This project investigates the feasibility of using native parallel languages for the construction of effective robotic controllers and the evolution of new controllers using genetic programming techniques. Our research will proceed in two phases.
- We will immerse ourselves in a specific, real world robotics task: finding and extinguishing a candle within a physical model of a home environment for the Trinity College Fire Fighting Home Robot Contest. This competition attracts teams from around the country to create robots capable of responding to an alarm and extinguishing a candle in a maze that resembles a house.
- We will transition from hand-crafted controllers making use of occam and the subsumption architecture to the use of layered control systems that we evolve using genetic algorithmic techniques. Using our experience with the TCFFHRC, we will evolve new controllers through the application of genetic programming by creating a virtual representation of the TCFFHRC within the USARSim environment. Our intention is to qualify and quantify the limits and benefits of this approach, and lay a potential foundation for evolving robotic controllers to the more complex (and true-to-life) RoboCupRescue competitions.
This project is a joint collaboration between Kathryn Hardey ’11 and Eren Corapcioglu ’11 (Centenary College) and Molly Mattis ’11 (Allegheny College) along with their research advisors, Mark Goadrich (Centenary) and Matt Jadud (Allegheny). The work is funded by the Collaborative Research Experiences for Undergraduates programme.