Qualitative Velocity and Ball Interception
- 460 Downloads
In many approaches for qualitative spatial reasoning, navigation of an agent in a more or less static environment is considered (e.g. in the double-cross calculus ). However, in general, real environment are dynamic, which means that both the agent itself and also other objects and agents in the environment may move. Thus, in order to perform spatial reasoning, not only (qualitative) distance and orientation information is needed (as e.g. in ), but also information about (relative) velocity of objects (see e.g. ). Therefore, we will introduce concepts for qualitative and relative velocity: (quick) to left, neutral, (quick) to right. We investigate the usefulness of this approach in a case study, namely ball interception of simulated soccer agents in the RoboCup . We compare a numerical approach where the interception point is computed exactly, a strategy based on reinforcement learning, a method with qualitative velocities developed in this paper, and the naïve method where the agent simply goes directly to the actual ball position.
Keywordscognitive robotics multiagent systems spatial reasoning
Unable to display preview. Download preview PDF.
- 2.Johan de Kleer and Daniel G. Bobrow. Qualitative reasoning with higher-order derivatives. In Proceedings of the American National Conference on Artificial Intelligence (AAAI-84), pages 86–91, 1984. Reprint in Daniel S. Weld and Johan D. Kleer (eds.), Readings in Qualitative Reasoning about Physical Systems, Morgan Kaufmann, San Francisco, 1990.Google Scholar
- 3.Ehsan Foroughi, Frederik Heintz, Spiros Kapetanakis, Kostas Kostiadis, Johann Kummeneje, Itsuki Noda, Oliver Obst, Pat Riley, Timo Steffens, and USTC9811 Group. RoboCup Soccer Server User Manual (for Soccer Server Version 7.06 and later), 2001.Google Scholar
- 6.Jan Murray, Oliver Obst, and Frieder Stolzenburg. Towards a logical approach for soccer agents engineering. In Peter Stone, Tucker Balch, and Gerhard Kraetzschmar, editors, RoboCup 2000: Robot Soccer World Cup IV, LNAI 2019, pages 199–208. Springer, Berlin, Heidelberg, New York, 2001.CrossRefGoogle Scholar
- 7.Alexandra Musto, Klaus Stein, Andreas Eisenkolb, Thomas Rofer, Wilfried Brauer, and Kerstin Schill. From motion observation to qualitative motion representation. In Christian Freksa, Wilfried Brauer, Christopher Habel, and Karl F. Wender, editors, Spatial Cognition II, LNCS 1849, pages 115–126. Springer, Berlin, Heidelberg, New York, 2000.CrossRefGoogle Scholar
- 9.Martin Riedmiller, Artur Merke, D. Meier, A. Hoffmann, A. Sinner, O. Thate, C. Kill, and R. Ehrmann. Karlsruhe Brainstormers-a reinforcement learning way to robotic soccer. In Peter Stone, Tucker Balch, and Gerhard Kraetzschmar, editors, RoboCup 2000: Robot Soccer World Cup IV, LNAI 2019, pages 367–372. Springer, Berlin, Heidelberg, New York, 2001.CrossRefGoogle Scholar
- 10.Peter Stone et al. Robocup-2000: The fourth robotic soccer world championships. AI magazine, 22(1):11–38, 2001.Google Scholar
- 11.Peter Stone and David McAllester. An architecture for action selection in robotic soccer. In Fifth International Conference on Autonomous Agents, 2001.Google Scholar