ROBOCHAMPION: After battling it out to win two campus robot competitions when he was a student, Research Associate Josh de Leeuw ’08 recently took his game to an international level, placing second in the worldwide programming competition, RoboChamps Urban Challenge, sponsored by KIA Motors and Microsoft. Using Microsoft’s free Robotics Developer Studio software, robotics enthusiasts around the world were charged with pitting robots against one another in six independent challenges. De Leeuw, who works in Vassar’s Interdisciplinary Robotics Research Laboratory, received a $10,000 cash prize for successfully programming a simulated robot car, which could drive autonomously in a 3-D virtual city. We touched base with the former cognitive science major to find out more about his work and the role robots play in our lives.
Tell me more about the competition?
In the simulated city, the idea was to go from a starting point past a series of checkpoints and then park at the end. My solution was to keep it simple, but make it work. I wrote a program that made the car stay on the road by tracking the city’s curbs, stop at intersections by finding the crosswalks, and obey traffic laws by identifying the traffic lights.
How long did it take you to program the car?
It took me about two days because I was able to find a simple way to generate what looks like a complex behavior. One of the things I learned in cognitive science classes was that a simple mechanism can be responsible for complex behaviors, and so it was just a matter of applying what I had learned to a real world problem.
How did you originally become interested in cog sci?
At first, I wasn’t sure what I wanted to do, so I liked how Vassar let me come in and explore. I took a cog sci course and loved it. Then, when I started learning robotics, I was hooked. I had always been interested in computer science and programming, but had never taken a class in it. This was a way to merge all the diverse interests I had.
How did your classes prepare you for working in the field?
Between URSI [the Undergraduate Research Summer Institute] and working with a small department as an undergraduate, I was able to do any research I wanted on my thesis and have access to all the equipment in the lab. Most grad students don’t get to touch that equipment right away, and they have a faculty member who’s steering them. By senior year, I was able to go off and do what I wanted. I’ve been working with Ken Livingston [professor of psychology] for the most part, but he encouraged me to test my own ideas to see if they worked. And it turns out they do.
Why is this research so important?
I think there is a potential for good research to come out of this. Robots are going to play a bigger role in our society in the coming decades, and they help us find out about who we are and how we work. I like to walk that boundary between creating new technologies and studying human learning using robots.