Logic-based robot control in highly dynamic domains

In this paper, we present the robot programming and planning language Readylog, a Golog dialect, which was developed to support the decision making of robots acting in dynamic real-time domains, such as robotic soccer. The formal framework of Readylog, which is based on the situation calculus, features imperative control structures such as loops and procedures, allows for decision-theoretic planning, and accounts for a continuously changing world. We developed high-level controllers in Readylog for our soccer robots in RoboCup’s Middle-size league, but also for service robots and for autonomous agents in interactive computer games. For a successful deployment of Readylog on a real robot it is also important to account for the control problem as a whole, integrating the low-level control of the robot (such as localization, navigation, and object recognition) with the logic-based high-level control. In doing so, our approach can be seen as a step towards bridging the gap between the fields of robotics and knowledge representation.