YODA - THE YOUNG OBSERVANT DISCOVERY AGENT

The YODA Robot Project at the University of Southern California/Inform ation Sciences Institute consists of a group of young researchers who share a passion for autonomous systems that can bootstrap its knowledg e from real environments by exploration, experimentation, learning, an d discovery. Our goal is to create a mobile agent that can autonomousl y learn from its environment based on its own actions, percepts, and m issions. Our participation in the Fifth Annual AAAI Mobile Robot Compe tition and Exhibition, held as part of the Thirteenth National Confere nce on Artificial Intelligence, served as the first milestone in advan cing us toward this goal. YODA's software architecture is a hierarchy of abstraction layers, ranging from a set of behaviors at the bottom l ayer to a dynamic, mission-oriented planner at the top. The planner us es a map of the environment to determine a sequence of goals to be acc omplished by the robot and delegates the detailed executions to the se t of behaviors at the lower layer. This abstraction architecture has p roven robust in dynamic and noisy environments, as shown by YODA's per formance at the robot competition.