This paper reports a new myoelectric interface for robotic hand control consisting of two main parts. The first part concerns the motion classification using electromyogram (EMG) signals of a support vector machine (SVM). Because there has been little research on the application of the SVM to motion classification using EMG signals, its effectiveness has not yet been established. The SVM has some advantages with respect to generalization and computational complexity, and therefore, we used the SVM to examine its classification ability. The second part concerns the estimation of an operator's joint angle corresponding to the motion determined by the first part. Estimation of the operator's joint angles is based on EMG-Joint angle models, which express the linear relationships between the EMG signals and joint angles. To verify the effectiveness of our interface, we performed off-line hand motion classification and real-time robotic hand control experiments with eight subjects. The experimental results showed that seven hand motions achieved a classification rate of more than 90% for all subjects. In addition, a three-dimensional computer graphics robotic hand was controlled in real-time (62.5Hz) without delay.

Various interfaces using Electromyogram (EMG) signals for controlling a robot hand have been developed. However, there are few researches that apply Support Vector Machines (SVMs) to EMG signal classification for estimating operator's hand motions. There is a possibility that the SVMs are effective classifiers. This paper proposes a real-time hand motion estimation method using the EMG signals with the SVMs. This method consists of two phases for the hand motion estimation. The first phase is the hand motion classification of EMG signal patterns with the SVMs. In addition to amplitude features in the EMG signals, cepstrum coefficients are extracted as frequency features for robust classification. The second phase is the estimation of operator's joint angles. The joint angles are estimated from EMG signals based on simple linear models between the joint angles and the EMG signals. These two phases are designed so that they can be processed in real-time. Experimental results of seven hand motion estimation show the effectiveness of our proposed method.

Although visual semoing is suitable for control of a mobile robot based on a single on-board camera image, wheeled vehicles have a non-holonomic property that the degree of freedom of the input is le33 than that of the configuration. T h w the visual semoing cannot be directly applied to a camera system fixed o n the vehicle. Furthermore there is no smooth and stable state feedback law for non-holonomic vehicle. To overcome these dificulties, we consider another situation that the pan angle of camera is actuated and used as an input of visual semoing. The desired state is given as not a constant value but a traject o y represented in terms of image sequences of a gazed object. Based on this idea, we propose a method of realizing "teaching and playback" for non-holonomic mobile robot. In the teaching mode, the robot gazes a landmark in the environment by a single on-board camera and stores its image sequences while running commanded by a human operator. In the playback mode, the robot t r a c b the desired trajectory with velocity commands for the vehicle and the pan angle for the camera determined from the stored and current images. W e discuss the convergence to a desired state and moreover point out an additional feedback term of a deviation of the pan angle w o r h t o improve the tracking performance. The eflectiveness of the proposed method is shown by illustrating computer simulation re-3Ult3.

A library creates new services for attracting library users continuously. This paper presents a new book recommendation digital signage system. The system classifies characteristics such as gender or age of a walking library user, and displays a recommended book on an LCD for him/her. A set of silhouette image sequence of a walker extracted from real-time video is used for classification with Support Vector Machine (SVM). Since a calculation amount of a silhouette-based classification method is less than a three-dimensional model-based classification, it is suitable for real-time classification. We design a classifier that has better performance by evaluating some parameters and image features for classification. Some experimental results reveal the validity and effectiveness of our proposed signage system. 10th International Conference on Machine Learning and Applications978-0-7695-4607-0/11 $26.00

No abstract