Non-linear Hysteresis Compensation of a Tendon-sheath-driven Robotic Manipulator using Motor Current

Tendon-sheath-driven manipulators (TSM) are widely used in minimally invasive surgical systems due to their long, thin shape, flexibility, and compliance making them easily steerable in narrow or tortuous environments. Many commercial TSM-based medical devices have non-linear phenomena resulting from their composition such as backlash and dead zone hysteresis, which lead to a considerable challenge for achieving precise control of the end effector pose. However, many recent works in the literature do not consider the combined effects and compensation of these phenomena, and less focus on practical ways to identify model parameters in real field. In this paper, we propose a simplified piece-wise linear model to compensate both backlash and dead zone hysteresis together. Further, we introduce a practical method to identify model parameters using motor current from a robotic controller for the TSM. We analyze our proposed methods with multiple Intra-cardiac Echocardiography catheters, which are typical commercial example of TSM. Our results show that the errors from backlash and dead zone hysteresis are considerably reduced and therefore the accuracy of robotic control is improved when applying the presented methods.

Baseline CNN structure analysis for facial expression recognition

We present a baseline convolutional neural network (CNN) structure and image preprocessing methodology to improve facial expression recognition algorithm using CNN. To analyze the most efficient network structure, we investigated four network structures that are known to show good performance in facial expression recognition. Moreover, we also investigated the effect of input image preprocessing methods. Five types of data input (raw, histogram equalization, isotropic smoothing, diffusion-based normalization, difference of Gaussian) were tested, and the accuracy was compared. We trained 20 different CNN models (4 networks x 5 data input types) and verified the performance of each network with test images from five different databases. The experiment result showed that a three-layer structure consisting of a simple convolutional and a max pooling layer with histogram equalization image input was the most efficient. We describe the detailed training procedure and analyze the result of the test accuracy based on considerable observation.