Header logo is


2001


no image
Biomimetic smooth pursuit based on fast learning of the target dynamics

Shibata, T., Schaal, S.

In IEEE International Conference on Intelligent Robots and Systems (IROS 2001), 2001, clmc (inproceedings)

Abstract
Following a moving target with a narrow-view foveal vision system is one of the essential oculomotor behaviors of humans and humanoids. This oculomotor behavior, called ``Smooth Pursuit'', requires accurate tracking control which cannot be achieved by a simple visual negative feedback controller due to the significant delays in visual information processing. In this paper, we present a biologically inspired and control theoretically sound smooth pursuit controller consisting of two cascaded subsystems. One is an inverse model controller for the oculomotor system, and the other is a learning controller for the dynamics of the visual target. The latter controller learns how to predict the target's motion in head coordinates such that tracking performance can be improved. We investigate our smooth pursuit system in simulations and experiments on a humanoid robot. By using a fast on-line statistical learning network, our humanoid oculomotor system is able to acquire high performance smooth pursuit after about 5 seconds of learning despite significant processing delays in the syste

am

link (url) [BibTex]

2001


link (url) [BibTex]


no image
Biomimetic oculomotor control

Shibata, T., Vijayakumar, S., Conradt, J., Schaal, S.

Adaptive Behavior, 9(3/4):189-207, 2001, clmc (article)

Abstract
Oculomotor control in a humanoid robot faces similar problems as biological oculomotor systems, i.e., capturing targets accurately on a very narrow fovea, dealing with large delays in the control system, the stabilization of gaze in face of unknown perturbations of the body, selective attention, and the complexity of stereo vision. In this paper, we suggest control circuits to realize three of the most basic oculomotor behaviors and their integration - the vestibulo-ocular and optokinetic reflex (VOR-OKR) for gaze stabilization, smooth pursuit for tracking moving objects, and saccades for overt visual attention. Each of these behaviors and the mechanism for their integration was derived with inspiration from computational theories as well as behavioral and physiological data in neuroscience. Our implementations on a humanoid robot demonstrate good performance of the oculomotor behaviors, which proves to be a viable strategy to explore novel control mechanisms for humanoid robotics. Conversely, insights gained from our models have been able to directly influence views and provide new directions for computational neuroscience research.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Development of a scaled teleoperation system for nano scale interaction and manipulation

Sitti, M., Aruk, B., Shintani, H., Hashimoto, H.

In Robotics and Automation, 2001. Proceedings 2001 ICRA. IEEE International Conference on, 1, pages: 860-867, 2001 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Irradiation-induced electron tunnelling and small-polaron hopping in single-crystalline YIG

Walz, F., Brabers, J. H. V. J., Torres, L., Kronmüller, H.

{Physica Status Solidi B-Basic Research}, 228(3):717-730, 2001 (article)

mms

[BibTex]

[BibTex]


no image
Kernspinresonanzuntersuchungen zur Diffusion von Wasserstoff in den Di- und Trihydriden der Übergangsmetalle

Gottwald, J.

Universität Stuttgart, Stuttgart, 2001 (phdthesis)

mms

[BibTex]


no image
Hexagonally ordered 100 nm period nickel nanowire arrays

Nielsch, K., Wehrspohn, R. B., Barthel, J., Kirschner, J., Gösele, U., Fischer, S. F., Kronmüller, H.

{Applied Physics Letters}, 79(9):1360-1362, 2001 (article)

mms

[BibTex]

[BibTex]


no image
Magnetization processes in isotropic and textured Nd2Fe14B- films

Melsheimer, A., Kronmüller, H.

{Physica B}, 299(3-4):251-259, 2001 (article)

mms

[BibTex]

[BibTex]


no image
Critical magnetic properties of disordered Cr-rich FeCr alloys

Fischer, S. F., Kaul, S. N., Kronmüller, H.

{Journal of Magnetism and Magnetic Materials}, 226(Sp. Iss. SI):540-541, 2001 (article)

mms

[BibTex]

[BibTex]


no image
Fast ab initio methods for the calculation of adiabatic spin wave spectra in complex systems

Grotheer, O., Ederer, C., Fähnle, M.

{Physical Review B}, 63(10):100401-100401, 2001 (article)

mms

[BibTex]

[BibTex]


no image
Hydrogen storage in sonicated carbon materials

Hirscher, M., Becher, M., Haluska, M., Dettlaff-Weglikowska, U., Quintel, A., Duesberg, G. S., Choi, Y. M., Downes, P., Hulman, M., Roth, S., Stepanek, I., Bernier, P.

{Applied Physics A-Materials Science \& Processing}, 72(2):129-132, 2001 (article)

mms

[BibTex]

[BibTex]


no image
Measurement of the low-temperature self-diffusivity of lithium by elastic recoil detection analysis

Wieland, O., Carstanjen, H. D.

In Proceedings of DIMAT 2000, the Fifth International Conference on Diffusion in Materials, 194/199, pages: 35-41, Defect and Diffusion Forum, Scitec Publications Ltd., Paris, France, 2001 (inproceedings)

mms

[BibTex]

[BibTex]


no image
Co(NH3)2Cl2 and Co(ND3)2Cl2: Order-Disorder Behaviour of N(H,D)3 and Antiferromagnetic Structure

Leineweber, A., Jacobs, H., E\ssmann, P., Allenspach, F., Fauth, F., Fischer, P.

{Zeitschrift f\"ur Anorganische und Allgemeine Chemie}, 627, pages: 2063-2069, 2001 (article)

mms

[BibTex]

[BibTex]


no image
Critical magnetic properties of disordered polycrystalline Fe75Fe25 and Cr70Fe30 alloys

Fischer, S. F., Kaul, S. N., Kronmüller, H.

{Physical Review B}, 65, 2001 (article)

mms

[BibTex]

[BibTex]


no image
From the electronic structure to the macroscopic behaviour: a multi-scale analysis of plasticity in intermetallic compounds

Fähnle, M., Kohlhammer, S., Bester, G.

In Influences of Interface and Dislocation Behavior on Microstructure Evolution, 652, pages: Y.4.5.1-Y.4.5.12, Materials Research Society Symposium Proceedings, MRS, Boston, Mass., 2001 (inproceedings)

mms

[BibTex]

[BibTex]


no image
Enhancement of the critical current density of YBa2Cu3O7-8-films by substracte irradiation

Leonhardt, S., Albrecht, J., Warthmann, R., Kronmüller, H.

In High-Tc Superconductors and Related Applications: Materials Science, Fundamental Properties, and Some Future Electronic Applications. Proceedings of the NATO Advanced Study Institute, 86, pages: 529-534, NATO Science Series 3. High Technology, Kluwer Academic Publishers, Albena, Bulgaria, 2001 (inproceedings)

mms

[BibTex]

[BibTex]


no image
Diffusion of 23Na and 35K in the eutectic melt Na0.32K0.69

Feinauer, A., Majer, G.

{Physical Review B}, 64, 2001 (article)

mms

[BibTex]

[BibTex]


no image
AMOC studies of positronium in fine MgO powder

van Waeyenberge, B., Dauwe, C., Stoll, H.

In Positron Annihilation. Proceedings of the 12th International Conference on Positron Annihilation, 363/365, pages: 401-403, Materials Science Forum, Trans Tech Publications Ltd., München, 2001 (inproceedings)

mms

[BibTex]

[BibTex]


no image
Influence of nanocrystallization on the evolution of domain patterns and the magnetoimpedance effect in amorphous Fe73.5Cu1Nb3Si13.5B9 ribbons

Guo, H. Q., Kronmüller, H., Dragon, T., Cheng, Z. H., Shen, B. G.

{Journal of Applied Physics}, 89(1):514-520, 2001 (article)

mms

[BibTex]

[BibTex]


no image
Ab-initio statistical mechanics for the phase diagram of NiAl including the effect of vacancies

Lechermann, F., Fähnle, M.

{Physica Status Solidi (B)}, 224, pages: R4-R6, 2001 (article)

mms

[BibTex]

[BibTex]


no image
Atomic defects and electronic structure of B2-FeAl, CoAl and NiAl

Fähnle, M., Meyer, B., Bester, G., Majer, J., Börnsen, N.

In Proceedings of DIMAT 2000, the Fifth International Conference on Diffusion in Materials, 194/199, pages: 279-285, Defect and Diffusion Forum, Scitec Publications Ltd., Paris, France, 2001 (inproceedings)

mms

[BibTex]

[BibTex]

1997


no image
Locally weighted learning

Atkeson, C. G., Moore, A. W., Schaal, S.

Artificial Intelligence Review, 11(1-5):11-73, 1997, clmc (article)

Abstract
This paper surveys locally weighted learning, a form of lazy learning and memory-based learning, and focuses on locally weighted linear regression. The survey discusses distance functions, smoothing parameters, weighting functions, local model structures, regularization of the estimates and bias, assessing predictions, handling noisy data and outliers, improving the quality of predictions by tuning fit parameters, interference between old and new data, implementing locally weighted learning efficiently, and applications of locally weighted learning. A companion paper surveys how locally weighted learning can be used in robot learning and control. Keywords: locally weighted regression, LOESS, LWR, lazy learning, memory-based learning, least commitment learning, distance functions, smoothing parameters, weighting functions, global tuning, local tuning, interference.

am

link (url) [BibTex]

1997


link (url) [BibTex]


no image
Locally weighted learning for control

Atkeson, C. G., Moore, A. W., Schaal, S.

Artificial Intelligence Review, 11(1-5):75-113, 1997, clmc (article)

Abstract
Lazy learning methods provide useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of complex systems. This paper surveys ways in which locally weighted learning, a type of lazy learning, has been applied by us to control tasks. We explain various forms that control tasks can take, and how this affects the choice of learning paradigm. The discussion section explores the interesting impact that explicitly remembering all previous experiences has on the problem of learning to control. Keywords: locally weighted regression, LOESS, LWR, lazy learning, memory-based learning, least commitment learning, forward models, inverse models, linear quadratic regulation (LQR), shifting setpoint algorithm, dynamic programming.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning from demonstration

Schaal, S.

In Advances in Neural Information Processing Systems 9, pages: 1040-1046, (Editors: Mozer, M. C.;Jordan, M.;Petsche, T.), MIT Press, Cambridge, MA, 1997, clmc (inproceedings)

Abstract
By now it is widely accepted that learning a task from scratch, i.e., without any prior knowledge, is a daunting undertaking. Humans, however, rarely attempt to learn from scratch. They extract initial biases as well as strategies how to approach a learning problem from instructions and/or demonstrations of other humans. For learning control, this paper investigates how learning from demonstration can be applied in the context of reinforcement learning. We consider priming the Q-function, the value function, the policy, and the model of the task dynamics as possible areas where demonstrations can speed up learning. In general nonlinear learning problems, only model-based reinforcement learning shows significant speed-up after a demonstration, while in the special case of linear quadratic regulator (LQR) problems, all methods profit from the demonstration. In an implementation of pole balancing on a complex anthropomorphic robot arm, we demonstrate that, when facing the complexities of real signal processing, model-based reinforcement learning offers the most robustness for LQR problems. Using the suggested methods, the robot learns pole balancing in just a single trial after a 30 second long demonstration of the human instructor. 

am

link (url) [BibTex]

link (url) [BibTex]


no image
Robot learning from demonstration

Atkeson, C. G., Schaal, S.

In Machine Learning: Proceedings of the Fourteenth International Conference (ICML ’97), pages: 12-20, (Editors: Fisher Jr., D. H.), Morgan Kaufmann, Nashville, TN, July 8-12, 1997, 1997, clmc (inproceedings)

Abstract
The goal of robot learning from demonstration is to have a robot learn from watching a demonstration of the task to be performed. In our approach to learning from demonstration the robot learns a reward function from the demonstration and a task model from repeated attempts to perform the task. A policy is computed based on the learned reward function and task model. Lessons learned from an implementation on an anthropomorphic robot arm using a pendulum swing up task include 1) simply mimicking demonstrated motions is not adequate to perform this task, 2) a task planner can use a learned model and reward function to compute an appropriate policy, 3) this model-based planning process supports rapid learning, 4) both parametric and nonparametric models can be learned and used, and 5) incorporating a task level direct learning component, which is non-model-based, in addition to the model-based planner, is useful in compensating for structural modeling errors and slow model learning. 

am

link (url) [BibTex]

link (url) [BibTex]


no image
Local dimensionality reduction for locally weighted learning

Vijayakumar, S., Schaal, S.

In International Conference on Computational Intelligence in Robotics and Automation, pages: 220-225, Monteray, CA, July10-11, 1997, 1997, clmc (inproceedings)

Abstract
Incremental learning of sensorimotor transformations in high dimensional spaces is one of the basic prerequisites for the success of autonomous robot devices as well as biological movement systems. So far, due to sparsity of data in high dimensional spaces, learning in such settings requires a significant amount of prior knowledge about the learning task, usually provided by a human expert. In this paper we suggest a partial revision of the view. Based on empirical studies, it can been observed that, despite being globally high dimensional and sparse, data distributions from physical movement systems are locally low dimensional and dense. Under this assumption, we derive a learning algorithm, Locally Adaptive Subspace Regression, that exploits this property by combining a local dimensionality reduction as a preprocessing step with a nonparametric learning technique, locally weighted regression. The usefulness of the algorithm and the validity of its assumptions are illustrated for a synthetic data set and data of the inverse dynamics of an actual 7 degree-of-freedom anthropomorphic robot arm.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning tasks from a single demonstration

Atkeson, C. G., Schaal, S.

In IEEE International Conference on Robotics and Automation (ICRA97), 2, pages: 1706-1712, Piscataway, NJ: IEEE, Albuquerque, NM, 20-25 April, 1997, clmc (inproceedings)

Abstract
Learning a complex dynamic robot manoeuvre from a single human demonstration is difficult. This paper explores an approach to learning from demonstration based on learning an optimization criterion from the demonstration and a task model from repeated attempts to perform the task, and using the learned criterion and model to compute an appropriate robot movement. A preliminary version of the approach has been implemented on an anthropomorphic robot arm using a pendulum swing up task as an example

am

link (url) [BibTex]

link (url) [BibTex]

1996


no image
A kendama learning robot based on a dynamic optimiation principle

Miyamoto, H., Gandolfo, F., Gomi, H., Schaal, S., Koike, Y., Rieka, O., Nakano, E., Wada, Y., Kawato, M.

In Preceedings of the International Conference on Neural Information Processing, pages: 938-942, Hong Kong, September 1996, clmc (inproceedings)

am

[BibTex]

1996


[BibTex]


no image
Incorporating invariances in support vector learning machines

Schölkopf, B., Burges, C., Vapnik, V.

In Artificial Neural Networks: ICANN 96, LNCS vol. 1112, pages: 47-52, (Editors: C von der Malsburg and W von Seelen and JC Vorbrüggen and B Sendhoff), Springer, Berlin, Germany, 6th International Conference on Artificial Neural Networks, July 1996, volume 1112 of Lecture Notes in Computer Science (inproceedings)

Abstract
Developed only recently, support vector learning machines achieve high generalization ability by minimizing a bound on the expected test error; however, so far there existed no way of adding knowledge about invariances of a classification problem at hand. We present a method of incorporating prior knowledge about transformation invariances by applying transformations to support vectors, the training examples most critical for determining the classification boundary.

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
A Kendama learning robot based on bi-directional theory

Miyamoto, H., Schaal, S., Gandolfo, F., Koike, Y., Osu, R., Nakano, E., Wada, Y., Kawato, M.

Neural Networks, 9(8):1281-1302, 1996, clmc (article)

Abstract
A general theory of movement-pattern perception based on bi-directional theory for sensory-motor integration can be used for motion capture and learning by watching in robotics. We demonstrate our methods using the game of Kendama, executed by the SARCOS Dextrous Slave Arm, which has a very similar kinematic structure to the human arm. Three ingredients have to be integrated for the successful execution of this task. The ingredients are (1) to extract via-points from a human movement trajectory using a forward-inverse relaxation model, (2) to treat via-points as a control variable while reconstructing the desired trajectory from all the via-points, and (3) to modify the via-points for successful execution. In order to test the validity of the via-point representation, we utilized a numerical model of the SARCOS arm, and examined the behavior of the system under several conditions.

am

link (url) [BibTex]

link (url) [BibTex]


no image
From isolation to cooperation: An alternative of a system of experts

Schaal, S., Atkeson, C. G.

In Advances in Neural Information Processing Systems 8, pages: 605-611, (Editors: Touretzky, D. S.;Mozer, M. C.;Hasselmo, M. E.), MIT Press, Cambridge, MA, 1996, clmc (inbook)

Abstract
We introduce a constructive, incremental learning system for regression problems that models data by means of locally linear experts. In contrast to other approaches, the experts are trained independently and do not compete for data during learning. Only when a prediction for a query is required do the experts cooperate by blending their individual predictions. Each expert is trained by minimizing a penalized local cross validation error using second order methods. In this way, an expert is able to adjust the size and shape of the receptive field in which its predictions are valid, and also to adjust its bias on the importance of individual input dimensions. The size and shape adjustment corresponds to finding a local distance metric, while the bias adjustment accomplishes local dimensionality reduction. We derive asymptotic results for our method. In a variety of simulations we demonstrate the properties of the algorithm with respect to interference, learning speed, prediction accuracy, feature detection, and task oriented incremental learning. 

am

link (url) [BibTex]

link (url) [BibTex]


no image
One-handed juggling: A dynamical approach to a rhythmic movement task

Schaal, S., Sternad, D., Atkeson, C. G.

Journal of Motor Behavior, 28(2):165-183, 1996, clmc (article)

Abstract
The skill of rhythmic juggling a ball on a racket is investigated from the viewpoint of nonlinear dynamics. The difference equations that model the dynamical system are analyzed by means of local and non-local stability analyses. These analyses yield that the task dynamics offer an economical juggling pattern which is stable even for open-loop actuator motion. For this pattern, two types of pre dictions are extracted: (i) Stable periodic bouncing is sufficiently characterized by a negative acceleration of the racket at the moment of impact with the ball; (ii) A nonlinear scaling relation maps different juggling trajectories onto one topologically equivalent dynamical system. The relevance of these results for the human control of action was evaluated in an experiment where subjects performed a comparable task of juggling a ball on a paddle. Task manipulations involved different juggling heights and gravity conditions of the ball. The predictions were confirmed: (i) For stable rhythmic performance the paddle's acceleration at impact is negative and fluctuations of the impact acceleration follow predictions from global stability analysis; (ii) For each subject, the realizations of juggling for the different experimental conditions are related by the scaling relation. These results allow the conclusion that for the given task, humans reliably exploit the stable solutions inherent to the dynamics of the task and do not overrule these dynamics by other control mechanisms. The dynamical scaling serves as an efficient principle to generate different movement realizations from only a few parameter changes and is discussed as a dynamical formalization of the principle of motor equivalence.

am

link (url) [BibTex]

link (url) [BibTex]