Stanley’s Brain, An overview of Stanford’s winning entry to the Darpa Grand Challenge

The DARPA Grand Challenge was a race with a $2M prize for the first robot that could travel 132 miles of unrehearsed desert road in under 10 hours. Stanley, Stanford’s entry, won this historic race in 6:53 minutes averaging 19.1 miles an hour. I will give an overview of the functional systems that made up Stanley’s brain focusing some on where machine learning was used illustrating with filmstrips from the race. I will describe some of the software tools used, especially the Open Source Computer Vision Library (OpenCV http://www.intel.com/technology/computing/opencv/index.htm) and will end with some speculations on robotic and biological vision.

Presenter(s)

Gary Rost Bradski Principle Engineer and manager of the Machine Learning group for Intel Research with a joint appointment as consulting Professor at Stanford. His basic goal is to enable and accelerate AI internally and externally. Some external tools he started for this are the Probabilistic Network Library (PNL) and the Open Source Computer Vision Library (OpenCV) available open, for free on Source Forge. The vision library is used around the world and has become a notable part of the commercial Intel performance library (IPP) products. A statistical machine learning library (MLL) is for early 2006.

Gary received a B.S. degree from U.C. Berkeley and a Ph.D. in Cognitive and Neural Systems (mathematical modeling of biological perception) in May, 1994 from Boston University Center for Adaptive Systems. Gary has worked in the fields of: proximity security systems; medical electronics; computerized EEG; and as a quantitative analyst at First Union´s Derivatives Trading Group. Gary also worked as a consultant to the medical electronics industry (NeuroSoft) and in assembly line automation.