ROBOCUP-97 SMALL-ROBOT WORLD CHAMPION TEAM

Robotic soccer is a challenging research domain that involves multiple agents that need to collaborate in an adversarial environment to achi eve specific objectives. In this article, we describe CMUNITED, the te am of small robotic agents that we developed to enter the RoboCup-97 c ompetition. We designed and built the robotic agents, devised the appr opriate vision algorithm, and developed and implemented algorithms for strategic collaboration between the robots in an uncertain and dynami c environment. The robots can organize themselves in formations, hold specific roles, and pursue their goals. In game situations, they have demonstrated their collaborative behaviors on multiple occasions. We p resent an overview of the vision-processing algorithm that successfull y tracks multiple moving objects and predicts trajectories. The articl e then focuses on the agent behaviors, ranging from low-level individu al behaviors to coordinated, strategic team behaviors. CMUNITED won th e RoboCup-97 small-robot competition at the Fifteenth International Jo int Conference on Artificial Intelligence in Nagoya, Japan.