Michael Beetz and Thorsten Belker

Learning Structured Reactive Navigation Plans from Excecuting MDP Navigation Policies

Proceedings of the Second International Cognitive Robotics Workshop

---

Abstract

Autonomous robots, such as robot office couriers, need navigation routines that support flexible task execution and effective action planning. This paper describes XfrmLearn, a system that learns structured symbolic navigation plans. Given a navigation task, XfrmLearn learns to structure continuous navigation behavior and represents the learned structure as compact and transparent plans. The structured plans are obtained by starting with monolithic default plans that are optimized for average performance and adding subplans to improve the navigation performance for the given task. Compactness is achieved by incorporating only subplans that achieve significant performance gains. The resulting plans support action planning and opportunistic task execution. XfrmLearn is implemented and extensively evaluated on an autonomous mobile robot.

---

Download

Full paper [.pdf] (361 kB)

---

Bibtex

@InProceedings{Beetz00CR,
  author =       {M. Beetz and T. Belker},
  title =        {Learning Structured Reactive Navigation Plans from Executng MDP policies},
  booktitle =    {Proceedings of the Second International Cognitive Robotics Workshop},
  OPTcrossref =  {},
  OPTkey =       {},
  OPTpages =     {},
  year =         {2000},
  OPTeditor =    {},
  OPTvolume =    {},
  OPTnumber =    {},
  OPTseries =    {},
  OPTaddress =   {},
  OPTmonth =     {},
  OPTorganization = {},
  OPTpublisher = {},
  OPTnote =      {},
  OPTannote =    {}
}