apl. Prof. Dr. Jochen Steil

The CoR-Lab: The Research Institute for Cognition and Robotics (CoR-Lab) has been founded at the Bielefeld University in July 2007 to face the enormous challenges implied by creating intelligent systems and robots. CoR-Lab investigates artificial cognition, computer vision, neural networks, and robot learning and runs a Graduate School in Cognitions and Robotics, jointly with the strategic partner Honda Research Institute Europe. More than 100 researchers on all levels are involved in CoR-Lab projects. The CoR-Lab is headed by a directorium (apl. Prof. Steil, Prof. Ritter, Prof. Sagerer, Prof. Körner) and administred by J. Steil (Managing Director) and Dr. Carola Haumann (Manging Director Graduate School). Within CoR-Lab, J. Steil is  the head of a research group "cognitive robotics and learning".

Vita: In 1993, I received the diploma in mathematics from the Bielefeld University, and joined the Neuroinformatics Group headed by Prof. H. Ritter. In 1995/96 I stayed one year at the St. Petersburg Electrotechnical University, Russia, supported by a German Academic Exchange Foundation (DAAD) grant. In 1999, I received the PhD. Degree (Dr. rer. nat) with a Dissertation on "Input-Output Stability of Recurrent Neural Networks". In 2002, I was appointed tenured senior researcher (Akad. Rat) and in 2006 my habilitation was accepted by the Faculty of Technology  and I was assigned the venia legendi in Neuroinformatics. From March-July 2006 I was on leave as principal scientist at the Honda Research Institute Europe, Offenbach. In 2008, I have been appointed apl. Professor for Neuroinformatics at the Faculty of Technology. Since April 2007, I have been managing director of the Research Institute for Cognition and Robotics, CoR-Lab and since Nov. 2007 a member of the scientific board of the center of excellence in Cognitive Interaction Technology (CITEC). Since 2010, I am coordinator of the FP7-EU project AMARSi - Adaptive Modular Architectures for Rich Motor Skills

Research Interests: Learning in artificial cognitive systems, learning and stability in recurrent networks, reservoir networks and nonlinear dynamics, representation in dynamical systems, robot learning, imitation learning, robot learning and system architectures, generative learning

Selected  Publication: The following paper introduces online-learning goal babbling algorithm that allows exploration of sensori-motor mappings at human speed.

Rolf, M., J. J. Steil, and M. Gienger, "Online Goal Babbling for rapid bootstrapping of inverse models in high dimensions", IEEE Int. Conf. Development and Learning and on Epigenetic Robotics (Best Student Paper Award), Frankfurt, IEEE, 08/2011. Tagged XML BibTex Google Scholar Download: RolfSteilGienger2011-ICDL-EpiRob.pdf (1.49 MB)

Selected  Publication: The following paper introduces the online-learning algorithm BPDC for reservoir computing and shows that a reservoir approach naturally arises from a constraint optimisation of the standard quadratic error function.

Educational material like tutorial talks, tutorial paper, or poster.

Research Projects:

• Coordination of AMARSi: Adaptive Modular Architecturs for Rich Motor Skills, large scale FP7-IP project
  • Dr. A. Soltoggio, Technical Coordinator:  Modulatory Neural Learning
  • A. Lemme: Neural Learning of Motion Primitives
  • A. Nordmann: Software Architecture for Motion Control of Compliant Robots, co-supervisor Dr. S. Wrede
     
• Research Group on Cognitive Robotics & Learning (CoR-Lab):
  • Goal-babbling: Online Exploration of redundant inverse mappings (M. Rolf)
  • Reservoir Computing with Output Feedback (F. Reinhart)
  • Representation in and temporal encoding in recurrent reservoirs (C. Emmerich)
  • IP Learning for Feature Regularization (K. Neumann)
  • Neural Learning of Motion Primitives (A. Lemme, AMARSi)
  • Calibration Free Hand-Eye Coordination (A. Freire), DAAD co-funded PhD grant in cooperation with Prof. G. Baretto, Fortaleza, Brazil
• CITEC (Excellence Center in Cognitive Interaction Technology)

  • Task-dependent control of eye movements and mobile visual sensors (Dr. Anna Belardinelli, Dipl. Inf. Marco Wischnewski), co-superviser  Prof. W.X. Schneider, Department of Psychology, Bielefeld University
    

• Industrial R&D cooperation

  • “Interaktive Bedienhilfe in der ZSVA” (S. Ruether), R&D project with industry partner Miele Professional, Miele & Cie. KG, co-supervisor Dr. T. Hermann, Prof. Dr. S. Kopp

• Finished projects
  • 2008-2011 Goal-directed imitation learning from humans (Dr. M. Mühlig), co-superviser Dr. M. Gienger, HRI
  • 2008-2011, Neural learning of flexible full body motion (M. Rolf),  R&D project with Honda Research Institute (HRI) in cooperation with Dr. M. Gienger
  • 2006-2011, ALEGRO: Autonomous Learning of Generative Representations of Objects (Dr. A. Denecke),  R&D project with Honda Research Institute (HRI) in cooperation with Dr. H. Wersing (HRI)
  • 2006-2010 project C4 “Adaptive Alignment in Human-Robot-Cooperation” in special
    research unit (SFB) 673 “Alignment in Communication” with Prof. Ritter
  • “Haptic object classification by recursive networks in anthropomorphic grasping”,
    DAAD funded cooperation with Prof. A. Sperduti, Padua, Italy
  • 04/2003 – 03/2007 “Viola: Visual Online Learning and Action” in cooperation with Honda Research Institute Europe, Offenbachin cooperation with Dr. H. Wersing (HRI)
  • 01/2003 – 12/2005 project D6 “Architectures for Learning by Imitation in Speech-action Systems” in SFB 360 “Situated Artificial Communicators” with Prof. Ritter