Adaptation and Robust Learningof Probabilistic Movement Primitives

Adaptation and Robust Learning of Probabilistic Movement Primitives

Abstract

Probabilistic representations of movement primitives open important new possibilities for machine learning in robotics. These representations are able to capture the variability of the demonstrations from a teacher as a probability distribution over trajectories, providing a sensible region of exploration and the ability to adapt to changes in the robot environment. However, to be able to capture variability and correlations between different joints, a probabilistic movement primitive requires the estimation of a larger number of parameters compared to their deterministic counterparts, that focus on modeling only the mean behavior. In this paper, we make use of prior distributions over the parameters of a probabilistic movement primitive to make robust estimates of the parameters with few training instances. In addition, we introduce general purpose operators to adapt movement primitives in joint and task space. The proposed training method and adaptation operators are tested in a coffee preparation and in robot table tennis task. In the coffee preparation task we evaluate the generalization performance to changes in the location of the coffee grinder and brewing chamber in a target area, achieving the desired behavior after only two demonstrations. In the table tennis task we evaluate the hit and return rates, outperforming previous approaches while using fewer task specific heuristics.

Robot Learning, Robot Motion

References

Sebastian Gomez-Gonzalez joined the MPI for Intelligent Systems in 2015. He is also affiliated with Technische Universitaet Darmstadt as an external member. His research interests include machine learning, generative models for motion and reinforcement learning. Sebastian received his MSc and BSc degree in computer science from Universidad Tecnologica de Pereira. He obtained the “Best in Education” award for obtaining the best score in Colombia in the standardized test for computer science in 2011.

Gerhard Neumann is a Professor of Robotics & Autonomous Systems in College of Science of Lincoln University. Before coming to Lincoln, he has been an Assistant Professor at the TU Darmstadt. Before that, he was Post-Doc and Group Leader at the Intelligent Autonomous Systems Group (IAS) also in Darmstadt. Gerhard obtained his Ph.D. under the supervision of Prof. Wolfgang Mass at the Graz University of Technology. Gerhard has a strong publication record both in machine learning venues (e.g., NIPS, ICML) and in the robotics community (e.g., ICRA, IROS). He has been active at bringing researchers from both fields together by organizing multiple workshops at the frontier between these two fields, e.g., on reinforcement learning and motor skill acquisition. He served in the senior program committee of some of the most prestigious conferences in artificial intelligence including NIPS and AAAI.

Bernhard Schölkopf ’s scientific interests are in machine learning and causal inference. He has applied his methods to a number of different application areas, ranging from biomedical problems to computational photography and astronomy. Bernhard has researched at AT&T Bell Labs, at GMD FIRST, Berlin, and at Microsoft Research Cambridge, UK, before becoming a Max Planck director in 2001. He is a member of the German Academy of Sciences (Leopoldina), and has received the J.K. Aggarwal Prize of the International Association for Pattern Recognition, the Max Planck Research Award (shared with S. Thrun), the Academy Prize of the Berlin-Brandenburg Academy of Sciences and Humanities, and the Royal Society Milner Award.

Jan Peters is a full professor (W3) for Intelligent Autonomous Systems at the Computer Science Department of the Technische Universitaet Darmstadt and at the same time a senior research scientist and group leader at the Max-Planck Institute for Intelligent Systems, where he heads the interdepartmental Robot Learning Group. Jan Peters has received the Dick Volz Best 2007 US PhD Thesis Runner-Up Award, the Robotics: Science & Systems - Early Career Spotlight, the INNS Young Investigator Award, and the IEEE Robotics & Automation Society’s Early Career Award. Recently, he received an ERC Starting Grant. In 2019, Jan Peters was appointed IEEE Fellow. Jan Peters has studied Computer Science, Electrical, Mechanical and Control Engineering at TU Munich and FernUni Hagen in Germany, at the National University of Singapore (NUS) and the University of Southern California (USC). He has received four Master’s degrees in these disciplines as well as a Computer Science PhD from USC. Jan Peters has performed research in Germany at DLR, TU Munich and the Max Planck Institute for Biological Cybernetics (in addition to the institutions above), in Japan at the Advanced Telecommunication Research Center (ATR), at USC and at both NUS and Siemens Advanced Engineering in Singapore.

Comments 0
Request Comment
You are adding the first comment!
How to quickly get a good reply:
  • Give credit where it’s due by listing out the positive aspects of a paper before getting into which changes should be made.
  • Be specific in your critique, and provide supporting evidence with appropriate references to substantiate general statements.
  • Your comment should inspire ideas to flow and help the author improves the paper.

The better we are at sharing our knowledge with each other, the faster we move forward.
""
The feedback must be of minimum 40 characters and the title a minimum of 5 characters
   
Add comment
Cancel
Loading ...
408776
This is a comment super asjknd jkasnjk adsnkj
Upvote
Downvote
""
The feedback must be of minumum 40 characters
The feedback must be of minumum 40 characters
Submit
Cancel

You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description