A Study On Brain Computer Interface(BCI)-Based Functional Assistance For The Seriously Disabled

Millions of people around the world suffer from severe mobility impairments, such as strokes, spinal cord injuries(SCI), amyotrophic lateral sclerosis(ALS). These severely disable individuals cannot convey their intentions with these convention human machine interfaces(e.g., keyboard). Fortunately, brain-computer interfaces(BCIs) provide non-muscular communication and control by directly translating brain activities recorded from the scalp into control commands and thus enable these individuals with motor disabilities to interact with the external world. Most of paralyzed patients are long-term bedridden and thus generally have limited motion space constrained on in bed or wheelchair. In view of this, the main content of this article makes a research on the BCI-based functional assistance for the severely paralyzed patients, and devotes to developing practical and user-friendly BCI-based assistance devices, such as braincontrolled wheelchairs and nursing bed in order to assist the daily life of the severely paralyzed patients.This paper firstly conducts the study on combining the BCI techniques with automatic navigation to share the control over the wheelchair. Using an autonomous navigation system,candidate destinations and waypoints are automatically generated based on the existing environment. The user selects a destination using a motor imagery(MI)-based or P300-based BCI.According to the determined destination, the navigation system plans a short and safe path and navigates the wheelchair to the destination. Compared with other BCI-based wheelchairs of the same type, the mental burden of the user can be substantially alleviated via our system. Furthermore, our system can adapt to changes in the environment. Two experiments based on MI and P300 were conducted to demonstrate the effectiveness of our system.Most of home environment is unstructured, the wheelchair systems based on known environment map have some limitations in unstructured environment. In view of this, a braincontrolled wheelchair combining the fusion of sensed information and BCI techniques is developed from a pespective of shared control, in which the user and the autonomous navigation system share the control over the wheelchair in the unknown environment. The techniques of direction recognition and angle tracking is applied to the wheelchair system in order to solve the problem that multistep selections are required to reach a long distance destination under such as corridor environments. Furthermore, the paper presents a detection algorithm based on fast eye blinking and employ it for the stop command of the wheelchair, and thus increase the response speed of the stop command.Moreover, an asynchronous P300-based BCI is presented. First, the high dimensional EEG features are firstly transformed into the univariate space, and the statistical models for the EEG features under different states(control or idle state) of the subject are then built. Thirdly, we deduce the computational method of the specific intention of the subject. Last, we provide a detection algorithm on asynchronous P300-based BCI and apply it into the control of nursing bed system for the severely paralyzed patients. Experimental results not only demonstrated the proposed algorithm could detect the different states of the subject, but also showed all subjects,including a SCI patient, can perform a series of operations via the proposed nursing bed system.Based on the previously described BCI-based intelligent wheelchair and nursing bed, we develop a P300 BCI-based environmental control system to provide daily assistance to the paralyzed patients with severe SCIs. The proposed system can run with synchronous and asynchronous control mode under different situations in order to achieve self-paced control while keeping the performance of the BCI system. Furthermore, we introduce several pseudo-keys and a verification mechanism into our paradigm to effectively reduce the false operation rate.Two experiments involving six patients with severe SCIs were conducted separately in a nursing bed and a wheelchair. Experimental results showed that these SCI patients could use the proposed P300 BCI-based environmental control system satisfactorily, and thus demonstrated its potential to assist severely paralyzed individuals in their daily lives.