The neural learning for robotics research (NLR) laboratory is lead by Prof. Elmar Rueckert and located at the Institute for Robotics and Cognitive Systems at University of Lübeck and affiliated with the Technical University Darmstadt.
The group’s research topics are autonomous systems, machine and deep learning, brain-computer interfaces and simulations and computational models.
News
December 3, 2019
Successful grant: DFG project with > 650kEURO granted
Together with Prof. Philipp Beckerle from the TU Dortmund, we got our research project on ‘Active transfer learning with neural networks through human-robot interactions’ granted.August 26, 2019
Winner of the ’German AI-Young Research Price 2019’
Prof. Rueckert won the ’German AI-Young Researcher Price 2019’ (germ. deutscher KI-Nachwuchspreis 2019) by Bilanz & McKinsey – KI-Denker der Zukunft. The awards ceremony was on Sept. 26th, 2019. The main AI price was given to Prof. Kristian Kersting from the TU-Darmstadt. The german company DeepL received the award for..
Read MoreJuly 26, 2019
Advanced Robotics Best Paper Award
for the paper: Probabilistic Movement Primitives under Unknown System Dynamics, by Paraschos, Alexandros and Rueckert, Elmar and Peters, Jan and Neumann, Gerhard. Advanced Robotics (ARJ), 32 (6), pp. 297-310, 2018.June 22, 2019
Conference Paper accepted at ECMR 2019
The paper by Nils Rottmann, Ralf Bruder, Achim Schweikard and Elmar Rueckert on “Loop Closure Detection in Closed Environments” was accepted for publication at the 2019 European Conference on Mobile Robots (ECMR).June 20, 2019
Conference Paper Accepted at IROS 2019
The paper by Svenja Stark, Jan Peters and Elmar Rueckert on “Experience Reuse with Probabilistic Movement Primitives” was accepted for publication in the Proceedings of the 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019).June 7, 2019
Successful grant: Autonome Elektrofahrzeuge als urbane Lieferanten
Das Projekt Autonome Elektrofahrzeuge als urbane Lieferanten wird im Rahmen des Programms „Our Common Future“ von der Robert Bosch Stiftung gefördert. Projektstart ist der 01.07.2019 bis 30.10.2021 More at: https://future.ai-lab.scienceApril 17, 2019
Gründungssitzung Grundlagen von KI Systemen
Fachausschusses FA1.60 zu Grundlagen lernender intelligenter Systeme, Gründungsmitglieder: Barbara Hammer (Universität Bielefeld), Elmar Rückert (gewählter Vorsitzender), Georg Schildbach (Universität zu Lübeck), Gerhard Neumann (Universität Tübingen), Heinz Koeppl (Technische Universität Darmstadt), Jan Peters (Technische Universität Darmstadt), Justus Piater (Universität Innsbruck), Kristian Kersting (Technische Universität Darmstadt), Marc Toussaint (Universität Stuttgart), Micheal Ginger..
Read MoreJanuary 5, 2019
Best Paper Award
for the paper: Learning to Categorize Bug Reports with LSTM Networks, by Gondaliya, Kaushikkumar D; Peters, Jan; Rueckert, Elmar. In Proceedings of the International Conference on Advances in System Testing and Validation Lifecycle (VALID)., pp. 6, XPS (Xpert Publishing Services), Nice, France, 2018, ISBN: 978-1-61208-671-2, ( October 14-18, 2018).December 21, 2018
Conference paper accepted at BIOSIGNALS 2019
Rottmann, N; Bruder, R; Schweikard, A; Rueckert, E. (2019). Cataglyphis ant navigation strategies solve the global localization problem in robots with binary sensors, Proceedings of the International Conference on Bio-inspired Systems and Signal Processing (BIOSIGNALS).October 9, 2018
Journal Paper Accepted at Neural Networks
Daniel Tanneberg, Jan Peters, Elmar Rueckert Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks accepted (Oct, 9th 2018) at Neural Networks – Elsevier with an Impact Factor of 7.197 (2017).July 31, 2018
Conference paper accepted at VAILD 2018
Gondaliya, D. Kaushikkumar; Peters, J.; Rueckert, E. (2018). Learning to categorize bug reports with LSTM networks: An empirical study on thousands of real bug reports from a world leading software company, Proceedings of the International Conference on Advances in System Testing and Validation Lifecycle (VALID).July 18, 2018
Journal Paper Accepted at JMLR – Journal of Machine Learning Research.
Adrian Šošić, Elmar Rueckert, Jan Peters, Abdelhak M. Zoubir, Heinz Koeppl Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling accepted (Oct, 8th 2018) at Journal of Machine Learning Research (JMLR).February 1, 2018
1st day as Assistant Professor
September 18, 2017
Invited Talk at the ICDL Conference, Lisbon, Portugal
Home – Background Slideshow Title: Experience Replay and Intrinsic Motivation in Neural Motor Skill Learning ModelsSeptember 18, 2017
3 HUMANOIDS Papers Accepted
Rueckert, E.; Nakatenus, M.; Tosatto, S.; Peters, J. (2017). Learning Inverse Dynamics Models in O(n) time with LSTM networks. Tanneberg, D.; Peters, J.; Rueckert, E. (2017). Efficient Online Adaptation with Stochastic Recurrent Neural Networks. Stark, S.; Peters, J.; Rueckert, E. (2017). A Comparison of Distance Measures for Learning Nonparametric Motor..
Read MoreSeptember 1, 2017
CoRL Paper accepted
Tanneberg, D.; Peters, J.; Rueckert, E. (2017). Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals, Proceedings of the Conference on Robot Learning (CoRL).August 4, 2017
W1 Juniorprofessorship with tenure track at University Lübeck
With February 1st, 2018 I will work as professor for robotics at the university Lübeck.February 28, 2017
Invited Talk at University Lübeck
Title: Neural models for robot motor skill learning. Abstract: The challenges in understanding human motor control, in brain-machine interfaces and anthropomorphic robotics are currently converging. Modern anthropomorphic robots with their compliant actuators and various types of sensors (e.g., depth and vision cameras, tactile fingertips, full-body skin, proprioception) have reached the perceptuomotor..
Read MoreJanuary 31, 2017
Invited Talk at the Frankfurt Institute for Advanced Studies (FIAS), Germany
Learning to Plan through Reinforcement Learning in Spiking Neural Networks Abstract: Movement planing is a fundamental skill that is involved in many human motor control tasks. While the hippocampus plays a central role, the functional principles underlying planning are largely unexplored. In this talk, I present a computational model for planning..
Read MoreNovember 18, 2016
Invited Talk at the Institute of Neuroinformatics (INI), Zurich, Switzerland
Probabilistic computational models of human motor control for robot learning.November 14, 2016
Invited Talk at the Albert-Ludwigs-Universität Freiburg, Germany
Neural models for brain-machine interfaces and anthropomorphic roboticsFebruary 6, 2016
Journal Paper Accepted at Nature Publishing Group: Scientific Reports.
Rueckert, Elmar; Camernik, Jernej; Peters, Jan; Babic, Jan Probabilistic Movement Models Show that Postural Control Precedes and Predicts Volitional Motor Control Nature Publishing Group: Scientific Reports, 6 (28455), 2016.December 18, 2015
Journal Paper Accepted at Nature Publishing Group: Scientific Reports.
Rueckert, Elmar; Kappel, David; Tanneberg, Daniel; Pecevski, Dejan; Peters, Jan Recurrent Spiking Networks Solve Planning Tasks Nature Publishing Group: Scientific Reports, 6 (21142), 2016.March 1, 2014
Postdoctoral fellow at IAS, Darmstadt
Elmar Rueckert joined the Autonomous Systems Labs of Prof. Jan Peters as Post-Doc in March 2014.February 4, 2014
Ph.D. Defense – Summa Cum Laude (with honors).
At the Technical University Graz, Austria with Prof. Wolfgang Maass.June 1, 2013
Two Journal Papers Accepted at Frontiers in Computational Neurosciene
Rueckert, Elmar; d’Avella, Andrea Learned parametrized dynamic movement primitives with shared synergies for controlling robotic and musculoskeletal systems Rueckert, Elmar; Neumann, Gerhard; Toussaint, Marc; Maass, Wolfgang Learned graphical models for probabilistic planning provide a new class of movement primitivesJanuary 28, 2010
M.Sc. defense – Summa Cum Laude (with honors).
At the technical University Graz with Prof. Horst Bischof.