Wearable devices are gaining recognition for their use as a biosensor platform. Electrical impedance tomography (EIT) is one of the sensing techniques that utilizes wearable sensors as its primary data acquisition system. It measures the impedance or resistance at the peripheral (skin) level and calculates the conductivity distribution throughout the body. Even though the technology has existed for several decades, modern-day EIT devices are still costly and bulky. The paper proposes a novel low-cost kirigami-based wearable device that has soft PEDOT: PSS electrodes for sensing skin impedances. Simulation results show that the proposed kirigami structure for the bracelet has a large deformation during actuation while experiencing relatively lower stress. The paper also presents a comparative study on a few machine learning algorithms to classify hand gestures, based on the measured skin impedance. The best classification accuracy (91.49%) was observed from the quadratic support vector machine (SVM) algorithm with 48 principal components.

This paper is an extension of our previous work about a modular anthropomorphic robotic hand with soft enhancements focusing on simultaneous pinch grasp and suction-based object manipulations. The base structure is a tendon-driven robotic hand comprising five fingers and a palm. Each finger consists of two rigid links covered with soft enhancements. The soft enhancements are like the skin and tissues of the robotic hand. The tip of the finger is equipped with a suction module which can be actuated by regulating negative pressure to the soft layers. While our previous work dealt with the rationale behind and the structure of the modular design with kinematic analysis, this paper focuses on analyzing two specific capabilities of the gripper—pinch grasp and suction modality. Experiments validate that the proposed gripper together with the soft enhancement layers is capable of performing delicate single finger suction-based manipulation tasks and two-finger pinch grasp tasks.

<span>In our daily life, we, human beings use our hands in various ways for most of our day-to-day activities. Tracking the position, orientation and articulation of human hands has a variety of applications including gesture recognition, robotics, medicine and health care, design and manufacturing, art and entertainment across multiple domains. However, it is an equally complex and challenging task due to several factors like higher dimensional data from hand motion, higher speed of operation, self-occlusion, etc. This paper puts forth a novel method for tracking the finger tips of human hand using two distinct sensors and combining their data by sensor fusion technique.</span>