Contact

Zhikun Wang

Address: Spemannstr. 38
72076 Tübingen
Room number: 237
Fax: +49 7071 601 552
E-Mail: zhikun.wang
Print page    
Picture of Wang, Zhikun

Zhikun Wang

Position: PhD Student  Unit: Alumni Schölkopf

Recent advances in sensors and algorithms allow for robots with improved perception abilities. However, effective perception alone may not be sufficient for human-robot interaction, since the robot's reaction should depend on understanding the human's intention. Hence, my research interests lie in the strategic level of human-robot interaction, which serves as a bridge between perception of human action and planning for reaction. On one side, the robot needs to infer the underlying intention of humans. On the other side, efficient planning for reaction can be achieved by utilizing motor skills with reactive policies learned to choose the right skill at the right time.

 

I have been developing and implementing machine learning algorithms for intention inference and learning reactive policies. I have chosen robot table tennis as a benchmark, as it is a sufficiently complex scenario for evaluation while intuition still allows interpreting the results. We have achieved promising experimental results, which exhibit their potentials in many other human-robot interaction scenarios.

 

See http://robot-learning.de/Team/ZhikunWang for more information.

Preferences: 
References per page: Year: Medium:

  
Show abstracts

Articles (4):

Zhang K Person, Wang Z Person, Zhang J and Schölkopf B Person (2014) On estimation of functional causal models: General results and application to post-nonlinear causal model ACM Transactions on Intelligent Systems and Technologies . accepted
Wang Z Person, Mülling K Person, Deisenroth M Person, Ben Amor H , Vogt D , Schölkopf B Person and Peters J Person (2013) Probabilistic movement modeling for intention inference in human-robot interaction International Journal of Robotics Research 32(7) 841-858.
pdf
Wang Z Person, Boularias A Person, Mülling K Person, Schölkopf B Person and Peters J Person (2013) Anticipatory Action Selection for Human-Robot Table Tennis . submitted
Wang Z Person, Deisenroth M Person, Zhang K Person, Boularias A Person, Schölkopf B Person and Peters J Person (2013) Hierarchical Gaussian Process Dynamics Models for Human Movement Analysis . submitted

Conference papers (6):

Zhang K Person, Schölkopf B Person, Muandet K Person and Wang Z Person (2013) Domain adaptation under Target and Conditional Shift In: Proceedings of The 30th International Conference on Machine Learning, Volume 28, (Ed) Sanjoy Dasgupta and David McAllester, 30th International Conference on Machine Learning (ICML 2013), 819–827.
pdf
Zhang K Person, Wang Z Person and Schölkopf B Person (2013) On estimation of functional causal models: Post-nonlinear causal model as an example First IEEE ICDM workshop on causal discovery.
pdf
Wang Z Person, Deisenroth M Person, Ben Amor H , Vogt D , Schölkopf B Person and Peters J Person (2012) Probabilistic Modeling of Human Movements for Intention Inference Robotics: Science and Systems (R:SS 2012), 8 pages. accepted
pdf
Wang Z Person, Lampert CH Person, Mülling K Person, Schölkopf B Person and Peters J Person (2011) Learning anticipation policies for robot table tennis (Ed) NM Amato, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), IEEE, Piscataway, NJ, USA, 332-337.
pdf
Wang Z Person, Boularias A Person, Mülling K Person and Peters J Person (2011) Balancing Safety and Exploitability in Opponent Modeling (Ed) Burgard, W. , D. Roth, Twenty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2011), AAAI Press, Menlo Park, CA, USA, 1515-1520.
pdf
Peters J Person, Kober J Person, Mülling K Person, Krömer O Person, Nguyen-Tuong D Person, Wang Z Person, Rodriguez Gomez M Person and Grosse-Wentrup M Person (2010) Learning as a key ability for Human-Friendly Robots 3rd Workshop for Young Researchers on Human-Friendly Robotics (HFR 2010), 1-2.

Export as:
BibTeX, XML, Pubman, Edoc