Julen Urain De Jesus

Quick Info

Research Interests

Probabilistic Modelling, Stochastic Dynamical Systems, Generative Models, Representation Learning

More Information

Google Citations

Contact Information

Mail. Julen Urain De Jesus
TU Darmstadt, FG IAS,
Hochschulstr. 10, 64289 Darmstadt
Office. Room E225, Building S2|02

Julen joined the Intelligent Autonomous Systems Group at TU Darmstadt as a Ph.D. researcher in January 2019. Julen received his MS in Automatic Control and Robotics From UPC (Barcelona) in November 2017. Julen has gained a lot of knowledge in machine learning and robotics from different institutions. He developed his master thesis in BioRob lab in EPFL(Laussane) under the supervision of Auke Ijspeert and Jessica Lanini, He did an internship in the first edition of Deep Learning and Robotics Challenge (DLRC) in VW Data:Lab (Munich) and for the last year from December 2017 to December 2018 He has worked as a robotics researcher in IK4-Tekniker (Eibar).

Research Topic

My main research line is in the integration of machine learning algorithms to learn complex manipulation skills. During the Ph.D., I am looking for new ways of representing the environment and policies, following probabilistic models. It is expected that better models for representing them will improve the prediction, classification, and generation of motion applied in several fields from Imitation Learning to Human-Robot Interaction. In my thesis, I study the integration of Generative Modelling methods, Energy Based Models (EBM), Normalizing Flows with Robotics theory (Stability, Riemannian Geometry, Safety) to integrate in a smart way generative modelling methods into robotics and learn complex manipulation tasks.

Research Interest

Machine Learning

Probabilistic Modelling, Generative Models, Energy Based Models, Normalizing Flows, Score Based Models

Robotics and Control

Stochastic Dynamical Systems, Stability, Trajectory Optimization, Model Predictive Control, Reactive Motion Generation

Robot Learning

Inverse Reinforcement Learning, Imitation Learning, cost learning

Key References

  1. Urain, J.; Li, A.; Liu, P.; D'Eramo, C.; Peters, J. (2021). Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning, Robotics: Science and Systems (RSS).   Download Article [PDF]   BibTeX Reference [BibTex]
  2. Urain, J.; Tateo, D.; Ren, T.; Peters, J. (2020). Structured policy representation: Imposing stability in arbitrarily conditioned dynamic systems, NeurIPS 2020, 3rd Robot Learning Workshop, pp.7.   Download Article [PDF]   BibTeX Reference [BibTex]
  3. Urain, J.; Ginesi, M.; Tateo, D.; Peters, J. (2020). ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows, IEEE/RSJ International Conference on Intelligent Robots and Systems.   Download Article [PDF]   BibTeX Reference [BibTex]
  4. Urain, J.; Peters, J. (2019). Generalized Multiple Correlation Coefficient as a Similarity Measurement between Trajectories, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   Download Article [PDF]   BibTeX Reference [BibTex]

!!Key References #

Completed Theses and Projects

StartTypeIn coorperation withStudent(s)TopicDocument
2021Master's Thesis Yifei WangBimanual Control and Learning with Composable Energy Policiespdf
2021Master's Thesis Jiawei HuangMulti-Objective Reactive Motion Planning in Mobile Manipulatorspdf
2021Master's Thesis Hanyu SunCan we improve time-series classification with Inverse Reinforcement Learning?
2021Master's Thesis Lanmiao LiuDetection and Prediction of Human Gestures by Probabilistic Modellingpdf
2020Master ThesisPuze LiuZhenhui ZhouApproximated Policy Search in Black-Box Optimizationpdf
2021Integrated ProjectJoao CarvalhoJascha Hellwig, Mark BaierlActive Visual Search with POMDPs
2021Integrated Project Johannes WeyelUtilizing 6D Pose-Estimation over ROS
2021Integrated ProjectPuze LiuNiklas Babendererde, Johannes WeyelSyntethic Dataset generation for Articulation prediction
2020Integrated ProjectPuze LiuNiklas Babendererde, Jiawei HuangBenchmarking Multi-Arm Bandit & Black Box optimization(DFO) 4 Grasping
2020Integrated Project Lanmiao Liu, Hanyu SunCan we use Structured Inference Networks for Human Motion Prediction?
2020Integrated Project Pengfei ZhaoTowards Semantic Imitation Learning


zum Seitenanfang