Distributive tactile sensing using fibre Bragg grating sensors

Abstract

Two distributive tactile sensing systems are presented, based on fibre Bragg grating sensors. The first is a onedimensional metal strip with an array of 4 sensors, which is capable of detecting the magnitude and position of a contacting load. This system is compared experimentally with a similar system using resistive strain gauges. The second is a two-dimensional steel plate with 9 sensors which is able to distinguish the position and shape of a contacting load. This system is compared with a similar system using 16 infrared displacement sensors. Each system uses neural networks to process the sensor data to give information concerning the type of contact.

An approach to improve the spatial resolution of a force mapping sensing system

“…The overall sensor performance can also be characterized by the average magnitude of the error vector x x 0 ∥ ∥ − in equation (5), calculated for the 30 test configurations of table 1. The resulting average errors were 0.10 kgf and 0.06 kgf for the ridge regression and LASSO, respectively.…”

“…The proposed strategy differs from the one used by Heo et al [3] as it uses a smaller number of transducers than the number of sensed regions. When compared to the methodology introduced by Cowie [5], the method proposed in this paper has the advantage of enabling the sensing of multiple simultaneous forces which were not considered in the calibration (as in the training stage of a neural network), although presenting a limited resolution with respect to the number of regions into which the plate was split.…”

“…One potential limitation of such construction models occurs when the sensed area needs to be enlarged, causing the number of transducers to be proportionately incremented while keeping the same spatial resolution. Attempting to overcome this drawback, other authors have proposed a system using FBG sensors properly affixed to a metal plate [5], where the detection of the position of a load on the sensed plate was performed using artificial neural networks. The problem of dealing with loads of different magnitudes or with a set of more than two loads simultaneously positioned on this sensed plate remained unsolved.…”

Quantifying sway through surface deflection patterns: A novel approach using distributive tactile sensing

“…Much research has focused on the implementation of a neural network for DTS applictions [12,18,19]. In these studies, the sensor elements were strain gauges distributed and embedded along a cantilever.…”

Enhancing thickness determination of nanoscale dielectric films in phase diffraction-based optical characterization systems with radial basis function neural networks

“…The neural network approaches in the photonics area have received a lot of interest in the last decade by eliminating the need for human intervention, increasing accuracy, and speeding up the process. It has a wide range of application areas in the open literature, including optical distance measurement [27], defect detection [28], event identification [29], strain sensing [30][31][32], acoustic sensing [33,34], temperature sensing [35], optical fiber bending measurement [36], optical communication networks [37][38][39], optical reflectivity measurements [40,41], tactile sensing [42], leakage detection [43] etc. They have also been used in the thickness characterization of dielectric films due to their importance in fiber optic sensor technologies [44,45].…”