Learning and generalization of complex tasks from unstructured demonstrations

  title={Learning and generalization of complex tasks from unstructured demonstrations},
  author={Scott Niekum and Sarah Osentoski and George Konidaris and Andrew G. Barto},
  journal={2012 IEEE/RSJ International Conference on Intelligent Robots and Systems},
We present a novel method for segmenting demonstrations, recognizing repeated skills, and generalizing complex tasks from unstructured demonstrations. This method combines many of the advantages of recent automatic segmentation methods for learning from demonstration into a single principled, integrated framework. Specifically, we use the Beta Process Autoregressive Hidden Markov Model and Dynamic Movement Primitives to learn and generalize a multi-step task on the PR2 mobile manipulator and to… CONTINUE READING
Highly Cited
This paper has 106 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 75 extracted citations

WMRA skill learning through segmentation of demonstration

2017 2nd International Conference on Advanced Robotics and Mechatronics (ICARM) • 2017
View 7 Excerpts
Highly Influenced

Imitation Learning for Mobile Robot Control

Michael Krawez, Minija Tamosiunaite
View 4 Excerpts
Highly Influenced

107 Citations

Citations per Year
Semantic Scholar estimates that this publication has 107 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 26 references

Joint modeling of multiple related time series via the beta process

E. Fox, E. Sudderth, M. Jordan, A. Willsky
arXiv:1111.4226, November 2011. • 2011
View 2 Excerpts

Skill learning and task outcome prediction for manipulation

2011 IEEE International Conference on Robotics and Automation • 2011
View 1 Excerpt

Incremental learning of subtasks from unsegmented demonstration

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems • 2010
View 2 Excerpts

Similar Papers

Loading similar papers…