Date of Award

Summer 7-2012

Access Type

Thesis - Open Access

Degree Name

Master of Science in Mechanical Engineering

Department

Mechanical Engineering

Committee Chair

Brian Butka

First Committee Member

Darris L. White

Second Committee Member

Charles F. Reinholtz

Abstract

Mimicking real-time human motion with a low cost solution has been an extremely difficult task in the past but with the release of the Microsoft Kinect motion capture system, this problem has been simplified. This thesis discusses the feasibility and design behind a simple robotic skeleton that utilizes the Kinect to mimic human movements in near real-time. The goal of this project is to construct a 1/3-scale model of a robotically enhanced skeleton and demonstrate the abilities of the Kinect as a tool for human movement mimicry. The resulting robot was able to mimic many human movements but was mechanically limited in the shoulders. Its movements were slower then real-time due to the inability for the controller to handle real-time motions. This research was presented and published at the 2012 SouthEastCon. Along with this, research papers about the formula hybrid accumulator design and the 2010 autonomous surface vehicle were presented and published.

Share

COinS