Header logo is


2011


no image
Fast Convergent Algorithms for Expectation Propagation Approximate Bayesian Inference

Seeger, M., Nickisch, H.

In JMLR Workshop and Conference Proceedings Volume 15: AISTATS 2011, pages: 652-660, (Editors: Gordon, G. , D. Dunson, M. Dudík ), MIT Press, Cambridge, MA, USA, 14th International Conference on Artificial Intelligence and Statistics, April 2011 (inproceedings)

Abstract
We propose a novel algorithm to solve the expectation propagation relaxation of Bayesian inference for continuous-variable graphical models. In contrast to most previous algorithms, our method is provably convergent. By marrying convergent EP ideas from (Opper&Winther, 2005) with covariance decoupling techniques (Wipf&Nagarajan, 2008; Nickisch&Seeger, 2009), it runs at least an order of magnitude faster than the most common EP solver.

ei

PDF Web [BibTex]

2011


PDF Web [BibTex]


no image
Active Exploration for Robot Parameter Selection in Episodic Reinforcement Learning

Kroemer, O., Peters, J.

In Proceedings of the 2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL 2011), pages: 25-31, IEEE, Piscataway, NJ, USA, IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), April 2011 (inproceedings)

Abstract
As the complexity of robots and other autonomous systems increases, it becomes more important that these systems can adapt and optimize their settings actively. However, such optimization is rarely trivial. Sampling from the system is often expensive in terms of time and other costs, and excessive sampling should therefore be avoided. The parameter space is also usually continuous and multi-dimensional. Given the inherent exploration-exploitation dilemma of the problem, we propose treating it as an episodic reinforcement learning problem. In this reinforcement learning framework, the policy is defined by the system's parameters and the rewards are given by the system's performance. The rewards accumulate during each episode of a task. In this paper, we present a method for efficiently sampling and optimizing in continuous multidimensional spaces. The approach is based on Gaussian process regression, which can represent continuous non-linear mappings from parameters to system performance. We employ an upper confidence bound policy, which explicitly manages the trade-off between exploration and exploitation. Unlike many other policies for this kind of problem, we do not rely on a discretization of the action space. The presented method was evaluated on a real robot. The robot had to learn grasping parameters in order to adapt its grasping execution to different objects. The proposed method was also tested on a more general gain tuning problem. The results of the experiments show that the presented method can quickly determine suitable parameters and is applicable to real online learning applications.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Relative Entropy Inverse Reinforcement Learning

Boularias, A., Kober, J., Peters, J.

In JMLR Workshop and Conference Proceedings Volume 15: AISTATS 2011, pages: 182-189, (Editors: Gordon, G. , D. Dunson, M. Dudík ), MIT Press, Cambridge, MA, USA, Fourteenth International Conference on Artificial Intelligence and Statistics, April 2011 (inproceedings)

Abstract
We consider the problem of imitation learning where the examples, demonstrated by an expert, cover only a small part of a large state space. Inverse Reinforcement Learning (IRL) provides an efficient tool for generalizing the demonstration, based on the assumption that the expert is optimally acting in a Markov Decision Process (MDP). Most of the past work on IRL requires that a (near)-optimal policy can be computed for different reward functions. However, this requirement can hardly be satisfied in systems with a large, or continuous, state space. In this paper, we propose a model-free IRL algorithm, where the relative entropy between the empirical distribution of the state-action trajectories under a uniform policy and their distribution under the learned policy is minimized by stochastic gradient descent. We compare this new approach to well-known IRL algorithms using approximate MDP models. Empirical results on simulated car racing, gridworld and ball-in-a-cup problems show that our approach is able to learn good policies from a small number of demonstrations.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Removing noise from astronomical images using a pixel-specific noise model

Burger, H., Schölkopf, B., Harmeling, S.

In pages: 8, (Editors: H Lensch and SL Narasimhan and ME Testorf), IEEE, Piscataway, NJ, USA, IEEE International Conference on Computational Photography (ICCP), April 2011 (inproceedings)

Abstract
For digital photographs of astronomical objects, where exposure times are usually long and ISO settings high, the so-called dark-current is a significant source of noise. Dark-current refers to thermally generated electrons and is therefore present even in the absence of light. This paper presents a novel approach for denoising astronomical images that have been corrupted by dark-current noise. Our method relies on a probabilistic description of the dark-current of each pixel of a given camera. The noise model is then combined with an image prior which is adapted to astronomical images. In a laboratory environment, we use a black and white CCD camera containing a cooling unit and show that our method is superior to existing methods in terms of root mean squared error. Furthermore, we show that our method is practically relevant by providing visually more appealing results on astronomical photographs taken with a single lens reflex CMOS camera.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Towards Motor Skill Learning for Robotics

Peters, J., Mülling, K., Kober, J., Nguyen-Tuong, D., Kroemer, O.

In Robotics Research, pages: 469-482, (Editors: Pradalier, C. , R. Siegwart, G. Hirzinger), Springer, Berlin, Germany, 14th International Symposium on Robotics Research (ISRR), January 2011 (inproceedings)

Abstract
Learning robots that can acquire new motor skills and refine existing one has been a long standing vision of robotics, artificial intelligence, and the cognitive sciences. Early steps towards this goal in the 1980s made clear that reasoning and human insights will not suffice. Instead, new hope has been offered by the rise of modern machine learning approaches. However, to date, it becomes increasingly clear that off-the-shelf machine learning approaches will not suffice for motor skill learning as these methods often do not scale into the high-dimensional domains of manipulator and humanoid robotics nor do they fulfill the real-time requirement of our domain. As an alternative, we propose to break the generic skill learning problem into parts that we can understand well from a robotics point of view. After designing appropriate learning approaches for these basic components, these will serve as the ingredients of a general approach to motor skill learning. In this paper, we discuss our recent and current progress in this direction. For doing so, we present our work on learning to control, on learning elementary movements as well as our steps towards learning of complex tasks. We show several evaluations both using real robots as well as physically realistic simulations.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Learning Visual Representations for Interactive Systems

Piater, J., Jodogne, S., Detry, R., Kraft, D., Krüger, N., Kroemer, O., Peters, J.

In Robotics Research, pages: 399-416, (Editors: Pradalier, C. , R. Siegwart, G. Hirzinger), Springer, Berlin, Germany, 14th International Symposium on Robotics Research (ISRR), January 2011 (inproceedings)

Abstract
We describe two quite different methods for associating action parameters to visual percepts. Our RLVC algorithm performs reinforcement learning directly on the visual input space. To make this very large space manageable, RLVC interleaves the reinforcement learner with a supervised classification algorithm that seeks to split perceptual states so as to reduce perceptual aliasing. This results in an adaptive discretization of the perceptual space based on the presence or absence of visual features. Its extension RLJC also handles continuous action spaces. In contrast to the minimalistic visual representations produced by RLVC and RLJC, our second method learns structural object models for robust object detection and pose estimation by probabilistic inference. To these models, the method associates grasp experiences autonomously learned by trial and error. These experiences form a non-parametric representation of grasp success likelihoods over gripper poses, which we call a gra sp d ensi ty. Thus, object detection in a novel scene simultaneously produces suitable grasping options.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
A Non-Parametric Approach to Dynamic Programming

Kroemer, O., Peters, J.

In Advances in Neural Information Processing Systems 24, pages: 1719-1727, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
In this paper, we consider the problem of policy evaluation for continuousstate systems. We present a non-parametric approach to policy evaluation, which uses kernel density estimation to represent the system. The true form of the value function for this model can be determined, and can be computed using Galerkin’s method. Furthermore, we also present a unified view of several well-known policy evaluation methods. In particular, we show that the same Galerkin method can be used to derive Least-Squares Temporal Difference learning, Kernelized Temporal Difference learning, and a discrete-state Dynamic Programming solution, as well as our proposed method. In a numerical evaluation of these algorithms, the proposed approach performed better than the other methods.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Transfer Learning with Copulas

Lopez-Paz, D., Hernandez-Lobato, J.

In pages: 2, NIPS, Workshop on Copulas in Machine Learning, 2011 (inproceedings)

ei

PDF [BibTex]

PDF [BibTex]


no image
Denoising sparse noise via online dictionary learning

Cherian, A., Sra, S., Papanikolopoulos, N.

In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2011, pages: 2060 -2063, IEEE, IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2011 (inproceedings)

ei

DOI [BibTex]

DOI [BibTex]


no image
PILCO: A Model-Based and Data-Efficient Approach to Policy Search

Deisenroth, MP., Rasmussen, CE.

In Proceedings of the 28th International Conference on Machine Learning, ICML 2011, pages: 465-472, (Editors: L Getoor and T Scheffer), Omnipress, 2011 (inproceedings)

Abstract
In this paper, we introduce PILCO, a practical, data-efficient model-based policy search method. PILCO reduces model bias, one of the key problems of model-based reinforcement learning, in a principled way. By learning a probabilistic dynamics model and explicitly incorporating model uncertainty into long-term planning, PILCO can cope with very little data and facilitates learning from scratch in only a few trials. Policy evaluation is performed in closed form using state-of-the-art approximate inference. Furthermore, policy gradients are computed analytically for policy improvement. We report unprecedented learning efficiency on challenging and high-dimensional control tasks.

ei

Web [BibTex]

Web [BibTex]


no image
Kernel Bayes’ Rule

Fukumizu, K., Song, L., Gretton, A.

In Advances in Neural Information Processing Systems 24, pages: 1737-1745, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Curran Associates, Inc., Red Hook, NY, USA, Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

ei

PDF [BibTex]

PDF [BibTex]


no image
Optimal Reinforcement Learning for Gaussian Systems

Hennig, P.

In Advances in Neural Information Processing Systems 24, pages: 325-333, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
The exploration-exploitation trade-off is among the central challenges of reinforcement learning. The optimal Bayesian solution is intractable in general. This paper studies to what extent analytic statements about optimal learning are possible if all beliefs are Gaussian processes. A first order approximation of learning of both loss and dynamics, for nonlinear, time-varying systems in continuous time and space, subject to a relatively weak restriction on the dynamics, is described by an infinite-dimensional partial differential equation. An approximate finitedimensional projection gives an impression for how this result may be helpful.

ei pn

PDF Web [BibTex]

PDF Web [BibTex]


no image
Efficient inference in matrix-variate Gaussian models with iid observation noise

Stegle, O., Lippert, C., Mooij, J., Lawrence, N., Borgwardt, K.

In Advances in Neural Information Processing Systems 24, pages: 630-638, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
Inference in matrix-variate Gaussian models has major applications for multioutput prediction and joint learning of row and column covariances from matrixvariate data. Here, we discuss an approach for efficient inference in such models that explicitly account for iid observation noise. Computational tractability can be retained by exploiting the Kronecker product between row and column covariance matrices. Using this framework, we show how to generalize the Graphical Lasso in order to learn a sparse inverse covariance between features while accounting for a low-rank confounding covariance between samples. We show practical utility on applications to biology, where we model covariances with more than 100,000 dimensions. We find greater accuracy in recovering biological network structures and are able to better reconstruct the confounders.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Expectation Propagation for the Estimation of Conditional Bivariate Copulas

Hernandez-Lobato, J., Lopez-Paz, D., Gharhamani, Z.

In pages: 2, NIPS, Workshop on Copulas in Machine Learning, 2011 (inproceedings)

ei

PDF [BibTex]

PDF [BibTex]


no image
Efficient Similarity Search for Covariance Matrices via the Jensen-Bregman LogDet Divergence

Cherian, A., Sra, S., Banerjee, A., Papanikolopoulos, N.

In IEEE International Conference on Computer Vision, ICCV 2011, pages: 2399-2406, (Editors: DN Metaxas and L Quan and A Sanfeliu and LJ Van Gool), IEEE, 13th International Conference on Computer Vision (ICCV), 2011 (inproceedings)

ei

DOI [BibTex]

DOI [BibTex]


no image
Introducing the detection of auditory error responses based on BCI technology for passive interaction

Zander, TO., Klippel, DM., Scherer, R.

In Proceedings of the 5th International Brain–Computer Interface Conference, pages: 252-255, (Editors: GR Müller-Putz and R Scherer and M Billinger and A Kreilinger and V Kaiser and C Neuper), Graz: Verlag der Technischen Universität, 2011 (inproceedings)

ei

[BibTex]

[BibTex]


no image
Generalized Dictionary Learning for Symmetric Positive Definite Matrices with Application to Nearest Neighbor Retrieval

Sra, S., Cherian, A.

In Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2011, LNCS vol 6913, Part III, pages: 318-332, (Editors: D Gunopulos and T Hofmann and D Malerba and M Vazirgiannis), Springer, 22th European Conference on Machine Learning (ECML), 2011 (inproceedings)

ei

DOI [BibTex]

DOI [BibTex]


no image
Restricted boltzmann machines as useful tool for detecting oscillatory eeg components

Balderas, D., Zander, TO., Bachl, F., Neuper, C., Scherer, R.

In Proceedings of the 5th International Brain–Computer Interface Conference, pages: 68-71, (Editors: GR Müller-Putz and R Scherer and M Billinger and A Kkreilinger and V Kaiser and C Neuper), Graz: Verlag der Technischen Universität, 2011 (inproceedings)

ei

[BibTex]

[BibTex]


no image
Hierarchical Multitask Structured Output Learning for Large-scale Sequence Segmentation

Görnitz, N., Widmer, C., Zeller, G., Kahles, A., Sonnenburg, S., Rätsch, G.

In Advances in Neural Information Processing Systems 24, pages: 2690-2698, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and FCN Pereira and KQ Weinberger), Curran Associates, Inc., Red Hook, NY, USA, Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

ei

PDF [BibTex]

PDF [BibTex]


no image
Phase transition in the family of p-resistances

Alamgir, M., von Luxburg, U.

In Advances in Neural Information Processing Systems 24, pages: 379-387, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
We study the family of p-resistances on graphs for p ≥ 1. This family generalizes the standard resistance distance. We prove that for any fixed graph, for p=1, the p-resistance coincides with the shortest path distance, for p=2 it coincides with the standard resistance distance, and for p → ∞ it converges to the inverse of the minimal s-t-cut in the graph. Secondly, we consider the special case of random geometric graphs (such as k-nearest neighbor graphs) when the number n of vertices in the graph tends to infinity. We prove that an interesting phase-transition takes place. There exist two critical thresholds p^* and p^** such that if p < p^*, then the p-resistance depends on meaningful global properties of the graph, whereas if p > p^**, it only depends on trivial local quantities and does not convey any useful information. We can explicitly compute the critical values: p^* = 1 + 1/(d-1) and p^** = 1 + 1/(d-2) where d is the dimension of the underlying space (we believe that the fact that there is a small gap between p^* and p^** is an artifact of our proofs. We also relate our findings to Laplacian regularization and suggest to use q-Laplacians as regularizers, where q satisfies 1/p^* + 1/q = 1.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
On Fast Approximate Submodular Minimization

Jegelka, S., Lin, H., Bilmes, J.

In Advances in Neural Information Processing Systems 24, pages: 460-468, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
We are motivated by an application to extract a representative subset of machine learning training data and by the poor empirical performance we observe of the popular minimum norm algorithm. In fact, for our application, minimum norm can have a running time of about O(n7) (O(n5) oracle calls). We therefore propose a fast approximate method to minimize arbitrary submodular functions. For a large sub-class of submodular functions, the algorithm is exact. Other submodular functions are iteratively approximated by tight submodular upper bounds, and then repeatedly optimized. We show theoretical properties, and empirical results suggest significant speedups over minimum norm while retaining higher accuracies.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
PAC-Bayesian Analysis of Contextual Bandits

Seldin, Y., Auer, P., Laviolette, F., Shawe-Taylor, J., Ortner, R.

In Advances in Neural Information Processing Systems 24, pages: 1683-1691, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
We derive an instantaneous (per-round) data-dependent regret bound for stochastic multiarmed bandits with side information (also known as contextual bandits). The scaling of our regret bound with the number of states (contexts) $N$ goes as $\sqrt{N I_{\rho_t}(S;A)}$, where $I_{\rho_t}(S;A)$ is the mutual information between states and actions (the side information) used by the algorithm at round $t$. If the algorithm uses all the side information, the regret bound scales as $\sqrt{N \ln K}$, where $K$ is the number of actions (arms). However, if the side information $I_{\rho_t}(S;A)$ is not fully used, the regret bound is significantly tighter. In the extreme case, when $I_{\rho_t}(S;A) = 0$, the dependence on the number of states reduces from linear to logarithmic. Our analysis allows to provide the algorithm large amount of side information, let the algorithm to decide which side information is relevant for the task, and penalize the algorithm only for the side information that it is using de facto. We also present an algorithm for multiarmed bandits with side information with computational complexity that is a linear in the number of actions.

ei

PDF PDF Web [BibTex]

PDF PDF Web [BibTex]


no image
Fast projections onto L1,q-norm balls for grouped feature selection

Sra, S.

In Machine Learning and Knowledge Discovery in Databases - European Conference, ECML PKDD 2011, LNCS vol 6913, Part III, pages: 305-317, (Editors: D Gunopulos and T Hofmann and D Malerba and M Vazirgiannis), Springer, 22th European Conference on Machine Learning (ECML), 2011 (inproceedings)

ei

DOI [BibTex]

DOI [BibTex]


no image
Kernel Belief Propagation

Song, L., Gretton, A., Bickson, D., Low, Y., Guestrin, C.

In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, Vol. 15, pages: 707-715, (Editors: G Gordon and D Dunson and M Dudík), JMLR, AISTATS, 2011 (inproceedings)

ei

PDF [BibTex]

PDF [BibTex]


no image
On Causal Discovery with Cyclic Additive Noise Models

Mooij, J., Janzing, D., Schölkopf, B., Heskes, T.

In Advances in Neural Information Processing Systems 24, pages: 639-647, (Editors: J Shawe-Taylor and RS Zemel and PL Bartlett and FCN Pereira and KQ Weinberger), Curran Associates, Inc., Red Hook, NY, USA, Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
We study a particular class of cyclic causal models, where each variable is a (possibly nonlinear) function of its parents and additive noise. We prove that the causal graph of such models is generically identifiable in the bivariate, Gaussian-noise case. We also propose a method to learn such models from observational data. In the acyclic case, the method reduces to ordinary regression, but in the more challenging cyclic case, an additional term arises in the loss function, which makes it a special case of nonlinear independent component analysis. We illustrate the proposed method on synthetic data.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Additive Gaussian Processes

Duvenaud, D., Nickisch, H., Rasmussen, C.

In Advances in Neural Information Processing Systems 24, pages: 226-234, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
We introduce a Gaussian process model of functions which are additive. An additive function is one which decomposes into a sum of low-dimensional functions, each depending on only a subset of the input variables. Additive GPs generalize both Generalized Additive Models, and the standard GP models which use squared-exponential kernels. Hyperparameter learning in this model can be seen as Bayesian Hierarchical Kernel Learning (HKL). We introduce an expressive but tractable parameterization of the kernel function, which allows efficient evaluation of all input interaction terms, whose number is exponential in the input dimension. The additional structure discoverable by this model results in increased interpretability, as well as state-of-the-art predictive power in regression tasks.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
k-NN Regression Adapts to Local Intrinsic Dimension

Kpotufe, S.

In Advances in Neural Information Processing Systems 24, pages: 729-737, (Editors: J Shawe-Taylor and RS Zemel and P Bartlett and F Pereira and KQ Weinberger), Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
Many nonparametric regressors were recently shown to converge at rates that depend only on the intrinsic dimension of data. These regressors thus escape the curse of dimension when high-dimensional data has low intrinsic dimension (e.g. a manifold). We show that k-NN regression is also adaptive to intrinsic dimension. In particular our rates are local to a query x and depend only on the way masses of balls centered at x vary with radius. Furthermore, we show a simple way to choose k = k(x) locally at any x so as to nearly achieve the minimax rate at x in terms of the unknown intrinsic dimension in the vicinity of x. We also establish that the minimax rate does not depend on a particular choice of metric space or distribution, but rather that this minimax rate holds for any metric space and doubling measure.

ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
Fast Newton-type Methods for Total-Variation with Applications

Barbero, A., Sra, S.

In Proceedings of the 28th International Conference on Machine Learning, ICML 2011, pages: 313-320, (Editors: L Getoor and T Scheffer), Omnipress, 28th International Conference on Machine Learning (ICML), 2011 (inproceedings)

ei

[BibTex]

[BibTex]


no image
Parallel Gibbs Sampling: From Colored Fields to Thin Junction Trees

Gonzalez, J., Low, Y., Gretton, A., Guestrin, C.

In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics, Vol. 15, pages: 324-332, (Editors: G Gordon and D Dunson and M Dudík), JMLR, AISTATS, 2011 (inproceedings)

ei

PDF [BibTex]

PDF [BibTex]


no image
STOMP: Stochastic trajectory optimization for motion planning

Kalakrishnan, M., Chitta, S., Theodorou, E., Pastor, P., Schaal, S.

In IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China, May 9-13, 2011, clmc (inproceedings)

Abstract
We present a new approach to motion planning using a stochastic trajectory optimization framework. The approach relies on generating noisy trajectories to explore the space around an initial (possibly infeasible) trajectory, which are then combined to produced an updated trajectory with lower cost. A cost function based on a combination of obstacle and smoothness cost is optimized in each iteration. No gradient information is required for the particular optimization algorithm that we use and so general costs for which derivatives may not be available (e.g. costs corresponding to constraints and motor torques) can be included in the cost function. We demonstrate the approach both in simulation and on a dual-arm mobile manipulation system for unconstrained and constrained tasks. We experimentally show that the stochastic nature of STOMP allows it to overcome local minima that gradient-based optimizers like CHOMP can get stuck in.

am

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


Thumb xl problem
Recovering Intrinsic Images with a Global Sparsity Prior on Reflectance

Gehler, P., Rother, C., Kiefel, M., Zhang, L., Schölkopf, B.

In Advances in Neural Information Processing Systems 24, pages: 765-773, (Editors: Shawe-Taylor, John and Zemel, Richard S. and Bartlett, Peter L. and Pereira, Fernando C. N. and Weinberger, Kilian Q.), Curran Associates, Inc., Red Hook, NY, USA, Twenty-Fifth Annual Conference on Neural Information Processing Systems (NIPS), 2011 (inproceedings)

Abstract
We address the challenging task of decoupling material properties from lighting properties given a single image. In the last two decades virtually all works have concentrated on exploiting edge information to address this problem. We take a different route by introducing a new prior on reflectance, that models reflectance values as being drawn from a sparse set of basis colors. This results in a Random Field model with global, latent variables (basis colors) and pixel-accurate output reflectance values. We show that without edge information high-quality results can be achieved, that are on par with methods exploiting this source of information. Finally, we are able to improve on state-of-the-art results by integrating edge information into our model. We believe that our new approach is an excellent starting point for future developments in this field.

ei ps

website + code pdf poster Project Page Project Page [BibTex]

website + code pdf poster Project Page Project Page [BibTex]


no image
Path Integral Control and Bounded Rationality

Braun, D. A., Ortega, P. A., Theodorou, E., Schaal, S.

In IEEE Symposium on Adaptive Dynamic Programming And Reinforcement Learning (ADPRL), 2011, clmc (inproceedings)

Abstract
Path integral methods [7], [15],[1] have recently been shown to be applicable to a very general class of optimal control problems. Here we examine the path integral formalism from a decision-theoretic point of view, since an optimal controller can always be regarded as an instance of a perfectly rational decision-maker that chooses its actions so as to maximize its expected utility [8]. The problem with perfect rationality is, however, that finding optimal actions is often very difficult due to prohibitive computational resource costs that are not taken into account. In contrast, a bounded rational decision-maker has only limited resources and therefore needs to strike some compromise between the desired utility and the required resource costs [14]. In particular, we suggest an information-theoretic measure of resource costs that can be derived axiomatically [11]. As a consequence we obtain a variational principle for choice probabilities that trades off maximizing a given utility criterion and avoiding resource costs that arise due to deviating from initially given default choice probabilities. The resulting bounded rational policies are in general probabilistic. We show that the solutions found by the path integral formalism are such bounded rational policies. Furthermore, we show that the same formalism generalizes to discrete control problems, leading to linearly solvable bounded rational control policies in the case of Markov systems. Importantly, Bellman?s optimality principle is not presupposed by this variational principle, but it can be derived as a limit case. This suggests that the information- theoretic formalization of bounded rationality might serve as a general principle in control design that unifies a number of recently reported approximate optimal control methods both in the continuous and discrete domain.

am

PDF [BibTex]

PDF [BibTex]


no image
Skill learning and task outcome prediction for manipulation

Pastor, P., Kalakrishnan, M., Chitta, S., Theodorou, E., Schaal, S.

In IEEE International Conference on Robotics and Automation (ICRA), Shanghai, China, May 9-13, 2011, clmc (inproceedings)

Abstract
Learning complex motor skills for real world tasks is a hard problem in robotic manipulation that often requires painstaking manual tuning and design by a human expert. In this work, we present a Reinforcement Learning based approach to acquiring new motor skills from demonstration. Our approach allows the robot to learn fine manipulation skills and significantly improve its success rate and skill level starting from a possibly coarse demonstration. Our approach aims to incorporate task domain knowledge, where appropriate, by working in a space consistent with the constraints of a specific task. In addition, we also present an approach to using sensor feedback to learn a predictive model of the task outcome. This allows our system to learn the proprioceptive sensor feedback needed to monitor subsequent executions of the task online and abort execution in the event of predicted failure. We illustrate our approach using two example tasks executed with the PR2 dual-arm robot: a straight and accurate pool stroke and a box flipping task using two chopsticks as tools.

am

link (url) Project Page Project Page [BibTex]

link (url) Project Page Project Page [BibTex]


no image
An Iterative Path Integral Stochastic Optimal Control Approach for Learning Robotic Tasks

Theodorou, E., Stulp, F., Buchli, J., Schaal, S.

In Proceedings of the 18th World Congress of the International Federation of Automatic Control, 2011, clmc (inproceedings)

Abstract
Recent work on path integral stochastic optimal control theory Theodorou et al. (2010a); Theodorou (2011) has shown promising results in planning and control of nonlinear systems in high dimensional state spaces. The path integral control framework relies on the transformation of the nonlinear Hamilton Jacobi Bellman (HJB) partial differential equation (PDE) into a linear PDE and the approximation of its solution via the use of the Feynman Kac lemma. In this work, we are reviewing the generalized version of path integral stochastic optimal control formalism Theodorou et al. (2010a), used for optimal control and planing of stochastic dynamical systems with state dependent control and diffusion matrices. Moreover we present the iterative path integral control approach, the so called Policy Improvement with Path Integrals or (PI2 ) which is capable of scaling in high dimensional robotic control problems. Furthermore we present a convergence analysis of the proposed algorithm and we apply the proposed framework to a variety of robotic tasks. Finally with the goal to perform locomotion the iterative path integral control is applied for learning nonlinear limit cycle attractors with adjustable land scape.

am

PDF [BibTex]

PDF [BibTex]


Thumb xl fosterembs2011
Combining wireless neural recording and video capture for the analysis of natural gait

Foster, J., Freifeld, O., Nuyujukian, P., Ryu, S., Black, M. J., Shenoy, K.

In Proc. 5th Int. IEEE EMBS Conf. on Neural Engineering, pages: 613-616, IEEE, 2011 (inproceedings)

ps

pdf Project Page [BibTex]

pdf Project Page [BibTex]


no image
Design and analysis of a magnetically actuated and compliant capsule endoscopic robot

Yim, S., Sitti, M.

In Robotics and Automation (ICRA), 2011 IEEE International Conference on, pages: 4810-4815, 2011 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Micro-scale propulsion using multiple flexible artificial flagella

Singleton, J., Diller, E., Andersen, T., Regnier, S., Sitti, M.

In Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on, pages: 1687-1692, 2011 (inproceedings)

pi

Project Page [BibTex]

Project Page [BibTex]


no image
Amorphous grain boundary layers in the ferromagnetic nanograined ZnO films

Straumal, B. B., Mazilkin, A. A., Protasova, S. G., Myatiev, A. A., Straumal, P. B., Goering, E., Baretzky, B.

In 520, pages: 1192-1194, Hersonissos, Greece, 2011 (inproceedings)

mms

DOI [BibTex]

DOI [BibTex]


no image
Inversed solid-phase grain boundary wetting in the Al-Zn system

Protasova, S. G., Kogtenkova, O. A., Straumal, B. B., Zieba, P., Baretzky, B.

In 46, pages: 4349-4353, Mie, Japan, 2011 (inproceedings)

mms

DOI [BibTex]

DOI [BibTex]


no image
Control of multiple heterogeneous magnetic micro-robots on non-specialized surfaces

Diller, E., Floyd, S., Pawashe, C., Sitti, M.

In Robotics and Automation (ICRA), 2011 IEEE International Conference on, pages: 115-120, 2011 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Tip based robotic precision micro/nanomanipulation systems

Onal, C., Sumer, B., Ozcan, O., Nain, A., Sitti, M.

In SPIE Defense, Security, and Sensing, pages: 80580M-80580M, 2011 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Design of a miniature integrated multi-modal jumping and gliding robot

Woodward, M. A., Sitti, M.

In Intelligent Robots and Systems (IROS), 2011 IEEE/RSJ International Conference on, pages: 556-561, 2011 (inproceedings)

pi

Project Page [BibTex]

Project Page [BibTex]


no image
Movement segmentation using a primitive library

Meier, F., Theodorou, E., Stulp, F., Schaal, S.

In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), Sept. 25-30, San Francisco, CA, 2011, clmc (inproceedings)

Abstract
Segmenting complex movements into a sequence of primitives remains a difficult problem with many applications in the robotics and vision communities. In this work, we show how the movement segmentation problem can be reduced to a sequential movement recognition problem. To this end, we reformulate the orig-inal Dynamic Movement Primitive (DMP) formulation as a linear dynamical sys-tem with control inputs. Based on this new formulation, we develop an Expecta-tion-Maximization algorithm to estimate the duration and goal position of a par-tially observed trajectory. With the help of this algorithm and the assumption that a library of movement primitives is present, we present a movement seg-mentation framework. We illustrate the usefulness of the new DMP formulation on the two applications of online movement recognition and movement segmen-tation.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning Force Control Policies for Compliant Manipulation

Kalakrishnan, M., Righetti, L., Pastor, P., Schaal, S.

In 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 4639-4644, IEEE, San Francisco, USA, sep 2011 (inproceedings)

Abstract
Developing robots capable of fine manipulation skills is of major importance in order to build truly assistive robots. These robots need to be compliant in their actuation and control in order to operate safely in human environments. Manipulation tasks imply complex contact interactions with the external world, and involve reasoning about the forces and torques to be applied. Planning under contact conditions is usually impractical due to computational complexity, and a lack of precise dynamics models of the environment. We present an approach to acquiring manipulation skills on compliant robots through reinforcement learning. The initial position control policy for manipulation is initialized through kinesthetic demonstration. We augment this policy with a force/torque profile to be controlled in combination with the position trajectories. We use the Policy Improvement with Path Integrals (PI2) algorithm to learn these force/torque profiles by optimizing a cost function that measures task success. We demonstrate our approach on the Barrett WAM robot arm equipped with a 6-DOF force/torque sensor on two different manipulation tasks: opening a door with a lever door handle, and picking up a pen off the table. We show that the learnt force control policies allow successful, robust execution of the tasks.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Control of legged robots with optimal distribution of contact forces

Righetti, L., Buchli, J., Mistry, M., Schaal, S.

In 2011 11th IEEE-RAS International Conference on Humanoid Robots, pages: 318-324, IEEE, Bled, Slovenia, 2011 (inproceedings)

Abstract
The development of agile and safe humanoid robots require controllers that guarantee both high tracking performance and compliance with the environment. More specifically, the control of contact interaction is of crucial importance for robots that will actively interact with their environment. Model-based controllers such as inverse dynamics or operational space control are very appealing as they offer both high tracking performance and compliance. However, while widely used for fully actuated systems such as manipulators, they are not yet standard controllers for legged robots such as humanoids. Indeed such robots are fundamentally different from manipulators as they are underactuated due to their floating-base and subject to switching contact constraints. In this paper we present an inverse dynamics controller for legged robots that use torque redundancy to create an optimal distribution of contact constraints. The resulting controller is able to minimize, given a desired motion, any quadratic cost of the contact constraints at each instant of time. In particular we show how this can be used to minimize tangential forces during locomotion, therefore significantly improving the locomotion of legged robots on difficult terrains. In addition to the theoretical result, we present simulations of a humanoid and a quadruped robot, as well as experiments on a real quadruped robot that demonstrate the advantages of the controller.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Learning Motion Primitive Goals for Robust Manipulation

Stulp, F., Theodorou, E., Kalakrishnan, M., Pastor, P., Righetti, L., Schaal, S.

In IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 325-331, IEEE, San Francisco, USA, sep 2011 (inproceedings)

Abstract
Applying model-free reinforcement learning to manipulation remains challenging for several reasons. First, manipulation involves physical contact, which causes discontinuous cost functions. Second, in manipulation, the end-point of the movement must be chosen carefully, as it represents a grasp which must be adapted to the pose and shape of the object. Finally, there is uncertainty in the object pose, and even the most carefully planned movement may fail if the object is not at the expected position. To address these challenges we 1) present a simplified, computationally more efficient version of our model-free reinforcement learning algorithm PI2; 2) extend PI2 so that it simultaneously learns shape parameters and goal parameters of motion primitives; 3) use shape and goal learning to acquire motion primitives that are robust to object pose uncertainty. We evaluate these contributions on a manipulation platform consisting of a 7-DOF arm with a 4-DOF hand.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Inverse Dynamics Control of Floating-Base Robots with External Constraints: a Unified View

Righetti, L., Buchli, J., Mistry, M., Schaal, S.

In 2011 IEEE International Conference on Robotics and Automation, pages: 1085-1090, IEEE, Shanghai, China, 2011 (inproceedings)

Abstract
Inverse dynamics controllers and operational space controllers have proved to be very efficient for compliant control of fully actuated robots such as fixed base manipulators. However legged robots such as humanoids are inherently different as they are underactuated and subject to switching external contact constraints. Recently several methods have been proposed to create inverse dynamics controllers and operational space controllers for these robots. In an attempt to compare these different approaches, we develop a general framework for inverse dynamics control and show that these methods lead to very similar controllers. We are then able to greatly simplify recent whole-body controllers based on operational space approaches using kinematic projections, bringing them closer to efficient practical implementations. We also generalize these controllers such that they can be optimal under an arbitrary quadratic cost in the commands.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
First measurement of the heat effect of the grain boundary wetting phase transition

Straumal, B. B., Kogtenkova, O. A., Protasova, S. G., Zieba, P., Czeppe, T., Baretzky, B., Valiev, R. Z.

In 46, pages: 4243, Mie, Japan, 2011 (inproceedings)

mms

DOI [BibTex]

DOI [BibTex]


no image
Free flight simulations and pitch and roll control experiments of a sub-gram flapping-flight micro aerial vehicle

Hines, L. L., Arabagi, V., Sitti, M.

In Robotics and Automation (ICRA), 2011 IEEE International Conference on, pages: 1-7, 2011 (inproceedings)

pi

Project Page [BibTex]

Project Page [BibTex]