Back to list

Yanlong Huang

Post Doc

Research Line

Advanced Robotics

Center

IIT Central Research Labs Genova

Contacts

yanlong.huang@iit.it

Social profiles

github

About

I am interested in imitation learning, optimal control, reinforcement learning, motion planning and their applications to robotic systems. Plese see my research experience as follows:

- Italian Institute of Technology, Genova, Italy (2017-present) 
Develop novel movement primitives for imitation learning as well as reinforcement learning associated with high-dimensional states/actions.

- Max-Planck Institute for Intelligent Systems, Tübingen, Germany (2013-2016) 
Developed regression and reinforcement learning algorithm, applied them to an anthropomorphic robot table tennis. Meanwhile, a more general robot table tennis setup was developed.

- Institute of Automation, Chinese Academy of Sciences, Beijing, China (2010-2013) 
Formulated the learning of a robot table tennis as a data-driven learning problem. Besides, the integration of human knowledge and memory-based learning approaches was developed. 

Selected Publications

  1. Y. Huang and D. G. Caldwell. A linearly constrained nonparametric framework for imitation learningarXiv:1909.07374, 2019.

  2. Y. Huang, F. J. Abu-Dakka, J. Silvério and D. G. Caldwell. Towards orientation learning and adaptation in Cartesian spacearXiv:1907.03918, 2019.

  3. J. Silvério, Y. Huang, F. J. Abu-Dakka, L. Rozo, D. G. Caldwell. Uncertainty-aware imitation learning using kernelized movement primitives, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Macau, China, 2019. [video]

  4. Y. Huang, L. Rozo, J. Silvério, and D. G. Caldwell. Kernelized movement primitives, International Journal of Robotics Research (IJRR), 38(7):833-852, 2019. [video]

  5. Y. Huang, F. J. Abu-Dakka, J. Silvério and D. G. Caldwell. Generalized orientation learning in robot task spaceIEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, pp. 2531-2537, 2019. [video]

  6. Y. Huang, L. Rozo, J. Silvério and D. G. Caldwell. Non-parametric imitation learning of robot motor skillsIEEE International Conference on Robotics and Automation (ICRA), Montreal, Canada, pp. 5266-5272, 2019.

  7. J. Silvério, Y. Huang, L. Rozo, and D. G. Caldwell. An uncertainty-aware minimal intervention control strategy learned from demonstrations, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, pp. 6065-6071, 2018. [video]

  8. J. Silvério, Y. Huang, L. Rozo, S. Calinon, and D. G. Caldwell. Probabilistic learning of torque controllers from kinematic and force constraints, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, pp. 6552-6559, 2018. [video]

  9. Y. Huang, J. Silvério, and D. G. Caldwell. Towards minimal intervention control with competing constraintsIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, pp. 733-738, 2018.

  10. Y. Huang, J. Silvério, L. Rozo, and D. G. Caldwell. Generalized task-parameterized skill learning, IEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, pp. 5667-5674, 2018. [video]

  11. Y. Huang, J. Silvério, L. Rozo, and D. G. Caldwell. Hybrid probabilistic trajectory optimization using null-space explorationIEEE International Conference on Robotics and Automation (ICRA), Brisbane, Australia, pp. 7226-7232, 2018. [video]

  12. Y. Huang, D. Büchler, O. Koc, B. Schölkopf, and J. Peters. Jointly learning trajectory generation and hitting point prediction in robot table tennisIEEE International Conference on Humanoid Robots (HUMANOIDS), Cancun, Mexico, pp. 650-655, 2016. [video]

  13. Y. Huang, B. Schölkopf, and J. Peters. Learning optimal striking points for a ping-pong playing robotIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hamburg, Germany, pp. 4587-4592, 2015.

  14. Y. Huang, D. Xu, M. Tan, and H. Su. Adding active learning to LWR for ping-pong playing robotIEEE Transactions on Control Systems Technology (TCST), 21(4):1489-1494, 2013. [video]

  15. Y. Huang, D. Xu, M. Tan, and H. Su. Trajectory prediction of spinning ball for ping-pong player robotIEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), San Francisco, USA, pp. 3434-3439, 2011.

INFORMATIVA SUI COOKIES

Il sito web di IIT utilizza i seguenti tipi di cookies: di navigazione/sessione, analytics, di funzionalità e di terze parti. L'utente può scegliere di acconsentire all'uso dei cookies e accedere al sito. Facendo click su "Maggiori Informazioni" verrà visualizzata l'informativa estesa sui tipi di cookies utilizzati e sarà possibile scegliere se autorizzarli durante la navigazione sul sito.
Maggiori Informazioni
Accetta e chiudi