In recent years, the assistive technologies and stroke rehabilitation methods have been empowered by the use of virtual reality environments and the facilities offered by brain computer interface systems and functional electrical stimulators. In this paper, a therapy system for stroke rehabilitation based on these revolutionary techniques is presented. Using a virtual reality Oculus Rift device, the proposed system ushers the patient in a virtual scenario where a virtual therapist coordinates the exercises aimed at restoring brain function. The electrical stimulator helps the patient to perform rehabilitation exercises and the brain computer interface system and an electrooculography device are used to determine if the exercises are executed properly. Laboratory tests on healthy people led to system validation from technical point of view. The clinical tests are in progress, but the preliminary results of the clinical tests have highlighted the good satisfaction degree of patients, the quick accommodation with the proposed therapy, and rapid progress for each user rehabilitation.
The worldwide statistics reported by World Health Organization highlight that stroke is the third leading cause of death and about 15 million people suffer stroke worldwide each year . Of these, 5 million are permanently disabled needing long time assistance and only 5 million are considered socially integrated after recovering. Recovering from a stroke is a difficult and long process that requires patience, commitment, and access to various assistive technologies and special devices. Rehabilitation is an important part of recovering and helps the patient to keep abilities or gain back lost abilities in order to become more independent. Taking into account the depression installed after stroke, it is very important for a patient to benefit from an efficient and fast rehabilitation program followed by a quick return to community living . In the last decade, many research groups are focused on motor, cognitive, or speech recovery after stroke like Stroke Centers from Johns Hopkins Institute , ENIGMA-Stroke Recovery , or StrokeBack Consortium funded by European Union’s Seventh Framework Programme . Important ICT companies bring a major contribution to the development of technologies and equipment that can be integrated into rehabilitation systems. For example, Stroke Recovery with Kinect is a research project to build an interactive and home-rehabilitation system for motor recovery after a stroke based on Microsoft Kinect technology .
In the last years, the virtual reality (VR) applications received a boost in development due to VR headset prices that dropped below $1000, allowing them to become a mass-market product . The VR was and still is especially used for military training or video games to provide some sense of realism and interaction with the virtual environment to its users . Now it attracts more and more the interest of physicians and therapist which are exploring the potential of VR headset and augmented reality (AR) to improve the neuroplasticity of the brain, to be used in neurorehabilitation and treatment of motor/mental disorders . However, considering the diversity of interventions and methods used, there is no evidence that VR therapy alone can be efficacious compared with other traditional therapies for a particular type of impairment . This does not mean that the potential of VR was overestimated and the results are not the ones that were expected. The VR therapy must be complemented with other forms of rehabilitation technologies like robotic therapy, brain computer interface (BCI) and functional electrical stimulation (FES) therapy, and nevertheless traditional therapy to provide a more targeted approach .
SaeboVR is a virtual rehabilitation system exclusively focusing on activities of daily living and uses a virtual assistant that appears on the screen to educate and facilitate performance by providing real-time feedback . The neurotechnology company MindMaze has introduced MindMotion PRO, a 3D virtual environment therapy for upper limb neurorehabilitation incorporating virtual reality-based physical and cognitive exercise games into stroke rehabilitation programs . At New York Dynamic Neuromuscular Rehabilitation, the CAREN (Computer Assisted Rehabilitation Environment) based on VR is currently used to treat patients poststroke and postbrains injuries . EVREST Multicentre has achieved remarkable results regarding the use of VR exercises in stroke rehabilitation .
Motor imagery (MI) is a technique used in poststroke rehabilitation for a long time ago. One of its major problems was that there was not an objective method to determine whether the user is performing the expected movement imagination. MI-based BCIs can quantify the motor imagery and output signals that can be used for controlling an external device such as a wheelchair, neuroprosthesis, or computer. The FES therapy combined with MI-based BCI became a promising technique for stroke rehabilitation. Instead of providing communication, in this case, MI is used to induce closed-loop feedback within conventional poststroke rehabilitation therapy. This approach is called paired stimulation (PS) due to the fact that it pairs each user’s motor imagery with stimulation and feedback, such as activation of a functional electrical stimulator (FES), avatar movement, and/or auditory feedback . Recent research from many groups showed that MI can be recorded in the clinical environment from patients and used to control real-time feedback and at the same time, they support the hypothesis that PS could improve the rehabilitation therapy outcome [17–21].
In a recent study, Irimia et al.  have proved the efficacy of combining motor imagery, bar feedback, and real hand movements by testing a system combining a MI-based BCI and a neurostimulator on three stroke patients. In every session, the patients had to imagine 120 left-hand and 120 right-hand movements. The visual feedback was provided in form of an extending bar on the screen. During the trials where the correct imagination was classified, the FES was activated in order to induce the opening of the corresponding hand. All patients achieved high control accuracies and exhibited improvements in motor function. In a later study, Cho et al.  present the results of two patients who performed the BCI training with first-person avatar feedback. After the study, both patients reported improvements in motor functions and both have improved their scores on Upper Extremity Fugl-Meyer Assessment scale. Even if the number of patients presented in these two studies is low, they support the idea that this kind of systems may bring additional benefits to the rehabilitation process outcome in stroke patients.
2. General System Architecture
The BCI-FES technique presented in this paper is part of a much more complex system designed for stroke rehabilitation called TRAVEE , presented in Figure 1. The stimulation devices, the monitoring devices, the VR headset, and a computer running the software are the main modules of the TRAVEE system. The stimulation devices help the patient to perform the exercises and the monitoring devices are used to determine if the exercises are executed properly, according to the proposed scenarios. Actually, the TRAVEE system must be seen as a software kernel that allows defining a series of rehabilitation exercises using a series of USB connectable devices. This approach is very useful because it offers the patient the options to buy, borrow, or rent the abovementioned devices according to his needs and after connection, the therapist may choose the suitable set of exercises.[…]