The Indiana Experiment: Investigating the Role of Anticipation and Attention in a Dynamic Environment
We investigating the role of anticipation and attention in a dynamic environment in a number of large scale simulations of an agent that tries to negotiate a number of gates that continuously open and close. In particular we have looked at learning mechanisms that can predict the future positions of the gates and control strategies that will allow the agent to pass through the gates unharmed. The simulations reported below use the AARC architecture . This architecture combines a large number of different cognitive mechanisms. In Experiment 1, the task for the agent is to pass through a single gate and in Experiment 2, to pass through three successive gates. The results shows that the AARC architecture is flexible enough to handle very diverse situations. It is also somewhat surprising that linear predictors are sufficient in most cases.
KeywordsSafety Margin Trial Time Dynamic Object Local Goal Valid Trial
Unable to display preview. Download preview PDF.
- 1.Johansson, B.: Anticipation and Attention in Robot Control. PhD thesis, Lund University (2009)Google Scholar
- 2.Ball, D., Wyeth, G.: Modeling and exploiting behavior patterns in dynamic environments. In: IEEE/RSJ International Conference Intelligent on Robots and Systems, vol. 2, pp. 1371–1376 (2004)Google Scholar
- 3.Barakova, E.: Prediction of rapidly changing environmental dynamics for real time behavior adaptation using visual information. In: Würtz, L.M. (ed.) Proceedings of the 4th Workshop on Dynamic Perception, Bochum, Germany, pp. 147–152. IOS Press, Amsterdam (2002)Google Scholar
- 4.Sharifi, M., Mousavian, H., Aavani, A.: Predicting the future state of the robocup simulation environment: heuristic and neural networks approaches. In: IEEE International Conference on Systems, Man and Cybernetics, pp. 32–37. IEEE, Los Alamitos (2003)Google Scholar
- 5.Veloso, M., Stone, P., Bowling, M.: Anticipation as a key for collaboration in a team of agents: A case study in robotic soccer. In: Schenker, P.S., McKee, G.T. (eds.) Proceedings of SPIE Sensor Fusion and Decentralized Control in Robotic Systems II, Bellingham, vol. 3839, pp. 134–143 (1999)Google Scholar
- 7.Efe, M., Atherton, D.P.: Maneuvering target tracking with an adaptive kalman filter. In: Proceedings of the 37th IEEE Conference on Decision and Control, vol. 1 (1998)Google Scholar
- 9.Bar-Shalom, Y.: Recursive tracking algorithms: from the kalman filter to intelligent trackers for cluttered environment. In: Proceedings of IEEE International Conference on Control and Applications, ICCON 1989, pp. 675–680 (1989)Google Scholar
- 12.Johansson, B., Balkenius, C.: Prediction time in anticipatory systems. In: Pezzulo, G., Butz, M.V., Sigaud, O., Baldassarre, G. (eds.) ABiALS 2008, vol. 5499, pp. 283–300. Springer, Heidelberg (2009)Google Scholar
- 15.Johansson, B., Balkenius, C.: Learning to anticipate the movements of intermittently occluded objects. In: Schlesinger, M., Berthouze, L., Balkenius, C. (eds.) Eighth International Conference on Epigenetic Robotics, Lund University Cognitive Studies, vol. 139 (2008)Google Scholar
- 16.Prem, E., Hörtnagl, E., Dorffner, G.: Growing event memories for autonomous robots. In: Proceedings of the Workshop on Growing Artifacts that Live: Basic Principles and Future Trends (2002)Google Scholar