Design Of Wheelchair Control System Based On Multimodal Brain-computer Interface

In recent years,a growing body of research has shown that the performance of braincomputer interface(BCI)systems can be improved by employing multimodal signal fusions.Brain-controlled wheelchair(BCW)system,a control mode with a strong interconnection between BCI and life,relies on the brain directly rather than the external nerves or the muscle tissue as operating wheelchairs,so people with severe mobility disorders benefit enormously from operating wheelchairs under BCI systems independently in their daily lives.The primary goal of this research is to establish safe and reliable brain-controlled wheelchair systems that promote better alignment between the multimodal brain-computer interface technology and the wheelchair control systems.The main work of this paper includes:(1)The framework of the BCW system has been designed,including both the hardware design and software design of the system.For one thing,the control instructions are obtained based on the processing and classification of the user’s EEG signals and sent to the wheelchair main control board through Bluetooth.And for another,the wheelchair main control board realizes corresponding control from the analysis of all the instructions.(2)The BCW system based on P300 and the BCW system based on SSVEP have been built respectively.Meanwhile,offline and online experiments have been designed for these single-mode BCW systems.Specifically,the former is used to determine the signal classification algorithm and threshold.The latter is mainly used to test the synchronous control and asynchronous control performance of the two systems that provide a reference for the paradigm design of the multimodal BCW system.(3)A paradigm design framework for a multimodal BCW system has been built.The states of the BCW system are classified as closed states,waiting for the state,and running states on the basis of the wheelchair control.Therefore,the paradigm design of the multimodal system can be transformed into system waiting state paradigm design and running state paradigm design.On account of this,a brain-controlled wheelchair system based on EMG and SSVEP has been built.The EMG signal generated by gritting teeth is used to detect whether the user has control intention when the system is waiting,and the SSVEP is put in the movement control of the wheelchair.And this experiment shows that the brain-controlled wheelchair system based on EMG and SSVEP reduces the times of false starts of the system and improves the safety of the system on the premise of improving the synchronous control performance of the system.(4)A multimodal BCW system based on the P300 and SSVEP has been built,in which the attention state detection is introduced.Particularly,the P300 and attention detection suffice for judging the user’s control intention and setting parameters in the waiting state,and the SSVEP reacts to the wheelchair travel control.Experiments have shown that the average false alarm rate of the system in the waiting state is 0.44 times/minute,and the number of false starts is 0.Compared with other methods,the multimodal brain-controlled wheelchair system presented in this paper not only achieves synchronous performance but also effectively improves the performance and security of asynchronous control,which confirms the utility and significance of this study.