Abstract Recently, care robots are being developed that incorporate robotics into assistive products that focus on daily care for the physically disabled or elderly with reduced physical function. However, although care robots can reduce the physical burden of human intervention, they can also be dangerous depending on their situational awareness. This study describes a standardization that defines safety requirements for care robots and includes an evaluation method to test their safety based on these requirements. As an example of the application of this standard, a standard for the safety and performance method of a meal assistant robot is shown. This standardization study is expected to contribute to the spread of care robots in the future.

Electromyogram (EMG) signal generated by voluntary contraction of muscles is often used in rehabilitation devices because of its distinct output characteristics compared to other bio-signals. This paper proposes a wearable EMG-based human-computer interface (HCI) for electric-powered wheelchair users with motor disabilities by C4 or C5 level spinal cord injury. User expresses his intention as shoulder elevation gestures, which are recognized by comparing EMG signals acquired from the levator scapulae muscles with a preset threshold value. In this paper HCI command to control electric-powered wheelchair is made of combinations of left-, right-and both-shoulders elevation gestures. The proposed wearable HCI hardware consists of two active surface electrodes, a high-speed micro-controller, a Bluetooth module, and a battery. Experimental results using the wearable EMG based HCI and the electric-powered wheelchair developed show the proposed wearable EMG-based HCI is feasible for the users with severe motor disabilities.

This paper proposes a novel real-time EMG pattern recognition for the control of a multifunction myoelectric hand from four channel EMG signals. To cope with the nonstationary signal property of the EMG, features are extracted by wavelet packet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a linear-nonlinear feature projection composed of PCA and SOFM. The dimensionality reduction by PCA simplifies the structure of the classifier, and reduces processing time for the pattern recognition. The nonlinear mapping by SOFM transforms the PCA-reduced features to a new feature space with high class separability. Finally a multilayer neural network is employed as the pattern classifier. We implement a real-time control system for a multifunction myoelectric hand. From experimental results, we show that all processes, including myoelectric hand control, are completed within 125 msec, and the proposed method is applicable to real-time myoelectric hand control without an operation time delay.

The paralytic caused by the high-level spinal cord injury needs a human-computer interface (HCI) for expressing their intention. In this paper, we propose a novel method to estimate face direction angle using both image observation and electromyogram (EMG) signal from neck muscles. The EMG signal to neck muscle is linear to the face direction angle, but it is undetectable in relatively small angle. Using the image observation, the small face angle is estimated by the geometric relationship between pupils and the face. If two measurements obtained by the EMG signal and the image observation are available, the face direction angle is estimated accurately by a linear interpolation method. We implemented a camera viewing direction control system using the face direction interface, and showed that the proposed method can be used to construct an HCI system for the disabled people with severe motor disabilities.

This paper proposes an intelligent robotic wheelchair with user-friendly human-computer interface (HCI) based on electromyogram (EMG) signal, face directional gesture, and voice. The user's intention is transfered to the wheelchair via the HCI, and then the wheelchair is controlled to the intended direction. Additionally, the wheelchair can detect and avoid obstacles autonomously using sonar sensors. By combining HCI into the autonomous functions, it performs safe and reliable motions while considering the user's intention. The experimental results in the crowded environment show that the proposed robotic wheelchair is feasible for the disabled and the elderly with severe motor disabilities.

This paper proposes a prototype of a safe and reliable wheelchair robot with a human-robot interaction. Since the wheelchair is made for mobility aids for the handicapped, the wheelchair robot must guarantee the safety and reliability while considering the user's intention. A single color CCD camera is mounted to input user's command given by human-friendly gestures, and an array of ultrasonic sensors is used for sensing external environment configurations. We use face and hand directional gestures as the input gestures. By combining the sensory environment information with the user's command given by gestures, the planner of the wheelchair robot selects an optimal motion. We present an implemented prototype of the wheelchair robot, MR. HURI, and show experimentally that it is useful for the disabled and the elderly people.

This paper proposes a method to autonomously extract stable visual landmarks from sensory data. Given a 2D occupancy map, a mobile robot first extracts vertical line features which are distinct and on vertical planar surfaces, because they are expected to be observed reliably from various viewpoints. Since the feature information such as the position and the length includes uncertainties due to errors of vision and motion of the robot, the robot then reduces the uncertainty by matching the planar surface containing the features to the map. As a result, the robot obtains modeled stable visual landmarks from the extracted features. These processes are performed online in order to adapt to actual changes of lighting and scene depending on the robot's view. Experimental results in various scenes show the validity of the proposed method.

Proposes a method to autonomously select stable visual landmarks from observed features by stereo vision and a given 2D obstacle map. The robot selects as stable landmarks vertical line segments which are distinct and on a vertical plane, because they are expected to be observed reliably from various viewpoints. Due to the vision and motion error of the robot, the observed feature positions include uncertainty. This uncertainty can be reduced by matching the detected vertical plane which includes the features to a known plane in the map. The position of a selected feature is modeled by a probabilistic distribution on the known plane. The selection and modeling process is performed online to adapt to an actual lighting and background condition which varies depending on viewpoints. When the robot moves, it uses several, less uncertain landmarks to estimate its motion. Experimental results in real scenes show the validity of the proposed method.

This paper deals with planning of visual navigation strategies for a mobile robot under uncertainty of both visual data and dead reckoning data. When a robot passes through a narrow space, it has to move slowly while carefully observing surrounding objects and estimating the distances to the objects precisely. On the other hand, the robot can move fast in a widely open space. A novel method is proposed which can adaptively determine the speed of the robot and the visual landmarks, thereby realizing an efficient navigation of the robot. Experimental results show the feasibility of the method.