Training on the Job — Collecting Experience with Hierarchical Hybrid Automata

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4667)


We propose a novel approach to experience collection for autonomous service robots performing complex activities. This approach enables robots to collect data for multiple learning problems at a time, abstract it and transform it into information specific to the learning tasks and thereby speeding up the learning process. The approach is based on the concept of hierarchical hybrid automata, which are used as expressive representational mechanisms that allow for the specification of these experience-related capabilities independent of the program itself.


Learning Task Reactive Plan Manipulation Task Experience Acquisition Meaningful Learning Experience 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    McDermott, D.: A reactive plan language. Technical report, Yale University, Computer Science Dept. (1993)Google Scholar
  2. 2.
    Kirsch, A., Beetz, M.: Combining learning and programming for high-performance robot controllers. In: Autonome Mobile Systeme (2005)Google Scholar
  3. 3.
    Kirsch, A., Schweitzer, M., Beetz, M.: Making robot learning controllable: A case study in robot navigation. In: Proceedings of the ICAPS Workshop on Plan Execution: A Reality Check (2005)Google Scholar
  4. 4.
    Beetz, M., Kirsch, A., Müller, A.: RPL-LEARN: Extending an autonomous robot control language to perform experience-based learning. In: AAMAS. 3rd International Joint Conference on Autonomous Agents & Multi Agent Systems (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  1. 1.Technische Universität München 

Personalised recommendations