< Back to previous page
Project
Brain-Computer Interface for real-life applications (OZRIFTM3)
Throughout the years MFYS has built expertise around the evaluation process of different types of robotic prototypes and commercially available devices, i.e. industrial exoskeletons, motorized lower-extremity prostheses, orthoses and cobots, in terms of (psycho-)(electro-) physiological and biomechanical data gathering. Motorized robotic devices are being launched on the market, because of the significant impact on reducing physical and cognitive load, and improving the comfort of the user and in general the quality of life. However, a smooth human-robot interaction is still an issue and, consequently, motorized robots are scarce on the market, e.g. PowerKnee (Össur, Iceland) and the Cray X (German Bionics, Germany) are the sole motorized knee prosthesis and industrial exoskeleton, respectively.
To obtain an optimal human-robot interaction both the design of software and hardware should be improved. The missing link for an optimal human-robot interaction at the level of software is the integration of neural information, coming from the muscle and/or the brain, into the design of a robotic device. The current project Brain-Computer Interface for real-life applications focusses on the level of the brain, since human movement is initiated at the motor cortex. This means that electrical brain activity using electro-encephalography precedes before the onset of human movement. When successfully extracting pre-movement onset indicators and integrating this information into the design of a robotic device, the device will immediately respond to the needs of the user.
The major goal of the project proposal is to develop software for brain-computer interface (BCI) integration into robotic devices for daily use. To achieve this goal the project is divided into several work packages. In the first year, a thorough literature search on state-of-the-art neural networks within the BCI domain will be conducted and first single-subject experiments to set up a first software environment. The second year will be allocated to data acquisition via open sources and well-designed experiments. The plan for the third year is to develop, train and validate the model, and integrate the model into the
design of a robotic device (industrial exoskeleton or prosthetic device). Eventually, the robotic prototype with integrated AI will be evaluated in laboratory conditions and during real-life activities in the fourth year.
The challenging task to control a robotic device with the brain requires a multidisciplinary approach. The collaboration with ETIS is an added value, since ETIS Lab has years of experience with BCI research and systems. Our candidate, Arnau Dillen, has been collaborating in this field of research at the AI Lab of VUB for his master thesis (in collaboration with MFYS). As a computer scientist and software engineer Arnau’s profile fits within the project proposal to successfully complete the predetermined deliverables.
To conclude, the project proposal includes translational research in which a multidisciplinary collaboration is crucial. Software development will be mainly conducted at ETIS, whereas the more practical side of the project and BCI integration in the robotic device will be performed at MFYS.
To obtain an optimal human-robot interaction both the design of software and hardware should be improved. The missing link for an optimal human-robot interaction at the level of software is the integration of neural information, coming from the muscle and/or the brain, into the design of a robotic device. The current project Brain-Computer Interface for real-life applications focusses on the level of the brain, since human movement is initiated at the motor cortex. This means that electrical brain activity using electro-encephalography precedes before the onset of human movement. When successfully extracting pre-movement onset indicators and integrating this information into the design of a robotic device, the device will immediately respond to the needs of the user.
The major goal of the project proposal is to develop software for brain-computer interface (BCI) integration into robotic devices for daily use. To achieve this goal the project is divided into several work packages. In the first year, a thorough literature search on state-of-the-art neural networks within the BCI domain will be conducted and first single-subject experiments to set up a first software environment. The second year will be allocated to data acquisition via open sources and well-designed experiments. The plan for the third year is to develop, train and validate the model, and integrate the model into the
design of a robotic device (industrial exoskeleton or prosthetic device). Eventually, the robotic prototype with integrated AI will be evaluated in laboratory conditions and during real-life activities in the fourth year.
The challenging task to control a robotic device with the brain requires a multidisciplinary approach. The collaboration with ETIS is an added value, since ETIS Lab has years of experience with BCI research and systems. Our candidate, Arnau Dillen, has been collaborating in this field of research at the AI Lab of VUB for his master thesis (in collaboration with MFYS). As a computer scientist and software engineer Arnau’s profile fits within the project proposal to successfully complete the predetermined deliverables.
To conclude, the project proposal includes translational research in which a multidisciplinary collaboration is crucial. Software development will be mainly conducted at ETIS, whereas the more practical side of the project and BCI integration in the robotic device will be performed at MFYS.
Date:1 Oct 2020 → Today
Keywords:brain computer
Disciplines:Control systems, robotics and automation not elsewhere classified, Signal processing not elsewhere classified, Cybernetics, Machine learning and decision making
Project type:Collaboration project