The task sounds simple: Program Sony AIBO robots to play soccer. We use RoboCup to investigate techniques for multi-robot collaboration, active sensing, and efficient state estimation. Our multi-model technique for ball tracking allows our robots to accurately track the ball and its interactions with the environment; even under the highly non-linear dynamics typically occuring during a soccer game. Our active sensing strategy is based on reinforcement learning. It takes into account which uncertainty has to be minimized at each point in time (for example, relative ball position uncertainty vs. robot location uncertainty).
Members of the 2004 RoboCup team
Undergraduates Griff Hazen and Paul Larpenteur with Dieter Fox at RoboCup-04 in Lisbon, Portugal.
Advisory members
- Cody Kwok
- Matthew Mohebbi
- Jeffrey Hanke
Former members
- David Azari
- Matthew Burkhart
- Jonathan Burns
- Erik Curre
- Zach Crisman
- Kaustubh Deshmukh
- Jonathan Dandy
- David Dunham
- David Grimes
- Jayant Madhavan
- Bill Pentney
- Nathan Ratliff
- Matt Richardson
- Aaron Shon
- Nicholas Stipanovich
- Pat Tressel
- Leonid Tsybert
- Steve Wolfman
General information:
Dieter Fox (email: fox@cs.washington.edu)
Technical support:
Brian Youngstrom (email: byoung@cs.washington.edu)
This research is funded in part under NSF CAREER Award 0093406.
- Our Robocup 2004 participation was sponsored by -
