Modeling a robotic arm with conformal geometric algebra in a brain-computer interface

Abstract

In this paper, a conformai geometric algebra model is used to solve the inverse kinematics of a manipulator robot in a brain-computer interface (BCI) based on electroencephalography (EEG) measurements. The model is constructed in terms of simple algebraic elements such as lines, circles and spheres. The process to construct the model is explained in detail, as well as the design of the BCI. The results show that conformal geometric algebra allows to solve the inverse kinematics of a manipulator robot with precision. Furthermore, preliminary results using real EEG data from two naive volunteers showed good rates in controlling the BCI. Our current work will contribute to the design of more complex interfaces due to its low computational load in comparison to traditional inverse kinematics solutions.