Workshops

Lately, BCI systems become increasingly used in the context of stroke rehabilitation. Many BCI systems are based on motor imagery activity recorded from the sensorimotor cortex, which is translated into continuous control signals for rehabilitation devices.
The workshop will review current stroke rehabilitation using BCI technology and will provide insight into technology, experimental setups, results and outcomes of patient studies.
Some patients diagnosed as vegetative are reclassified as (at least) minimally conscious when assessed by expert teams. A further subset of potentially communicative non-responsive patients might be undetectable through standard clinical testing. Other patients might have transient periods of relative wakefulness, but remain unaware of their surroundings. The workshop will provide an overview of BCI technology to identify non-responsive patients that might be able to communicate and use the technology as an assessment tool.
In live demonstrations, we will show systems, which are already in use in rehabilitation units and hospitals. Participants will get the opportunity to try these systems.

Current research in the field of human-centered technologies has mainly focused on pushing forward the boundaries of the mechatronics and robotics. Yet, the role of real-time control architectures still represents an emerging area of investigation. Optimizing the control robustness is, in fact, a milestone that allows us to properly design robotic systems, which must closely interact with human beings.
The unmatched performance of the human sensorimotor system imposes multiple challenges for the design of robotic interfaces which should work in the field of neurorehabilitation, and assistive devices such as exoskeletons, prostheses, and telerobots. Bidirectional kinematic and dynamic communication between the robotic and human actors can be tackled by a control design which must be able to i) collect and interpret the user’s intention (e.g., EEG-EMG decoding), ii) convert it to control signals for the assistive device (e.g., AI-based predictive models), and iii) feedback to the user relevant sensory information (e.g., augmented feedback) to allow her/him to take the next action and, ultimately, (re-)learn the motor task.
All these stages further require optimal real-time control in order to be robust to latencies and disturbances originating from several sources. A challenge that still remains open, hampering human-machine interfaces to reach full effectiveness in neurorehabilitation.
To tackle this, a variety of control strategies and architectures have been developed in an ongoing global research effort in real-time embedded control systems, to devise the most seamless integration of robotic devices with human users, and boost their widespread adoption.
We believe that it is possible to foster the development of future solutions only by shedding light on these common problems from different perspectives. We, therefore, propose a workshop where successful techniques and development platforms are presented and jointly discussed, with the goal of sharing the most relevant information to finally overcome the existing challenges.