This paper presents a novel Continuously Variable Transmission (CVT) based on a Twisted String Actuator (TSA), capable of automatically adjusting its Transmission Ratio (TR) in response to external loads. Utilizing lightweight hyperelastic slender rods, the CVT achieves a simple, compact, and cost-effective design. By manipulating the distance between two twisted strings through rod deformation, the TR continuously adapts to varying load conditions. Mathematical models of the TSA-based CVT system are derived and experimentally validated, demonstrating a 2.1-fold TR variation from 0.1 kg to 1.5 kg loads. Application in an anthropomorphic robot finger showcases a 6.2-fold TR change between unloaded and loaded states. Our CVT offers unparalleled advantages in weight, cost, simplicity, compliance, and continuous TR adjustability, making it highly suitable for robotic systems.

In this paper, we present a Jacobian vector correction (JVC) method for calibrating tactile force in EIT-based tactile sensors. The JVC method addresses the non-uniform sensitivity distribution of EIT reconstruction by constructing a scaling vector for sensitivity correction based on the Jacobian vector. A thresholding segmentation strategy is employed to enhance the correction results within a region of interest (ROI). The proposed method achieves approximately constant sensitivity across all locations and eliminates the need for extensive data collection during force calibration. We provide a straightforward sensitivity analysis and visualizations to improve comprehension of EIT measurement properties and the calibration methodology. The effectiveness of the JVC method is evaluated through phantom experiments using various target objects with different conductivities or sizes, and on a non-array EIT-based tactile sensor composed of a porous elastic polymer and ionic liquid. The results demonstrate the ability of the JVC method to accurately capture strength information without being constrained by location dependency. Furthermore, the practicality of our proposed method is validated by integrating two calibrated flexible tactile sensors (each with a 100 cm2 area) into a robot arm platform.

In this paper, a large-area flexible tactile sensor for multi-touch and force detection based on EIT technology was developed. A novel design of a sensor material made of a porous elastic polymer and ionic liquid was proposed. The proposed conductive flexible materials combining elastic porous structures and conductive liquids provide continuous, linear changes in impedance with respect to touch forces. A deep learning scheme PSPNet based on MobileNet was adopted to postprocess the originally reconstructed images to improve the performance of tactile perception. By using this data-driven method, we can improve the spatial resolution of the tactile sensor to achieve a single-point position detection error of 7.5±4.5 mm without using internal electrodes.

In this paper, we presented a multi-frame constrained block sparse Bayesian learning (MFC-BSBL) reconstruction algorithm to tackle the challenge of poor-quality reconstruction images in electrical impedance tomography (EIT) for tactile sensing. The fundamental idea of MFC-BSBL is to explore the sparsity, intra-frame correlation, and inter-frame correlation of impedance distributions by extending the Bayesian inference framework. To verify the proposed algorithm, we conducted numerical simulations for different cases to identify one, multiple, round, and square targets. The simulation results demonstrated that this method can effectively detect the target positions and shapes by reducing artifacts and noise in the reconstructed images. To demonstrate the application of this approach to real EIT-based tactile sensing, we conducted real-contact detection experiments using the EIT tactile sensor system. Compared with traditional methods, the tactile sensor system using the MFC-BSBL algorithm can achieve accurate contact detection and significantly reduce artifacts and noise.

A novel two-electrode, frequency-scan electrical impedance tomography (EIT) system for gesture recognition not only reduces the measurement complexity and the number of electrodes, but also achieves a high accuracy in recognizing common gestures and pinch gestures. A bespoke circuit with two medical electrodes was developed to collect data from the back of the hand and presented a frequency-scan method to increase the diversity of impedance data. The data were processed using data cleaning and feature extraction methods. The processed data were then sent to machine learning classification models for training and realizing accurate gesture recognition. To verify the effectiveness of this system, we designed two groups of nine gestures in a hand-gesture recognition experiment. The results showed that the system can achieve a recognition accuracy of 98.3% with a group of four common gestures and an accuracy of 97.4% with a group of five pinch gestures. Additionally, two proof-of-concept interactive scenarios were implemented to demonstrate the general purpose of this system.