Jakub Tomczyński

Hand gesture-based interface with multichannel sEMG band enabling unknown gesture discrimination

A forearm band consisting of 7 EMG sensors was developed. The band is dedicated to serve as a human-machine interface and its applicability as a gesture-based interface was presented. The gesture recognition was performed by ANN with softmax output function. The classifier uses output entropy function to discriminate between known command gestures and unknown gestures. 15 features of low computational complexity were selected. The preliminary test was performed for 4 healthy volunteers. Continuous time series were used, including unknown gestures and transitions. Special attention was paid to analyze system properties of detecting and rejecting unknown gestures (not commands movements), even if they were not included in training set. Obtained preliminary results show the sensitivity for command gestures (including transition phases) of 97% and fall out of 1.9%. In case of the system trained to reject unknown gestures the sensitivity and fall out were 82% and 9%, respectively. The calculated unknown gestures rejection rate was at 96%. It was shown that in most cases the interface is robust to false positive detection of command gestures while performing other gestures, even if the same muscles groups were recruited for movement.

EKF-based method for kinematic configuration estimation of finger-like structure using low grade multi-IMU system

In this article, a method for kinematic configuration estimation of a structure similar to a human finger, is presented. The method is based on the EKF and a model reflecting kinematic constraints of a finger-like structure (2-DOF metacarpophalangeal joint, and one 1-DOF proximal interphalangeal rotational joint), using 3 low cost IMUs. During tests, the IMUs were attached to a 3D-printed setup equipped with encoders. The setup was fixed to the flange of a UR3 robotic arm. System accuracy and robustness was tested during various kinds of movement, including fast and slow movements in all joints (maximum angular rate of 550 deg/s), and simultaneous base rotation (up to 170 deg/s) and linear acceleration (up to 0.25 g). The obtained RMSE of estimated joint angle was 3.5 deg for all joints and all types of performed movements. In case of joint rotations around an axis parallel to gravity vector, RMSE of 4 deg was achieved.

Surface Electromyography Amplifier with High Environmental Interference Resistance

In this paper design of a miniature, low cost surface electromyography amplifier is proposed. Presented device can be considered to be resistant to common environmental interferences. Proposed design consists of main amplifier board and second board containing DRL circuit and reference voltage source. Major disturbance is provided by mains (50/60 Hz) - most emphasized interference in this paper. Design includes appropriate set of filtration circuits. Moreover comparison with four commercial and hobbyist devices is provided.

Influence of sEMG electrode matrix configuration on hand gesture recognition performance

This paper presents a study of a human-machine interface in the form of three parallel electromyographic bands placed around the users forearm, with the influence of sEMG electrode layout on gesture recognition performance as the primary focus. Tested electrode configurations included setups ranging from 4 to 24 electrodes, with varying placement on the subjects forearm, using both monopolar and bipolar measurement methods. An artificial neural network with softmax output layer was used as the gesture classifier. The test data included three participants performing nine gestures in various sequences, over the course of two days. The work focuses on minimisation of the setup size and complexity, while simultaneously preserving best possible gesture classification performance. The most reliable results were achieved using 24-electrode configuration (F1 = 0.96), however, comparable efficacy was obtained using less complex designs: two-band bipolar (F1 = 0.95) and single-band chained differential (F1 = 0.94). Moreover, it has been observed that for classification of a smaller command set (5 gestures), satisfactory results can be obtained using a simple 4-electrode setup (F1 = 0.94).

Localisation method for sEMG electrode array, towards hand gesture recognition HMI development

This paper presents a method for radial shift estimation of an electrode array located around the forearm. The algorithm is aimed at band-shaped EMG human-machine interfaces recognising hand gestures. Proposed algorithm relies on the approximation of muscle activity in several regions arranged radially around users forearm. The intensity is represented as a polygon on a polar plane. To estimate current electrode band orientation, the user is asked to perform a certain gesture. Recorded activity is then rotated to minimise area discrepancy in each region between current occurrence and a stored pattern calculated at a known orientation. Nine gestures were considered during the preliminary assessment phase, three gestures (fist, flexion, and extension) with most promising results were chosen for further evaluation. Selected gestures were used for cross-validation performed among three subjects using both subject-specific and averaged models. Best results were achieved with extension, giving 13.1° mean orientation estimation error and standard deviation of 9.0°.

CIE-DataGlove, A Multi-IMU System for Hand Posture Tracking

In this paper, a fully functional dataglove device, called CIE-DataGlove, is presented. CIE-DataGlove is a glove-like apparatus intended for human hand posture capture. The essential design requirement was not to hinder hand movement and object manipulation, and not to introduce additional mechanical resistance to the fingers. The system is based on 12 9-DOF inertial measurement units placed on phalanges and metacarpus. The article describes mechanical, hardware, and software implementations used in the development of CIE-DataGlove. Throughput performance of communication interface is studied in the context of interface response time.

Cross-Sensor Calibration Procedure for Magnetometer and Inertial Units

Due to inertial and magnetic sensors imperfections, pre-processing is crucial in obtaining reliable orientation estimates. An easy to implement method of sensor calibration is presented, requiring little to none additional equipment. The method does not need a reference sensor and relies on world magnetic and gravity vectors constant relationship. In addition to standard individual calibration, a cross-sensor reference frame alignment is performed. Comparison with a high-grade MARG unit is also provided. Magnetic inclination stability, inertial and magnetic vector magnitude, and angular error are evaluated.

CIE-Hand towards Prosthetic Limb

In this paper design of a compliant anthropomorphic five-finger gripper is presented. The device is intended to be used as a basis for a hand prosthesis development. Influence of the gripper underactuation on grasping capabilities was evaluated. In a series of tests, forces exerted on a manipulated objects were measured. It has been proven, that the gripper compliance significantly reduces forces required to perform secure grasps. Software synergies which are leading to dimensionality reduction of the input vector are presented. Their use allows to control an execution of basic grasp types using only two-dimensional control space.