13 May 2024
Brain Machine Interfaces (BMIs) facilitate the translation of neural activity into actionable commands, enabling individuals to control external devices and systems through their thoughts and attention. However, despite remarkable advancements in clinical settings, integrating BMIs into non-clinical applications like robot motion control remains difficult. Specifically, EEG-based motor imagery systems are still error-prone, posing safety risks when rigid robots operate near humans. In rigid robotics, this has been addressed by relying on force-based (i.e., impedance) control and by making the robot’s behaviour more predictable.
In this work, EMERGE partners from Delft University of Technology and collaborators present an alternative pathway towards safe and effective operation by combining wearable EEG with physically embodied safety in soft robots. This way, risks can be mitigated, and more natural interactions with an unstructured environment can be achieved by relying on structural compliance.
The authors introduce and test a pipeline that allows a user to move a soft robot's end effector in real time via brain waves that are measured by as few as three EEG channels. A robust motor imagery algorithm interprets the user's intentions to move the position of a virtual attractor to which the end effector is attracted, thanks to a new Cartesian impedance controller.
They specifically focus here on planar soft robot-based architected metamaterials, which require the development of a novel control architecture to deal with the peculiar nonlinearities - e.g., non-affinity in control. They preliminarily but quantitatively evaluate the approach on the task of setpoint regulation, observing that the user reaches the proximity of the setpoint in 66% of steps and that for successful steps, the average response time is 21.5s. The group also demonstrates the execution of simple real-world tasks involving interaction with the environment, which would be extremely hard to perform if it were not for the robot's softness.
Read the paper in the link below.
More Information
