Decoupling Research of a Novel Three-Dimensional Force Flexible Tactile Sensor Based on an Improved BP Algorithm

Abstract

Decoupling research on flexible tactile sensors play a very important role in the intelligent robot skin and tactile-sensing fields. In this paper, an efficient machine learning method based on the improved back-propagation (BP) algorithm is proposed to decouple the mapping relationship between the resistances of force-sensitive conductive pillars and three-dimensional forces for the 6 × 6 novel flexible tactile sensor array. Tactile-sensing principles and numerical experiments are analyzed. The tactile sensor array model accomplishes the decomposition of the force components by its delicate structure, and avoids direct interference among the electrodes of the sensor array. The force components loaded on the tactile sensor are decoupled with a very high precision from the resistance signal by the improved BP algorithm. The decoupling results show that the k-cross validation (k-CV) algorithm is a highly effective method to improve the decoupling precision of force components for the novel tactile sensor. The large dataset with the k-CV method obtains a better decoupling accuracy of the force components than the small dataset. All of the decoupling results are fairly good, and they indicate that the improved BP model with a strong non-linear approaching ability has an efficient and valid performance in decoupling force components for the tactile sensor.

Flexible resistive tactile pressure sensors

“…For instance, Song et al employed a backpropagation (BP) neural network to successfully decouple three-dimensional forces on a 6 × 6 flexible array touch sensor. 168 The sensor consists of numerous sensitive units, each with two upper tactile sensing electrodes at its top. When force components along the X and Z directions are applied to the sensor, the tactile sensor array undergoes deformation.…”

Flexible microstructured pressure sensors: design, fabrication and applications

“…Additionally, Additionally, Wang et al [218] decoupled three-dimensional forces by radial basis machinelearning algorithm in ideal conditions. Moreover, Song and co-authors [219] demonstrated an efficient machine learning method based on back-propagation (BP) algorithm for flexible pressure sensor arrays. The BP algorithm mainly consists of two parts: information forward-propagation and error backward-propagation [220].…”

“…All of the connecting weights are continuously adjusting during the convergence process until the mean square error is less than the target value. In the work of Song's group [219], the k-cross validated BP models with different hidden nodes is used to calculate the force components for the tactile sensor. The n-dimensional vector including the resistances of the devices is regarded as the input for the BP model, and the m-dimensional vector consisting of force components was reckoned for the output.…”

Editorial for the Special Issue on Tactile Sensing for Soft Robotics and Wearables

“…One review [1] and four research articles [2,3,4,5] have been published in this Special Issue. These cover several topics in the field, spanning the recent technological advancements and the analysis of novel devices to the development of sensor network systems and improved algorithms as well as their clinical application on blind patients.…”

“…Machine learning is becoming a useful and powerful tool for tactile sensing in soft systems. Song et al [4] faced the challenge of decoupling single components of three-axial force sensors by means of a machine learning method based on the improved back-propagation (BP) algorithm. This was applied in a 6 x 6 tactile sensor array to obtain the three-dimensional forces from the resistances of force-sensitive conductive pillars.…”