Towards Intelligent Brain-Controlled Body Augmentation Robotic Limbs

Abstract

Supernumerary Robotic Limbs (SRL) are body augmentation robotic devices that will extend the physical capabilities of humans in an unprecedented way. Researchers have explored the possibility to control SRLs in diverse ways - from manual operation through a joystick to myoelectric signals from muscle impulses - but the ultimate goal is to be able to control them with the brain. Brain-machine interface systems (BMI) have allowed the control of prosthetics and robotic devices using brainwaves alone, but the low number of brain-based commands that can be decoded does not allow an SRL to achieve a high number of actions. For this reason, in this paper, we present an intelligent brain-controlled SRL that has context-aware capabilities in order to complement BMI-based commands and increase the number of actions that it can perform with the same BMI-based command. The proposed system consists of a human-like robotic limb that can be activated (i.e. grasp action) with a non-invasive EEG-based BMI when the human operator imagines the action. Since there are different ways that the SRL can perform the action (i.e. different grasping configurations) depending on the context (i.e. type of the object), we provided vision capabilities to the SRL so it can recognize the context and optimize its behavior in order to match the user intention. The proposed hybrid BMI-SRL system opens up the possibilities to explore more complex and realistic human augmentation applications.