Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.

  

Back to basics: Advancing the state of brain-machine interfaces

Author(s):

J. DiGiovanna
Conference/Journal:

BioRoNZ: BioRobotics Network Zurich
Abstract:

Brain-machine interfaces create new pathways to allow the nervous system to control artificial devices. There has been active research in this area for decades by many groups around the world. However, clinical implementations have been limited by problems intrinsic to prior learning architectures. In this talk, I will introduce the current BMI control paradigm and explain the advantages of shifting to a state-based control scheme. This hierarchical control allows the brain to make ‘high-level’ decisions (e.g. walk) while lower-level controllers (e.g. spinal cord) manage the details of limb actuation. Identifying useful neuronal states can be a difficult task, but is possible via non-linear projections and reinforcement learning algorithms. Additionally, these state-based controllers allow co-adaptation between the artificial intelligence and the user. Such co-adaptation potentially will improve BMI controller robustness.

Year:

2010
Type of Publication:

(06)Talk
Supervisor:



No Files for download available.
% No recipe for automatically generating a BibTex entry for (06)Talk
Permanent link