been studied in detail. In this paper, we compare passive sensing and active sensing fo...
متن کاملDesign and Modeling of a New Type of Tactile Sensor Based on the Deformation of an Elastic Membrane
This paper presents the design and modeling of a flexible tactile sensor, capable of detecting the 2D surface texture image, contact-force estimation and stiffness of the sensed object. The sensor is made of polymer materials. It consists of a cylindrical chamber for pneumatic actuation and a membrane with a mesa structure. The inner radius of the cylindrical chamber is 2cm and its outer radius...
متن کامل