Joschka Boedecker

Publications (14) View all

• Source

  Available from: Joschka Boedecker

  Conference Proceeding: Real-Time Inverse Dynamics Learning for Musculoskeletal Robots based on Echo State Gaussian Process Regression

  Christoph Hartmann, Joschka Boedecker, Oliver Obst, Shuhei Ikemoto, Minoru Asada
  [show abstract] [hide abstract]
  ABSTRACT: A challenging topic in articulated robots is the control of redundantly many degrees of freedom with artificial muscles. Actuation with these devices is difficult to solve because of nonlinearities, delays and unknown parameters such as fric- tion. Machine learning methods can be used to learn control of these systems, but are faced with the additional problem that the size of the search space prohibits full exploration in reasonable time. We propose a novel method that is able to learn control of redundant robot arms with artificial muscles online from scratch using only the position of the end effector, without using any joint positions, accelerations or an analytical model of the system or the environment. To learn in real time, we use the so called online “goal babbling” method to effectively reduce the search space, a recurrent neural network to represent the state of the robot arm, and novel online Gaussian processes for regression. With our approach, we achieve good performance on trajectory tracking tasks for the end effector of two very challenging systems: a simulated 6 DOF redundant arm with artificial muscles, and a 7 DOF robot arm with McKibben pneumatic artificial muscles. We also show that the combination of techniques we propose results in significantly improved performance over using the individual techniques alone. Online at: http://www.roboticsproceedings.org/rss08/p15.html See also: https://sites.google.com/site/ridlesgp/ Code available at: http://www.christophartmann.de/research
  Proceedings of Robotics: Science and Systems, Sydney; 07/2012
• Source

  Available from: Joschka Boedecker

  Article: Information processing in echo state networks at the edge of chaos.

  Joschka Boedecker, Oliver Obst, Joseph T Lizier, N Michael Mayer, Minoru Asada
  [show abstract] [hide abstract]
  ABSTRACT: We investigate information processing in randomly connected recurrent neural networks. It has been shown previously that the computational capabilities of these networks are maximized when the recurrent layer is close to the border between a stable and an unstable dynamics regime, the so called edge of chaos. The reasons, however, for this maximized performance are not completely understood. We adopt an information-theoretical framework and are for the first time able to quantify the computational capabilities between elements of these networks directly as they undergo the phase transition to chaos. Specifically, we present evidence that both information transfer and storage in the recurrent layer are maximized close to this phase transition, providing an explanation for why guiding the recurrent layer toward the edge of chaos is computationally useful. As a consequence, our study suggests self-organized ways of improving performance in recurrent neural networks, driven by input data. Moreover, the networks we study share important features with biological systems such as feedback connections and online computation on input streams. A key example is the cerebral cortex, which was shown to also operate close to the edge of chaos. Consequently, the behavior of model systems as studied here is likely to shed light on reasons why biological systems are tuned into this specific regime.
  Theory in Biosciences 12/2011; 131(3):205-13. · 0.98 Impact Factor
• Source

  Available from: Joschka Boedecker

  Conference Proceeding: Between Frustration and Elation: Sense of Control Regulates the lntrinsic Motivation for Motor Learning.

  Beata Grzyb, Joschka Boedecker, Minoru Asada, Angel P. Del Pobil, Linda B. Smith
  Lifelong Learning, Papers from the 2011 AAAI Workshop, San Francisco, California, USA, August 7, 2011; 01/2011
• Source

  Available from: Joschka Boedecker

  Conference Proceeding: Improving Recurrent Neural Network Performance Using Transfer Entropy.

  Oliver Obst, Joschka Boedecker, Minoru Asada
  Neural Information Processing. Models and Applications - 17th International Conference, ICONIP 2010, Sydney, Australia, November 22-25, 2010, Proceedings, Part II; 01/2010
• Source

  Available from: Joschka Boedecker

  Article: Initialization and self-organized optimization of recurrent neural network connectivity.

  Joschka Boedecker, Oliver Obst, N Michael Mayer, Minoru Asada
  [show abstract] [hide abstract]
  ABSTRACT: Reservoir computing (RC) is a recent paradigm in the field of recurrent neural networks. Networks in RC have a sparsely and randomly connected fixed hidden layer, and only output connections are trained. RC networks have recently received increased attention as a mathematical model for generic neural microcircuits to investigate and explain computations in neocortical columns. Applied to specific tasks, their fixed random connectivity, however, leads to significant variation in performance. Few problem-specific optimization procedures are known, which would be important for engineering applications, but also in order to understand how networks in biology are shaped to be optimally adapted to requirements of their environment. We study a general network initialization method using permutation matrices and derive a new unsupervised learning rule based on intrinsic plasticity (IP). The IP-based learning uses only local learning, and its aim is to improve network performance in a self-organized way. Using three different benchmarks, we show that networks with permutation matrices for the reservoir connectivity have much more persistent memory than the other methods but are also able to perform highly nonlinear mappings. We also show that IP-based on sigmoid transfer functions is limited concerning the output distributions that can be achieved.
  HFSP journal. 10/2009; 3(5):340-9.