Vehicle Full-State Estimation and Prediction System Using State Observers
Kelvin is a four-wheeled land-based robotics research platform in development at the Machine Intelligence Lab at the University of Florida. The purpose of this project is to design a robust control and navigation system capable of both autonomous and semi-autonomous operation. The vehicle is about the size of a golf cart and is designed to operate on moderately flat terrain. It is highly agile with its adapted Ackerman's steering system, and can sustain speeds greater than 10mph. Kelvin is an electric vehicle carrying independent power supplies for both its motors and computer systems. The controlling onboard computer runs Linux and coordinates the operation of the entire system. It is interfaced directly to the actuation computer and the sensors. Two cameras, a digital compass, and global positioning system are the primary navigational sensors.