The paper describes a new approach to image segmentation. It accepts the inherent deficiencies occuring when extracting low-level features and when dealing with the complexity of real scenes. Image segmentation therefore is understood as deriving a rich symbolic description useful for tasks such as stereo or object recognition in outdoor scenes. The approach is based on a polymorphic scheme for simultaneously extracting points, lines and segments in a topologically consistent manner, together with their mutual relations derived from the feature adjacency graph (FAG) thereby performing several grouping steps which gradually use more and more specific domain knowledge to achieve an optimal image description. The heart of the approach is (1) a detailed analysis of the FAG and (2) a robust estimation for validating the found geometric hypotheses. The analysis of the FAG, derived from the exoskeleton of the features, allows to detect inconsistencies of the extracted features with the ideal image model, a cell-complex. The FAG is used for finding hypotheses about incidence relations and geometric hypotheses, such as collinearity or parallelity, also between non-neighbored points and lines. The M-type robust estimation is used for simultaneously eliminating wrong hypotheses on geometric relationships. It uses a new argument for the weighting function

Категория: Ищем научные статьи | Нет комментариев »

Task based repetitive therapy has been proposed as a promising approach to train stroke survivors to regain functional control of arm movement. The hypothesis is that such intensive therapeutic approach can induce the desirable neural plasticity or adaptation to compensate for the damage in central nervous system. We have developed a wearable exoskeleton rehabilitation robot, the associated control algorithm, the framework for automated and customizable therapy sessions, safety protection mechanisms, and a graphic user interface that is easy to use and intuitive to the patients and therapists. The system was first tested in a laboratory setting on 6 stroke survivors on 3 weekly visits. Each patient went through a four-week period of robot assisted therapy. We then conducted at-home therapy for 2 subjects who used the system for arm function therapy at least once daily. Both the patients and the spouses are favorably impressed by this system setup, which stresses for training the arm movement according to a video game. After one week, they have already increased the practice intensity to twice a day with evidence of competency in motor control for more demanding tasks. The therapeutic effect of repetitive therapy will be best realized by long term and multiple intensive sessions per day. Such approach is feasible by robotic assisted setup at-home. Our approach will provide valuable information on determining therapy intensity and repetitions and monitoring progress.

Категория: Ищем научные статьи | Нет комментариев »

In order to assist the motion in the daily lives of physically weak persons such as elderly persons, many kinds of power-assist robots have been developed. In the case of some physically weak persons, the ability to perceive the environment is sometimes deteriorated also. A method of perception-assist has been proposed to assist not only the user’s motion but also the user’s interaction with an environment, by applying the modification force to the user’s motion if it is necessary. In this paper, the perception-assist for a lower-limb power-assist exoskeleton robot is proposed. In the daily life, the walking is very important for persons to achieve desired tasks. Basically, the robot assists the user’s muscle force according to the user’s motion intention which is estimated based on EMG signals. If the robot has found problems which might lead the user to dangerous situation such as the falling down, the robot tries to modify the user’s motion in addition to the ordinal power-assists to make the user walk properly. Since the user might fall down by the effect of the additional modification force of the perception-assist, the robot automatically prevents the user from falling down by considering ZMP (Zero Moment Point). The effectiveness of the proposed method has been evaluated by performing experiments.

Категория: Ищем научные статьи | Нет комментариев »

The control of a rehabilitation robot for stroke should be designed to promote active participation of patients in the therapy process. This goal can be achieved by performance based assistance control to provide assistance only when needed and where it is needed. This control philosophy is implemented on Robot for Upper Extremity Repetitive Therapy (RUPERT), a wearable robotic exoskeleton powered by pneumatic muscle actuators. Therapy of stroke survivors under this control using RUPERT has been carried out on 6 patients. Some preliminary analysis of the performance outcome after the therapy is presented in this report. The result is promising though a controlled study has to be done to illustrate the real advantage of the adaptive performance based control.

Категория: Ищем научные статьи | Нет комментариев »

There are patients that cannot produce bioelectric signals such as patients with advanced stages of Amyotrophic Lateral Sclerosis or that have suffered severe spinal cord injury, are unable to use assistive devices such as the exoskeleton HAL. This paper proposes a non-invasive brain activity scanning method for collecting the patient’s movement intentions by developing a hybrid sensor that can measure both optical and bioelectrical signal of a same spot simultaneously and to evaluate it. The developed sensor consists of holography lasers and electrodes. Holography laser contains emitter and receiver inside it. In order to evaluate the hybrid sensor two kinds of experiments were carried out: 1) Data Collection Experiment in which the optical density was found to be high when the participant was in relaxation state. On the other hand, while the participant was executing mental tasks such as algebraic calculations the optical density lowered. 2) Proof of concept Experiment in which the participant tried to move the upper limb assistive device 10 times. The upper limb movement was recorded 24 times during this period. However out of this 24 times, the upper limb movement corresponded to the participant’s intention 7 times that was recorder 5sec before or after subject started calculation. We developed a hybrid sensor that can collect both kinds of optical and bioelectrical signal from the same spot on the scalp was developed and evaluated in order to measure brain activity by using optical and bioelectrical data.

Категория: Ищем научные статьи | Нет комментариев »