Technical Note: \cal Q-Learning
Machine Learning
Artificial intelligence: a new synthesis
Artificial intelligence: a new synthesis
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Low Latency Color Segmentation on Embedded Real-Time Systems
DIPES '02 Proceedings of the IFIP 17th World Computer Congress - TC10 Stream on Distributed and Parallel Embedded Systems: Design and Analysis of Distributed Embedded Systems
ICAS '08 Proceedings of the Fourth International Conference on Autonomic and Autonomous Systems
Hi-index | 0.00 |
In this paper we introduce an infrastructure for investigating Organic Computing principles such as self-optimization and self-organization in real-world scenarios based on a heterogeneous society of robots. This infrastructure, the R3PB-Workbench (Remote Real Robots at the University of Paderborn), provides a controlled environment for conducting real-world multi robot experiments, while relieving the developer from common problems like getting a global view of the entire environment and self-localization within this environment. In addition, it provides a communication layer that hides the heterogeneity of the controlled robot types and also facilitates access to each robot's subjective view. Currently we provide three types of mobile robots with different size and capabilities. Since the workbench is easily customizable, it supports the integration of additional types of robots. Hence, the degree of heterogeneity of the robot group conducting the experiments in the scope of our real-world scenario can be modified as needed. Furthermore, we elaborated a multi-robot game as an illustrative real-world scenario, which on the one hand allows for sophisticated scientific investigations and on the other hand is also appealing for an audience, even with little technical background.