Generalized Virtual Fixtures for Shared-Control Grasping in Brain-Machine Interfaces.

Abstract

In brain-machine interface (BMI) prosthetic systems, recordings of brain activity are used to control external devices such as computers or robots. BMI systems that have shown the highest fidelity of control use neural signals recorded directly from microelectrodes in the brain to control upper-limb prostheses. These have progressed from allowing control of 2 and 3 dimensional movement of a cursor on a computer screen [1], [2] to control of robot arms in first four [3], [4] and more recently seven degrees-of-freedom (DoF) (Fig. 1) [5], [6]. These types of systems require methods to train users to control large numbers of DoF simultaneously. In this paper we present a new method for shared-control guidance. This method of "Positive-Span" Virtual Fixturing extends the concept of Virtual Fixtures to guide both translational and rotational DoF of a brain-controlled robot hand toward whole sets of robot poses that would allow an object to be grasped. This system was used to successfully train monkeys to operate the 7-DoF BMI [5], leading directly to the simplified system of "ortho-impedance" used to guide human subject BMI control in a similar experiment [6].