In this article, the design of a five-fingered anthropomorphic gripper is presented specifically designed for the manipulation of elastic objects. The manipulator features a hybrid design, being equipped with three fully actuated fingers for precise manipulation, and two underactuated, tendon-driven digits for secure power grasping. For ease of reproducibility, the design uses as many off-the-shelf and 3D-printed components as possible. The on-board controller circuit and firmware are also presented. The design includes resistive position and angle sensors in each joint, resulting in full joint observability. The controller has a position-based controller integrated, along with USB communication protocol, enabling gripper state reporting and direct motor control from a PC. A high-level driver operating as a Robot Operating System node is also provided. All drives and circuitry of the PUT-Hand are integrated within the hand itself. The sensory system of the hand includes tri-axial optical force sensors placed on fully actuated fingers’ fingertips for reaction force measurement. A set of experiments is provided to present the motion and perception capabilities of the gripper. All design files and source codes are available online under CC BY-NC 4.0 and MIT licenses.

In this paper, we present a putEMG dataset intended for the evaluation of hand gesture recognition methods based on sEMG signal. The dataset was acquired for 44 able-bodied subjects and include 8 gestures (3 full hand gestures, 4 pinches and idle). It consists of uninterrupted recordings of 24 sEMG channels from the subject’s forearm, RGB video stream and depth camera images used for hand motion tracking. Moreover, exemplary processing scripts are also published. The putEMG dataset is available under a Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0). The dataset was validated regarding sEMG amplitudes and gesture recognition performance. The classification was performed using state-of-the-art classifiers and feature sets. An accuracy of 90% was achieved for SVM classifier utilising RMS feature and for LDA classifier using Hudgin’s and Du’s feature sets. Analysis of performance for particular gestures showed that LDA/Du combination has significantly higher accuracy for full hand gestures, while SVM/RMS performs better for pinch gestures. The presented dataset can be used as a benchmark for various classification methods, the evaluation of electrode localisation concepts, or the development of classification methods invariant to user-specific features or electrode displacement.

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 user's 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°.

This paper presents a study on the feasibility of an interface based on a mechanomyographic signal (MMG). Existing state-of-the-art studies show attempts of utilisation of MMG signal for gesture recognition where the sensors' location is strictly defined with respect to muscle position. A test setup consisting of 5 IMU sensors arranged in a band form was used. The classifier for 5 gestures (fist, pronation, supination, flexion, extension) and idle state was implemented by using a feed-forward neural network with softmax output. The feature vector consists of 18 features: 5 representing muscle activity (RMS) and 13 parameters corresponding to relative sensor orientation, being indicators of local skin surface deformation evoked by muscle shortening. It was shown that taking relative sensor orientation into consideration, was a crucial factor for improvement of classification performance and position invariance. The interface was tested on three subjects, in three distinct orientations. The results showed that average performance represented by F 1 score was 94±6%.

Due to inertial and magnetic sensors imperfections, preprocessing 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.

This paper presents a study of a human-machine interface in the form of three parallel electromyographic bands placed around the user's 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 subject's 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).

In this paper, a method of angular joint position estimation, utilizing small size IMUs, was presented. The method is based on an EKF and a model considering kinematic constraints of links, global orientation, angular velocities and magnetic vector orientation. The tests were performed using a 2-joint phantom with 3 IMUs. UR3 manipulator was used to generate base trajectories. The procedure covered simultaneous movements of manipulator and phantom's joints, and various orientations with respect to gravity vector. Maximum angular rate achieved was 290 degrees/s, while linear accelerations reached 0.6 m/s(2). The overall RMSE error did not exceed 5 degrees, and for movements with high manipulator velocities was kept below 10 degrees.

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.

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.

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.

This paper presents a method of recognizing EOG artifacts in an EEG signal. Moreover, it shows the possibility of determining the direction of eye movement. The idea behind this method is to develop a hybrid braincomputer interface relying on SSVEP phenomena and EOG artifacts acquired from the EEG signal. Recognition of an EOG event and its direction can be used to improve the SSVEP detection accuracy, overall system responsiveness, and increase the information transfer rate (ITR). Eye movement direction is recognized using a decision tree and histogrambased features calculated from EEG signals recorded in Fp1-O1 and Fp2O2 points. The accuracy of 75% was achieved for a group of 8 subjects, while the average precision of detecting movement direction in horizontal plane was 78%.

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.

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.