Header logo is


2019


Thumb xl learning tactile servoing thumbnail
Learning Latent Space Dynamics for Tactile Servoing

Sutanto, G., Ratliff, N., Sundaralingam, B., Chebotar, Y., Su, Z., Handa, A., Fox, D.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019, IEEE, International Conference on Robotics and Automation, May 2019 (inproceedings) Accepted

am

pdf video [BibTex]

2019


pdf video [BibTex]


no image
X-ray Optics Fabrication Using Unorthodox Approaches

Sanli, U., Baluktsian, M., Ceylan, H., Sitti, M., Weigand, M., Schütz, G., Keskinbora, K.

Bulletin of the American Physical Society, APS, 2019 (article)

mms pi

[BibTex]

[BibTex]


no image
Nanoscale detection of spin wave deflection angles in permalloy

Gross, F., Träger, N., Förster, J., Weigand, M., Schütz, G., Gräfe, J.

{Applied Physics Letters}, 114(1), American Institute of Physics, Melville, NY, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Extracting the dynamic magnetic contrast in time-resolved X-ray transmission microscopy

Schaffers, T., Feggeler, T., Pile, S., Meckenstock, R., Buchner, M., Spoddig, D., Ney, V., Farle, M., Wende, H., Wintz, S., Weigand, M., Ohldag, H., Ollefs, K, Ney, A.

{Nanomaterials}, 9(7), MDPI, Basel, Schweiz, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Generation of switchable singular beams with dynamic metasurfaces

Yu, P., Li, J., Li, X., Schütz, G., Hirscher, M., Zhang, S., Liu, N.

{ACS Nano}, 13(6):7100-7106, American Chemical Society, Washington, DC, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Coherent excitation of heterosymmetric spin waves with ultrashort wavelengths

Dieterle, G., Förster, J., Stoll, H., Semisalova, A. S., Finizio, S., Gangwar, A., Weigand, M., Noske, M., Fähnle, M., Bykova, I., Gräfe, J., Bozhko, D. A., Musiienko-Shmarova, H. Y., Tiberkevich, V., Slavin, A. N., Back, C. H., Raabe, J., Schütz, G., Wintz, S.

{Physical Review Letters}, 122(11), American Physical Society, Woodbury, N.Y., 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
A special issue on hydrogen-based Energy storage
{International Journal of Hydrogen Energy}, 44, pages: 7737, Elsevier, Amsterdam, 2019 (misc)

mms

DOI [BibTex]

DOI [BibTex]


no image
Reprogrammability and Scalability of Magnonic Fibonacci Quasicrystals

Lisiecki, F., Rychły, J., Kuświk, P., Głowiński, H., Kłos, J. W., Groß, F., Bykova, I., Weigand, M., Zelent, M., Goering, E. J., Schütz, G., Gubbiotti, G., Krawczyk, M., Stobiecki, F., Dubowik, J., Gräfe, J.

Physical Review Applied, 11, pages: 054003, 2019 (article)

Abstract
Magnonic crystals are systems that can be used to design and tune the dynamic properties of magnetization. Here, we focus on one-dimensional Fibonacci magnonic quasicrystals. We confirm the existence of collective spin waves propagating through the structure as well as dispersionless modes; the reprogammability of the resonance frequencies, dependent on the magnetization order; and dynamic spin-wave interactions. With the fundamental understanding of these properties, we lay a foundation for the scalable and advanced design of spin-wave band structures for spintronic, microwave, and magnonic applications.

mms

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Coordinated molecule-modulated magnetic phase with metamagnetism in metal-organic frameworks

Son, K., Kim, J. Y., Schütz, G., Kang, S. G., Moon, H. R., Oh, H.

{Inorganic Chemistry}, 58(14):8895-8899, American Chemical Society, Washington, DC, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Nanoscale X-ray imaging of spin dynamics in Yttrium iron garnet

Förster, J., Wintz, S., Bailey, J., Finizio, S., Josten, E., Meertens, D., Dubs, C., Bozhko, D. A., Stoll, H., Dieterle, G., Traeger, N., Raabe, J., Slavin, A. N., Weigand, M., Gräfe, J., Schütz, G.

2019 (misc)

mms

link (url) [BibTex]

link (url) [BibTex]


no image
Magnons in a Quasicrystal: Propagation, Extinction, and Localization of Spin Waves in Fibonacci Structures

Lisiecki, F., Rychły, J., Kuświk, P., Głowiński, H., Kłos, J. W., Groß, F., Träger, N., Bykova, I., Weigand, M., Zelent, M., Goering, E. J., Schütz, G., Krawczyk, M., Stobiecki, F., Dubowik, J., Gräfe, J.

Physical Review Applied, 11, pages: 054061, 2019 (article)

Abstract
Magnonic quasicrystals exceed the possibilities of spin-wave (SW) manipulation offered by regular magnonic crystals, because of their more complex SW spectra with fractal characteristics. Here, we report the direct x-ray microscopic observation of propagating SWs in a magnonic quasicrystal, consisting of dipolar coupled permalloy nanowires arranged in a one-dimensional Fibonacci sequence. SWs from the first and second band as well as evanescent waves from the band gap between them are imaged. Moreover, additional mini band gaps in the spectrum are demonstrated, directly indicating an influence of the quasiperiodicity of the system. Finally, the localization of SW modes within the Fibonacci crystal is shown. The experimental results are interpreted using numerical calculations and we deduce a simple model to estimate the frequency position of the magnonic gaps in quasiperiodic structures. The demonstrated features of SW spectra in one-dimensional magnonic quasicrystals allow utilizing this class of metamaterials for magnonics and make them an ideal basis for future applications.

mms

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Reconfigurable nanoscale spin wave majority gate with frequency-division multiplexing

Talmelli, G., Devolder, T., Träger, N., Förster, J., Wintz, S., Weigand, M., Stoll, H., Heyns, M., Schütz, G., Radu, I., Gräfe, J., Ciubotaru, F., Adelmann, C.

2019 (misc)

Abstract
Spin waves are excitations in ferromagnetic media that have been proposed as information carriers in spintronic devices with potentially much lower operation power than conventional charge-based electronics. The wave nature of spin waves can be exploited to design majority gates by coding information in their phase and using interference for computation. However, a scalable spin wave majority gate design that can be co-integrated alongside conventional Si-based electronics is still lacking. Here, we demonstrate a reconfigurable nanoscale inline spin wave majority gate with ultrasmall footprint, frequency-division multiplexing, and fan-out. Time-resolved imaging of the magnetisation dynamics by scanning transmission x-ray microscopy reveals the operation mode of the device and validates the full logic majority truth table. All-electrical spin wave spectroscopy further demonstrates spin wave majority gates with sub-micron dimensions, sub-micron spin wave wavelengths, and reconfigurable input and output ports. We also show that interference-based computation allows for frequency-division multiplexing as well as the computation of different logic functions in the same device. Such devices can thus form the foundation of a future spin-wave-based superscalar vector computing platform.

mms

link (url) [BibTex]

link (url) [BibTex]


no image
Prototyping Micro- and Nano-Optics with Focused Ion Beam Lithography

Keskinbora, K.

SL48, pages: 46, SPIE.Spotlight, SPIE Press, Bellingham, WA, 2019 (book)

mms

DOI [BibTex]

DOI [BibTex]


Thumb xl screenshot from 2019 03 21 12 11 19
Automated Generation of Reactive Programs from Human Demonstration for Orchestration of Robot Behaviors

Berenz, V., Bjelic, A., Mainprice, J.

ArXiv, 2019 (article)

Abstract
Social robots or collaborative robots that have to interact with people in a reactive way are difficult to program. This difficulty stems from the different skills required by the programmer: to provide an engaging user experience the behavior must include a sense of aesthetics while robustly operating in a continuously changing environment. The Playful framework allows composing such dynamic behaviors using a basic set of action and perception primitives. Within this framework, a behavior is encoded as a list of declarative statements corresponding to high-level sensory-motor couplings. To facilitate non-expert users to program such behaviors, we propose a Learning from Demonstration (LfD) technique that maps motion capture of humans directly to a Playful script. The approach proceeds by identifying the sensory-motor couplings that are active at each step using the Viterbi path in a Hidden Markov Model (HMM). Given these activation patterns, binary classifiers called evaluations are trained to associate activations to sensory data. Modularity is increased by clustering the sensory-motor couplings, leading to a hierarchical tree structure. The novelty of the proposed approach is that the learned behavior is encoded not in terms of trajectories in a task space, but as couplings between sensory information and high-level motor actions. This provides advantages in terms of behavioral generalization and reactivity displayed by the robot.

am

Support Video link (url) [BibTex]


no image
Interpreting first-order reversal curves beyond the Preisach model: An experimental permalloy microarray investigation

Groß, F., Ilse, S. E., Schütz, G., Gräfe, J., Goering, E.

{Physical Review B}, 99(6), American Physical Society, Woodbury, NY, 2019 (article)

mms

DOI [BibTex]


no image
Bistability of magnetic states in Fe-Pd nanocap arrays

Aravind, P. B., Heigl, M., Fix, M., Groß, F., Gräfe, J., Mary, A., Rajgowrav, C. R., Krupiński, M., Marszałek, M., Thomas, S., Anantharaman, M. R., Albrecht, M.

Nanotechnology, 30, pages: 405705, 2019 (article)

Abstract
Magnetic bistability between vortex and single domain states in nanostructures are of great interest from both fundamental and technological perspectives. In soft magnetic nanostructures, the transition from a uniform collinear magnetic state to a vortex state (or vice versa) induced by a magnetic field involves an energy barrier. If the thermal energy is large enough for overcoming this energy barrier, magnetic bistability with a hysteresis-free switching occurs between the two magnetic states. In this work, we tune this energy barrier by tailoring the composition of FePd alloys, which were deposited onto self-assembled particle arrays forming magnetic vortex structures on top of the particles. The bifurcation temperature, where a hysteresis-free transition occurs, was extracted from the temperature dependence of the annihilation and nucleation field which increases almost linearly with Fe content of the magnetic alloy. This study provides insights into the magnetization reversal process associated with magnetic bistability, which allows adjusting the bifurcation temperature range by the material properties of the nanosystem.

mms

link (url) [BibTex]

link (url) [BibTex]


no image
An international laboratory comparison study of volumetric and gravimetric hydrogen adsorption measurements

Hurst, K. E., Gennett, T., Adams, J., Allendorf, M. D., Balderas-Xicohténcatl, R., Bielewski, M., Edwards, B., Espinal, L., Fultz, B., Hirscher, M., Hudson, M. S. L., Hulvey, Z., Latroche, M., Liu, D., Kapelewski, M., Napolitano, E., Perry, Z. T., Purewal, J., Stavila, V., Veenstra, M., White, J. L., Yuan, Y., Zhou, H., Zlotea, C., Parilla, P.

{ChemPhysChem}, 20(15):1997-2009, Wiley-VCH, Weinheim, Germany, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Hydrogen Energy

Hirscher, M., Autrey, T., Orimo, S.

{ChemPhysChem}, 20, pages: 1153-1411, Wiley-VCH, Weinheim, Germany, 2019 (misc)

mms

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
The route to supercurrent transparent ferromagnetic barriers in superconducting matrix

Ivanov, Y. P., Soltan, S., Albrecht, J., Goering, E., Schütz, G., Zhang, Z., Chuvilin, A.

{ACS Nano}, 13(5):5655-5661, American Chemical Society, Washington, DC, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Systematic experimental study on quantum sieving of hydrogen isotopes in metal-amide-imidazolate frameworks with narrow 1-D channels

Mondal, S. S., Kreuzer, A., Behrens, K., Schütz, G., Holdt, H., Hirscher, M.

{ChemPhysChem}, 20(10):1311-1315, Wiley-VCH, Weinheim, Germany, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Artifacts from manganese reduction in rock samples prepared by focused ion beam (FIB) slicing for X-ray microspectroscopy

Macholdt, D. S., Förster, J., Müller, M., Weber, B., Kappl, M., Kilcoyne, A. L. D., Weigand, M., Leitner, J., Jochum, K. P., Pöhlker, C., Andreae, M. O.

{Geoscientific instrumentation, methods and data systems}, 8(1):97-111, Copernicus Publ., Göttingen, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Mixed-state magnetotransport properties of MgB2 thin film prepared by pulsed laser deposition on an Al2O3 substrate

Alzayed, N. S., Shahabuddin, M., Ramey, S. M., Soltan, S.

{Journal of Materials Science: Materials in Electronics}, 30(2):1547-1552, Springer, Norwell, MA, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Comparison of theories of fast and ultrafast magnetization dynamics

Fähnle, M.

{Journal of Magnetism and Magnetic Materials}, 469, pages: 28-29, NH, Elsevier, Amsterdam, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Concepts for improving hydrogen storage in nanoporous materials

Broom, D. P., Webb, C. J., Fanourgakis, G. S., Froudakis, G. E., Trikalitis, P. N., Hirscher, M.

{International Journal of Hydrogen Energy}, 44(15):7768-7779, Elsevier, Amsterdam, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Controlling dislocation nucleation-mediatd plasticity in nanostructures via surface modification

Shin, J., Chen, L. Y., Sanli, U. T., Richter, G., Labat, S., Richard, M., Cornelius, T., Thomas, O., Gianola, D. S.

{Acta Materialia}, 166, pages: 572-586, Elsevier Science, Kidlington, 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Reprogrammability and scalability of magnonic Fibonacci quasicrystals

Lisiecki, F., Rychly, J., Kuswik, P., Glowinski, H., Klos, J. W., Groß, F., Bykova, I., Weigand, M., Zelent, M., Goering, E. J., Schütz, G., Gubbiotti, G., Krawczyk, M., Stobiecki, F., Dubowik, J., Gräfe, J.

{Physical Review Applied}, 11(5), American Physical Society, College Park, Md. [u.a.], 2019 (article)

mms

DOI [BibTex]

DOI [BibTex]

2007


no image
Towards Machine Learning of Motor Skills

Peters, J., Schaal, S., Schölkopf, B.

In Proceedings of Autonome Mobile Systeme (AMS), pages: 138-144, (Editors: K Berns and T Luksch), 2007, clmc (inproceedings)

Abstract
Autonomous robots that can adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s, however, made it clear that an approach purely based on reasoning or human insights would not be able to model all the perceptuomotor tasks that a robot should fulfill. Instead, new hope was put in the growing wake of machine learning that promised fully adaptive control algorithms which learn both by observation and trial-and-error. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach to motor skill learning in order to get one step closer towards human-like performance. For doing so, we study two ma jor components for such an approach, i.e., firstly, a theoretically well-founded general approach to representing the required control structures for task representation and execution and, secondly, appropriate learning algorithms which can be applied in this setting.

am ei

PDF DOI [BibTex]

2007


PDF DOI [BibTex]


no image
Reinforcement Learning for Optimal Control of Arm Movements

Theodorou, E., Peters, J., Schaal, S.

In Abstracts of the 37st Meeting of the Society of Neuroscience., Neuroscience, 2007, clmc (inproceedings)

Abstract
Every day motor behavior consists of a plethora of challenging motor skills from discrete movements such as reaching and throwing to rhythmic movements such as walking, drumming and running. How this plethora of motor skills can be learned remains an open question. In particular, is there any unifying computa-tional framework that could model the learning process of this variety of motor behaviors and at the same time be biologically plausible? In this work we aim to give an answer to these questions by providing a computational framework that unifies the learning mechanism of both rhythmic and discrete movements under optimization criteria, i.e., in a non-supervised trial-and-error fashion. Our suggested framework is based on Reinforcement Learning, which is mostly considered as too costly to be a plausible mechanism for learning com-plex limb movement. However, recent work on reinforcement learning with pol-icy gradients combined with parameterized movement primitives allows novel and more efficient algorithms. By using the representational power of such mo-tor primitives we show how rhythmic motor behaviors such as walking, squash-ing and drumming as well as discrete behaviors like reaching and grasping can be learned with biologically plausible algorithms. Using extensive simulations and by using different reward functions we provide results that support the hy-pothesis that Reinforcement Learning could be a viable candidate for motor learning of human motor behavior when other learning methods like supervised learning are not feasible.

am ei

[BibTex]

[BibTex]


no image
Reinforcement learning by reward-weighted regression for operational space control

Peters, J., Schaal, S.

In Proceedings of the 24th Annual International Conference on Machine Learning, pages: 745-750, ICML, 2007, clmc (inproceedings)

Abstract
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-base reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Policy gradient methods for machine learning

Peters, J., Theodorou, E., Schaal, S.

In Proceedings of the 14th INFORMS Conference of the Applied Probability Society, pages: 97-98, Eindhoven, Netherlands, July 9-11, 2007, 2007, clmc (inproceedings)

Abstract
We present an in-depth survey of policy gradient methods as they are used in the machine learning community for optimizing parameterized, stochastic control policies in Markovian systems with respect to the expected reward. Despite having been developed separately in the reinforcement learning literature, policy gradient methods employ likelihood ratio gradient estimators as also suggested in the stochastic simulation optimization community. It is well-known that this approach to policy gradient estimation traditionally suffers from three drawbacks, i.e., large variance, a strong dependence on baseline functions and a inefficient gradient descent. In this talk, we will present a series of recent results which tackles each of these problems. The variance of the gradient estimation can be reduced significantly through recently introduced techniques such as optimal baselines, compatible function approximations and all-action gradients. However, as even the analytically obtainable policy gradients perform unnaturally slow, it required the step from ÔvanillaÕ policy gradient methods towards natural policy gradients in order to overcome the inefficiency of the gradient descent. This development resulted into the Natural Actor-Critic architecture which can be shown to be very efficient in application to motor primitive learning for robotics.

am ei

[BibTex]

[BibTex]


no image
Policy Learning for Motor Skills

Peters, J., Schaal, S.

In Proceedings of 14th International Conference on Neural Information Processing (ICONIP), pages: 233-242, (Editors: Ishikawa, M. , K. Doya, H. Miyamoto, T. Yamakawa), 2007, clmc (inproceedings)

Abstract
Policy learning which allows autonomous robots to adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach policy learning with the goal of an application to motor skill refinement in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, we study policy learning algorithms which can be applied in the general setting of motor skill learning, and, secondly, we study a theoretically well-founded general approach to representing the required control structures for task representation and execution.

am ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Reinforcement learning for operational space control

Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Conference on Robotics and Automation, pages: 2111-2116, IEEE Computer Society, ICRA, 2007, clmc (inproceedings)

Abstract
While operational space control is of essential importance for robotics and well-understood from an analytical point of view, it can be prohibitively hard to achieve accurate control in face of modeling errors, which are inevitable in complex robots, e.g., humanoid robots. In such cases, learning control methods can offer an interesting alternative to analytical control algorithms. However, the resulting supervised learning problem is ill-defined as it requires to learn an inverse mapping of a usually redundant system, which is well known to suffer from the property of non-convexity of the solution space, i.e., the learning system could generate motor commands that try to steer the robot into physically impossible configurations. The important insight that many operational space control algorithms can be reformulated as optimal control problems, however, allows addressing this inverse learning problem in the framework of reinforcement learning. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-based reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Relative Entropy Policy Search

Peters, J.

CLMC Technical Report: TR-CLMC-2007-2, Computational Learning and Motor Control Lab, Los Angeles, CA, 2007, clmc (techreport)

Abstract
This technical report describes a cute idea of how to create new policy search approaches. It directly relates to the Natural Actor-Critic methods but allows the derivation of one shot solutions. Future work may include the application to interesting problems.

am ei

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Using reward-weighted regression for reinforcement learning of task space control

Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pages: 262-267, Honolulu, Hawaii, April 1-5, 2007, 2007, clmc (inproceedings)

Abstract
In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, `vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark

Riedmiller, M., Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pages: 254-261, ADPRL, 2007, clmc (inproceedings)

Abstract
In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, `vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

am ei

PDF [BibTex]

PDF [BibTex]


no image
Uncertain 3D Force Fields in Reaching Movements: Do Humans Favor Robust or Average Performance?

Mistry, M., Theodorou, E., Hoffmann, H., Schaal, S.

In Abstracts of the 37th Meeting of the Society of Neuroscience, 2007, clmc (inproceedings)

am

PDF [BibTex]

PDF [BibTex]


no image
Applying the episodic natural actor-critic architecture to motor primitive learning

Peters, J., Schaal, S.

In Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium, April 25-27, 2007, clmc (inproceedings)

Abstract
In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the Òbuilding blocks of movement generationÓ, called motor primitives. Motor primitives are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. We show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm.

am

link (url) [BibTex]

link (url) [BibTex]


no image
The new robotics - towards human-centered machines

Schaal, S.

HFSP Journal Frontiers of Interdisciplinary Research in the Life Sciences, 1(2):115-126, 2007, clmc (article)

Abstract
Research in robotics has moved away from its primary focus on industrial applications. The New Robotics is a vision that has been developed in past years by our own university and many other national and international research instiutions and addresses how increasingly more human-like robots can live among us and take over tasks where our current society has shortcomings. Elder care, physical therapy, child education, search and rescue, and general assistance in daily life situations are some of the examples that will benefit from the New Robotics in the near future. With these goals in mind, research for the New Robotics has to embrace a broad interdisciplinary approach, ranging from traditional mathematical issues of robotics to novel issues in psychology, neuroscience, and ethics. This paper outlines some of the important research problems that will need to be resolved to make the New Robotics a reality.

am

link (url) [BibTex]

link (url) [BibTex]


no image
A computational model of human trajectory planning based on convergent flow fields

Hoffman, H., Schaal, S.

In Abstracts of the 37st Meeting of the Society of Neuroscience, San Diego, CA, Nov. 3-7, 2007, clmc (inproceedings)

Abstract
A popular computational model suggests that smooth reaching movements are generated in humans by minimizing a difference vector between hand and target in visual coordinates (Shadmehr and Wise, 2005). To achieve such a task, the optimal joint accelerations may be pre-computed. However, this pre-planning is inflexible towards perturbations of the limb, and there is strong evidence that reaching movements can be modified on-line at any moment during the movement. Thus, next-state planning models (Bullock and Grossberg, 1988) have been suggested that compute the current control command from a function of the goal state such that the overall movement smoothly converges to the goal (see Shadmehr and Wise (2005) for an overview). So far, these models have been restricted to simple point-to-point reaching movements with (approximately) straight trajectories. Here, we present a computational model for learning and executing arbitrary trajectories that combines ideas from pattern generation with dynamic systems and the observation of convergent force fields, which control a frog leg after spinal stimulation (Giszter et al., 1993). In our model, we incorporate the following two observations: first, the orientation of vectors in a force field is invariant over time, but their amplitude is modulated by a time-varying function, and second, two force fields add up when stimulated simultaneously (Giszter et al., 1993). This addition of convergent force fields varying over time results in a virtual trajectory (a moving equilibrium point) that correlates with the actual leg movement (Giszter et al., 1993). Our next-state planner is a set of differential equations that provide the desired end-effector or joint accelerations using feedback of the current state of the limb. These accelerations can be interpreted as resulting from a damped spring that links the current limb position with a virtual trajectory. This virtual trajectory can be learned to realize any desired limb trajectory and velocity profile, and learning is efficient since the time-modulated sum of convergent force fields equals a sum of weighted basis functions (Gaussian time pulses). Thus, linear algebra is sufficient to compute these weights, which correspond to points on the virtual trajectory. During movement execution, the differential equation corrects automatically for perturbations and brings back smoothly the limb towards the goal. Virtual trajectories can be rescaled and added allowing to build a set of movement primitives to describe movements more complex than previously learned. We demonstrate the potential of the suggested model by learning and generating a wide variety of movements.

am

[BibTex]

[BibTex]


no image
On the theory of magnetization dynamics of non-collinear spin systems in the s-d model

De Angeli, L.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Zur ab-initio Elektronentheorie des Magnetismus bei endlichen Temperaturen

Dietermann, F.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Röntgenzirkulardichroische Untersuchungen an ferromagnetischen verdünnten Halbleitersystemen

Tietze, T.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Low-dimensional Fe on vicinal Ir(997): Growth and magnetic properties

Kawwam, M.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Micromagnetic simulations of switching processes and the role of thermal fluctuations

Macke, S.

Universität Stuttgart, Stuttgart, 2007 (mastersthesis)

mms

[BibTex]

[BibTex]


no image
Hydrogen storage in metal-organic frameworks

Hirscher, M., Panella, B.

{Scripta Materialia}, 56, pages: 809-812, 2007 (article)

mms

[BibTex]

[BibTex]


no image
Substrate-induced current anisotropy in YBa2Cu3O7-δthin films

Djupmyr, M., Albrecht, J.

{Physica C}, 460-462, pages: 1190-1191, 2007 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
A micellar approach to magnetic ultrahigh-density data-storage media: extending the limits of current colloidal methods

Ethirajan, A., Wiedwald, U., Boyen, H.-G., Kern, B., Han, L., Klimmer, A., Weigl, F., Kästle, G., Ziemann, P., Fauth, K., Cai, J., Behm, J., Romanyuk, A., Oelhafen, P., Walther, P., Biskupek, J., Kaiser, U.

{Advanced Materials}, 19, pages: 406-410, 2007 (article)

mms

[BibTex]

[BibTex]


no image
Size dependence in the magnetization reversal of Fe/Gd multilayers on self-assembled arrays of nanospheres

Amaladass, E., Ludescher, B., Schütz, G., Tyliszczak, T., Eimüller, T.

{Applied Physics Letters}, 91, 2007 (article)

mms

DOI [BibTex]

DOI [BibTex]


no image
Ma\ssgeschneiderte Wasserstoffspeicher

Hirscher, M., Panella, B.

{Nachrichten aus der Gdch-Energieinitiative}, (Sonderheft April 2007):12-13, 2007 (article)

mms

[BibTex]

[BibTex]


no image
Reconstruction of historical alloys for pipe organs brings true Baroque music back to life.

Baretzky, B., Friesel, M., Straumal, B.

{MRS Bulletin}, 32, pages: 249-255, 2007 (article)

mms

[BibTex]

[BibTex]