Biometric Analysis of Handwriting Dynamics Using a Script Generator Model

Viewing the motion of human body parts activates different regions of premotor, temporal, and parietal cortex

The goal of this study is to develop a wireless-controlled robotic hand that is capable of replicating the movements of a human hand. A central objective of the design process is the development of a sensing technique that can accurately capture and translate human hand movements into electrical signals in a sustainable manner. This sensing technology relies on the detection of flexion and extension in the human hand, achieved through the modulation of light transmitted from a Light-Emitting Diode (LED) and received by a Light-Dependent Resistor (LDR). Five sensors, each corresponding to a finger, are integrated into a glove worn by the user, thereby enabling an intuitive control of the robotic hand. The sensors generate discrete electrical signals with each finger movement, which are then wirelessly transmitted via nRF24l01 modules to the microcontroller of the robotic hand. Subsequently, the microcontroller generates the requisite electrical signals to actuate the servo motors, thereby orchestrating the movement of the robotic fingers to mimic human hand gestures. The robotic hand, comprising 46 individual components fabricated using biodegradable polylactic acid material via 3D printing, successfully achieves its objective of replicating human hand movements. However, a minor delay in milliseconds is observed between human hand movements and the corresponding robotic hand movements. Despite this delay, the developed system shows promise for applications in hazardous environments, such as dangerous chemistry experiments, and enhances safety in the medical laboratory. It may also play a crucial role in remote surgery procedures.

In this paper, Haptic End-effector for Medicine and Manufacturing (HEM2) with five degree of freedom (DoF) motion is developed for safer and more intuitive robotic surgery. In resent years, multi DoF forceps robots have been studied and developed to support surgeons. However, conventional multi DoF forceps robots cannot transmit force sensation to surgeons adequately. Force sensation is important for safe and accurate teleoperation. In this paper, a master-slave five DoF HEM2 is developed as a haptic forceps robot. Five DoF motion corresponds with the motion of human hand which can realize complex tasks. By implementing acceleration based bilateral control, force sensation can be transmitted. Spherical joint driven by parallel link mechanism realizes the bending motion of the end-effector. The coaxial driving power transmission mechanism is used to decrease the weight of movable part and improve backdrivability. Besides, the mechanism is composed of rigid parts. The performance of the five DoF HEM2 is validated by experiments.

The ability to measure human hand motions and interaction forces is critical to improving our understanding of manual gesturing and grasp mechanics. This knowledge serves as a basis for developing better tools for human skill training and rehabilitation, exploring more effective methods of designing and controlling robotic hands, and creating more sophisticated human-computer interaction devices which use complex hand motions as control inputs. This paper presents work on the design, fabrication, and experimental validation of a soft sensor-embedded glove which measures both hand motion and contact pressures during human gesturing and manipulation tasks. We design an array of liquid-metal embedded elastomer sensors to measure up to hundreds of Newtons of interaction forces across the human palm during manipulation tasks and to measure skin strains across phalangeal and carpal joints for joint motion tracking. The elastomeric sensors provide the mechanical compliance necessary to accommodate anatomical variations and permit a normal range of hand motion. We explore methods of assembling this soft sensor glove from modular, individually fabricated pressure and strain sensors and develop design guidelines for their mechanical integration. Experimental validation of a soft finger glove prototype demonstrates the sensitivity range of the designed sensors and the mechanical robustness of the proposed assembly method, and provides a basis for the production of a complete soft sensor glove from inexpensive modular sensor components.

This study clarifies the effects of follower–leader information asymmetry, which is due to a target position and a transport cycle, on brain activities during human–human 1-DOF parallel reciprocating transport work. Elucidating the effects of information asymmetry on leader–follower brain activities by analyzing brain activity and hand movements in humans with visual information and humans without visual information will reveal the behavioral characteristics of humans for cooperative work. Therefore, in this study, we simultaneously measured brain activities, the forces applied to a 1-DOF transportation mechanism, and the hand positions of two people during human–human 1-DOF parallel reciprocating transport work using a transport cycle of 3 s. Three levels were set for the follower side to antisymmetrize the information of a follower with respect to a leader: i) the follower was asked to wear an eye mask and not be informed of a target position and a transport cycle (Level 1), ii) the follower was informed of a target position but not a transport cycle (Level 2), and iii) the follower was informed of a transport cycle and a target position by a metronome sound (Level 3). In the evaluation of brain activity, brain activation was assessed by the amount of change in the concentration of oxygenated hemoglobin (Oxy–Hb), which had the highest correlation with changes in cerebral blood flow. The results showed that Level 2, which corresponded to cooperative work between humans with visual information, demonstrated significant synchronization changes in both cerebral blood flow in mirror neurons and hand inertia/stiffness compared to Level 1, which corresponded to cooperative work between humans with visual information and humans without visual information, suggesting a relationship between them. In addition, the evaluation of brain activation and impedance change suggests that cooperative work among humans with visual information did not involve voluntary movements but smoother cooperative work from both neuroscientific and kinematic perspectives.

The brain uses gaze orientation to organize myriad spatial tasks including hand movements. However, the neural correlates of gaze signals and their interaction with brain systems for arm movement control remain unresolved. Many studies have shown that gaze orientation modifies neuronal spike discharge in monkeys and activation in humans related to reaching and finger movements in parietal and frontal areas. To continue earlier studies that addressed interaction of horizontal gaze and hand movements in humans (Baker et al. 1999), we assessed how horizontal and vertical gaze deviations modified finger-related activation, hypothesizing that areas throughout the brain would exhibit movement-related activation that depended on gaze angle. The results indicated finger movement-related activation related to combinations of horizontal, vertical, and diagonal gaze deviations. We extended our prior findings to observation of these gaze-dependent effects in visual cortex, parietal cortex, motor, supplementary motor area, putamen, and cerebellum. Most significantly, we found a modulation bias for increased activation toward rightward, upper-right and vertically upward gaze deviations. Our results indicate that gaze modulation of finger movement-related regions in the human brain is spatially organized and could subserve sensorimotor transformations.

In this study, an adaptive object deformability-agnostic human-robot collaborative transportation framework is presented. The proposed framework enables to combine the haptic information transferred through the object with the human kinematic information obtained from a motion capture system to generate reactive whole-body motions on a mobile collaborative robot. Furthermore, it allows rotating the objects in an intuitive and accurate way during co-transportation based on an algorithm that detects the human rotation intention using the torso and hand movements. First, we validate the framework with the two extremities of the object deformability range (i.e., purely rigid aluminum rod and highly deformable rope) by utilizing a mobile manipulator which consists of an Omni-directional mobile base and a collaborative robotic arm. Next, its performance is compared with an admittance controller during a co-carry task of a partially deformable object in a 12-subjects user study. Quantitative and qualitative results of this experiment show that the proposed framework can effectively handle the transportation of objects regardless of their deformability and provides intuitive assistance to human partners. Finally, we have demonstrated the potential of our framework in a different scenario, where the human and the robot co-transport a manikin using a deformable sheet. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —Transportation of objects which requires the cooperation of multiple partners, is a common task in industrial settings such as factories and warehouses. The existing human-robot collaboration solutions for this task have focused only on purely rigid objects, although deformable objects need to be carried frequently in real-world applications. In this paper, we introduce a human-robot collaborative transportation framework that can handle objects with different deformability ranging from purely rigid to highly deformable. In particular, the proposed framework generates whole-body movements on a mobile collaborative robot by combining of the haptic information transmitted through the object and the human motion information obtained from a motion capture system. Moreover, the framework includes an intuitive way to rotate the object during the execution based on human hand and torso motion. The results of the experiments where objects with various deformability characteristics were transported in collaboration with a mobile manipulator demonstrated the high potential of the proposed approach in a laboratory setting. In the future, we plan to employ a less expensive vision-based human motion tracking system instead of the IMU-based system used in this study. With this change, we will be able to eliminate the need for wearable sensors from the framework presented, which would enhance its usability in real-world scenarios.

This paper proposes an algorithm to correct the gyroscope drift problem in Inertial Measurement Units used in human hand motion tracking. The algorithm will predict the bias offset error only when the sensor is static using a linear regression model. A quaternion orientation estimate was calculated using unbiased gyroscope data. The angular difference between the measured gravity vector from the accelerometer and the gravity vector calculated using the current quaternion was determined and used to update the quaternion orientation estimate. The result shows that using gravity-vector compensation can reduce the gyroscope drift problem in orientation tracking for human hand motion.

The fact that neuroleptics may have a more or less noticeable influence on fine motor skills is well-known. However, up to now there is no system that allows one to measure and to quantify such an impact of neuroleptics or other drugs. This article goes a first step into this direction by demonstrating how the handwriting dynamics of a healthy person can automatically be distinguished from that of a schizophrenic and, therefore, appropriately medicated person. Moreover, it is shown that differences can be detected even for a very simple kind of hand movement. That is, the persons trace a given meander. The handwriting dynamics are measured by means of a pen equipped with force and tilt sensors (biometric smart pen). Then, the parameterized script generator model proposed by Hollerbach is used in order to extract characteristic features from the measured signals, e.g., features describing deviations of measured time series from predicted model time series. These features are then used as inputs of support vector machines that classify whether the handwriting has been provided by a healthy or a diseased person

본 연구는 마우스의 입력을 사람의 손동작으로 대체하는 휴먼마우스 시스템에 관한 것이다. 모니터의 해상도가 커지면서 웹카메라와 모니터간의 해상도 차이로 인하여 단순히 웹카메라에서 손의 위치를 인식하여 포인터를 이동시키는 방법으로는 모니터의 모든 범위에 커서를 위치시킬 수가 없다. 따라서, 되돌아오는 동작을 반복하지 않고 마우스의 위치를 모니터의 가장자리까지 원하는 곳으로 편리하게 위치시키는 효과적인 방법을 제안한다. 또한, 다양한 마우스이벤트를 처리하기 위하여 엄지와 검지를 이용한 손가락 동작 인식을 제안하고 인식률을 측정한 결과, 97% 이상으로 그 유효성을 확인하였다. This paper proposes a human mouse system that replaces mouse input by human hand movement. As the resolution of monitors increases, it is not quite possible, due to the resolution difference between web cameras and monitors, to place the cursor in the entire range of a monitor by simply moving the pointer which recognizes the position of the hand from the web camera. In this regard, we propose an effective method of placing the position of the mouse, without repeating the returning hand movements, in the corners of the monitor in which the user wants it to be. We also proposes the recognition method of finger movements in terms of using thumb and index finger. The measurement that we conducted shows the successful recognition rate of 97% that corroborates the effectiveness of our method.

Earlier experimental studies by one of us (Kelso, 1981a, 1984) have shown that abrupt phase transitions occur in human hand movements under the influence of scalar changes in cycling frequency. Beyond a critical frequency the originally prepared out-of-phase, antisymmetric mode is replaced by a symmetrical, in-phase mode involving simultaneous activation of homologous muscle groups. Qualitatively, these phase transitions are analogous to gait shifts in animal locomotion as well as phenomena common to other physical and biological systems in which new "modes" or spatiotemporal patterns arise when the system is parametrically scaled beyond its equilibrium state (Haken, 1983). In this paper a theoretical model, using concepts central to the interdisciplinary field of synergetics and nonlinear oscillator theory, is developed, which reproduces (among other features) the dramatic change in coordinative pattern observed between the hands.

The purpose of this study was to investigate the differences in the brain organization of motor control in left- and right-handers and to study whether early left-to-right handwriting switch changes the cortical representation of finger movements in the left and right hemispheres. Echo-planar MR imaging was performed in 52 subjects: consistent right-handers (RH), consistent left-handers (LH), and subjects who had been forced at an early age to switch their left-hand preferences toward the right side. The scanning was performed during simple (flexion/extension of the index finger) and complex (successive finger-thumb opposition) tasks. Subjects performed the tasks using both the preferred and non-preferred hand. In right-handers, there was a general predominance of left-hemisphere activation relative to right hemisphere activation. In lefthanders this pattern was reversed. The switched subjects showed no such volumetric asymmetry. Increasing levels of complexity of motor activity resulted in an increase in the volume of consistently activated areas and the involvement of the ipsilateral in addition to contralateral activations. In both right- and left-handers, movements of the preferred hand activated mainly the contralateral hemisphere, whereas movements of the non-preferred hand resulted in a more balanced pattern of activation in the two hemispheres, indicating greater involvement of the ipsilateral activations. Overall, this study shows that in both left- and right-handed subjects, the preferred hand is controlled mainly by the hemisphere contralateral to that hand, whereas the non-preferred hand is controlled by both hemispheres. The switched individuals share features of both lefthanders and right-handers regarding their motor control architectures.

By moving muscles, the myogenic potential (Electromyogram: EMG) is observed on the surface of the living body. It is considered that the EMG is useful for controlling a robot hand. However, the EMG depends on physical conditions, the state of mind and so on. So, the original EMG will be not used for controlling the robot hand directly. In this study, it is considered that the EMG relating the motion of the human hand is analyzed by the fuzzy theory for making the robot hand performs the same motion as the human hand. EMG were measured under the following conditions. (1) opening the hand, (2) bending the thumb, (3) bending the middle finger, (4) bending the index finger, (5) closing the hand, (6) not move. Six production rules were made with fuzzificate data resulted from fourier transforming the EMG (30-band 1/3 octave analysis). Also the EMG measured by experimental motion of the human hand was transformed into the fuzzificate date. Rates of recognitions were calculated in comparison with the six production rules and the experimental data. And one production rule with highest rate of recognition was used for recognition of movement of the human hand in the computer. From the experimental results, about 90% of movement were recognized by the computer. The results were applied to control the robot hand.

In recent years, the demands of using robotic hands have been increased dramatically in a variety of applications such as intelligent manufacturing. The current robotic hands usually are functioned relying on the assembly of numerous components, which bring unnecessary dead weight and complex control systems. Such shortcomings limit the further application of robotic hands. To address this issue, this paper presents a lightweight and low-complexity five-fingered robotic hand called the Integrated Finger Robotic Hand (IFRH). Each finger of the robotic hand is built as an integrated object based on a compliant joint called the Elastic Knuckle Connection (EKC). The 3D-printed finger design minimizes the number of components as well as the weight of the system. The IFRH can be assembled quickly and maintained easily due to its low number of parts compared to traditional separate-finger robotic hands. The IFRH is driven by servo motors which transmit motion to a monofilament fishing string. This fishing string is connected to each finger, which mirrors the grasping motion of a real human hand when contracted. With feedback from force sensors, the IFRH accomplishes the goal of high precision grasping of daily objects. The IFRH can be controlled by a potentiometer powered by Arduino, further increasing the user-friendly nature of the robotic hand. A number of experimental tests are conducted to verify the accuracy of the force transmission system, the grasping capabilities, and the grasping precision.

Learning models of bimanual manipulation tasks from human demonstration requires capturing human body and hand motions, as well as the objects involved in the demonstration, to provide all the information needed for learning manipulation task models on symbolic and subsymbolic level. We provide a new multi-modal dataset of bimanual manipulation actions consisting of accurate human whole-body motion data, full configuration of both hands, and the 6D pose and trajectories of all objects involved in the task. The data is collected using five different sensor systems: a motion capture system, two data gloves, three RGB-D cameras, a headmounted egocentric camera and three inertial measurement units (IMUs). The dataset includes 12 actions of bimanual daily household activities performed by two healthy subjects with a large number of intra-action variations and three repetitions of each action variation, resulting in 588 recorded demonstrations. A total of 21 household items are used to perform the various actions. In addition to the data collection, we developed tools and methods for the standardized representation and organization of multi-modal sensor data in large-scale human motion databases. We extended our Master Motor Map (MMM) framework to allow the mapping of collected demonstrations to a reference model of the human body as well as the segmentation and annotation of recorded manipulation tasks. The dataset includes raw sensor data, normalized data in the MMM format and annotations, and is made publicly available in the KIT Whole-Body Human Motion Database.