MinKyu Kim

A preliminary analysis of analysis window size and voting size with a time delay for a robust real-time sEMG pattern recognition

Myo-electric signals have been widely used in human-machine interfaces because these biosignal directly reflect human intentions to robots. The major difficulty of applying these biosignal in a pattern recognition system in real time is that they are unstable and vary in time. This instability occurs outside of the steady state of the signal, at the beginning and the ending of the motions. For real-time application users, the errors at the beginning of motion can lower the credibility of a pattern recognition system. In this sense, precise classification is the most significant factor for the system; thus the classification accuracy has higher priority compared to other factors. Generally, a trade-off relationship between the time delay of control commands and the classification accuracy has been known for sEMG users. Since parameters for signal processing can alter the sensitivity(time delay and accuracy) of the system, this study investigates limitations of a pattern recognition system due to transient-state errors. In particular, the performance of the system is analysed with respect to the analysis window size and the voting size of classification. Through an off-line simulation, we propose useful guidelines for the analysis window size and voting size in myoelectric signals for real-time applications.

Analytical modeling of disk-type piezoelectric variable friction tactile displays

This paper presents analytical modeling of disk-type Variable Friction Tactile Displays (VFTD) producing squeeze-film air damping elicited by ultrasonic flexural standing waves of piezoelectric-glass composites. Energy-based Lagrangian mechanics was employed to derive the system dynamic equations of motion of the VFTD vibrating at its fundamental mode. The coefficient of mode shape function and the accumulated electric charge on a piezoelectric element were adopted as two generalized coordinates for the Lagrangian formulation. The derived analytical models can predict undamped free and forced vibrations of VFTDs with hinged or clamped edges. The issues of open-circuit and short-circuit fundamental frequencies and the electromechanical coupling coefficients for several VFTDs with different dimensions were discussed for the optimal design of vibration-induced tactile displays. The theoretical fundamental frequencies were compared with experimental results for the verification of the proposed analytical model.

Tele-operation system with reliable grasping force estimation to compensate for the time-varying sEMG feature

This paper presents a real-time framework for tele-manipulation by using sEMG signals to estimate both human motion and force intention. Our previous study showed that the ability to detect discrete force levels was not applicable to complex tasks such as grasping, holding, and manipulating various objects with variable force. Consequently, we identified the need to simultaneously track the arm and hand configurations and estimate the grasping force. However, it is difficult to continuously estimate the grasping force because of the time-varying nature of surface Electromyogram (sEMG) signals, even if a force remains constant. To solve such a problem, this study proposes a new regression strategy to enable continuous and proportional measurements and transmission of the grasping force by using sEMG signals in transient and steady-states. A 7-DOF robot arm with a robotic hand was able to remotely imitate a subject via an easily-wearable sEMG and inertia measurement units sensor interface. The experimental results verified that the motion and force capturing system successfully enabled interaction tasks, such as grasping, holding, and releasing motions with objects, with reliable and continuous force estimation.

Development of a wearable HCI controller through sEMG & IMU sensor fusion

This paper studies a novel wearable human-computer interface that allows a user to interact with computer-based applications through the fusion of sEMG and IMU sensors. The proposed system is able to detect human motion intention, specifically, the gestures of the wrist and hand. It then translates the gestures and transmits it as command signals for computer-based applications. The novelty of the proposed system is the training-free control scheme to decode sEMG signals into target motions. The classified gestures could be identified by two sEMG sensors mounted on a forearm. One IMU sensor is used to calculate the real-time arm configuration. This can be a command signal for a cursor position in a computer-based application through the proposed projection method. Our method also comprises the drift compensation algorithm which makes our system more robust in prolonged operation. It also makes a user feel more comfortable. For evaluating the applicability of the proposed method, we developed a presentation controller that allows the user to control the mouse cursor, and three distinctive commands using wrist and hand gestures. The proposed system is validated by experiments with six subjects.

Underwater floor pattern matching with an unmanned underwater vehicle

The localization of unmanned underwater vehicle (UUV) is important for the UUV to inspect or manipulator objects. We assume that there is an UUV with a camera sensor and the UUV uses the underwater floor pattern for localization. Because the pattern is known beforehand, the pattern matching between the pattern image and the camera image lets the UUV know its position. The pattern matching algorithm uses the Canny edge extraction method and template based image matching method. The optimization of matching ratio generates the optimal position data of the UUV. We use the Particle Filter method for the optimization method. The experiments show that even though the candidate positional data is not correct, our proposed method finds the position of the UUV with high accuracy.

A robust control method of multi-DOF power-assistant robots for unknown external perturbation using sEMG signals

This paper presents a control method of multi-DOF power assistant robots for anatomical multi-axis joints such as the wrist and the ankle. It is difficult to calculate the accurate direction of human motion intention during manipulating an object due to discrepancy between the calculated force from F/T sensor and the real human intention. Only using an sEMG is not an adequate method of power assistance for unknown external perturbation in the anatomical multi-axis joint, because the sEMG signal cannot figure out where the intention vector exists during interactions. This paper proposes a robust control method of power-assistant robots for unknown external perturbation during manipulating an object by using both the F/T sensor and sEMG. The specific purpose of this study to control the exoskeleton robot for the wrist motion during manipulating an object, although the accurate intention vector of the wrist joint is unknown. It was verified that the proposed method generates the assisted power to follow the human motion intention even in the case of unknown external forces through experiments.

Increasing performance of a pattern recognition system using a sEMG signal by setting multi-references

This paper proposes a special technique for pattern classification problems using the sEMG signal from human forearm muscles. For improvement of classification accuracy, a multi-reference is set for each class so that the classifier can cover a wide range of obtained signals for training. The results of classification accuracy through an off-line simulation were analyzed to validate the proposed concept.

Pilot study on prediction of human hand configuration using transient state of surface-electromyography signals

Surface electromyography (sEMG) signals have been applied as control commands in numerous human-robot interface systems and have been deployed for rehabilitation or clinical applications. Although lots of previous workers have tried to determine features appropriate for specific sEMG-signal classification problems, little of this work has involved deeply searching for the inner characteristics of the signals. In this study, we try to evaluate the properties of the transient state of sEMG signals on randomly mounted, dry-type electrodes and use this to rapidly predict three kinds of hand configurations - rock, scissors and paper motions. In experiments, subjects performed a rock-scissor-paper game with a virtual hand. For data acquisition, the sEMG signals were sampled at 1 kHz with eight-channel electrodes (wearable, dry type) that were randomly mounted on forearms [2]. The results verified that the proposed algorithm, using the property of the transient state of sEMG signals, works successfully.

A Control Scheme to Minimize Muscle Energy for Power Assistant Robotic Systems Under Unknown External Perturbation

This paper proposes a novel control method to minimize muscle energy for power-assistant robotic systems that support the intended motions of a user under unknown external perturbations, using surface electromyogram (sEMG) signals. Conventional control methods based on force/torque (F/T) sensors have limitations to detect human intentions and could, presumably, misunderstand or distort such intentions because of external perturbations of the interaction forces, such as those found in activities of daily living. F/T sensors measure the sum of the applied force, including unknown external forces and human intention; thus, a power-assistant robot controller cannot exactly decompose the real human force. In this paper, we describe a counterexample that cannot be supported by conventional force-sensor-based control methods. We also verify why these control methods may guide human behavior in the wrong direction, and thus, have limitations under unknown external perturbations. We then propose a new control method to minimize the muscle energy indicated by sEMG signals. The proposed control approach is fundamentally based on the concept of power-assistance, in which a robot can reduce the users expended muscle energy while performing given tasks. The proposed control approach is verified through experiments using a power-assistant robotic system for the upper limbs under external perturbations.

Enhancement of sEMG-based gesture classification using mahanobis distance metric

This paper investigates how to improve the performance of Human-Machine Interface systems using surface electromyogram (sEMG) signals to detect human intention in the forearm muscles. Our goal is to make a robust bionic interface that can interact with computers or robots with human motion. Since recognition performance is highly sensitive to the number and the types of target motions to classify, features of them should be properly handled to generate a total number of user commands. This paper introduces two metric parameters: the Repeatability Index (RI) and the Separability Index (SI), both of which quantify feature distributions in feature space. By evaluating the distributions, we could judge which distribution is desired or not for a training dataset. Furthermore, we could know that which motions should be included or not to improve the performance of the system. Among possible target motion sets, we exploited proposed parameters to find optimal target motions, which lead to achieving precise recognition rates. We confirm the validity of this method through off-line simulation experiments. Using a database of 10 subjects, rather than emphasizing a high level of accuracy, we focused instead on determining the correlation between proposed paratmer and system performances. This research could accelerate the development of wearable sensors, which could then become a familiar and easily applicable part of our daily lives.