home · mobile · calendar · defenses · 2010-2011 · 

Thesis Defense - Krunic

Scalable Software Control of a Million-Element Cyber-Physical Systems Using Graphics Processing Unit
Computer Science PhD Candidate

Cyber-Physical Systems consisting of hundreds of thousands of elements are emerging, with even bigger systems likely to emerge in the immediate future. However, in order for emerging and reasonably anticipated systems to be practical, problems of the software control of million-element Cyber-Physical Systems need to be addressed.

This PhD dissertation describes the software control algorithms necessary for the realization of million-element Cyber-Physical Systems. This work will show that Graphics Processing Unit (GPU) based control of such Cyber-Physical Systems provides significant benefits both in the form of fast control of large numbers of elements as well as in terms of providing a viable and scalable option by using inexpensive, off-the-shelf hardware. GPU control will be shown to be particularly well suited for the combination of the virtual environment with the manipulation of the physical shape of the environment in which user resides.

It is anticipated that million-element Cyber-Physical Systems will emerge where physical objects and terrains could be rendered via an assembly of a large number of computer controlled micro-elements. Some examples of such systems include Physically Rendered Environments (PRE), various Microelectromechanical Systems (MEMS) and Catoms. In principle, each of these systems is envisioned as consisting of a large number of elements, potentially millions of them, which all need to be coordinated.

These previously mentioned systems have great potential in the area of the assistive technologies for visually impaired people. The concept provides for tactile and haptic feedback for users by adding tactile feedback to physically rendered representations of the virtual environment as well as the ability of the user to move inside that environment. Control of Microelectromechanical systems (MEMS) based assistive devices would be of particular help to people with visual disabilities.

As hardware is by its nature expensive to construct, it is important for the feasibility of these systems that we resolve in advance the conceptual software problems relating to the control of million elements based Cyber-Physical Systems.

The main contributions of this PhD dissertation consist of novel algorithms that utilize existing off-the-shelf GPUs to control the Constrained Motion Cyber-Physical Systems comprised of multi million element systems, and demonstrate the feasibility and scalability of such control algorithms. It would be shown how both control and coordination of the elements can be achieved, while at the same time accounting for the physical limitations of the Cyber-Physical System elements. The approach presented here generalizes to ability to control the position of the actuation elements as well as additional physical attributes of the system such as temperature, perceived elasticity of the actuating elements, slipperiness of the ground in the large scale systems, etc. We describe how to further extend our approach to deal with existing Cyber-Physical Systems like Catoms, CirculaFloor and MEMS based tactile devices, as well as describe an approach to addressing the physical safety of the user in large scale Cyber-Physical Systems.

Committee: Richard Han, Associate Professor (Chair)
Clayton Lewis, Professor
Willem (Vlakkies) Schreüder, Principia Mathematica, Inc.
Yung-Cheng Lee, Department of Mechanical Engineering
Randolph (Stick) Ware, Radiometrics Corporation
Department of Computer Science
University of Colorado Boulder
Boulder, CO 80309-0430 USA
May 5, 2012 (14:20)