3227 results (BibTeX)

2017


Thumb md cover
Path Integral Guided Policy Search

Chebotar, Y., Kalakrishnan, M., Yahya, A., Li, A., Schaal, S., Levine, S.

Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), April 2017 (conference)

am

pdf video [BibTex]

2017


pdf video [BibTex]


DeepCoder: Learning to Write Programs

Balog, M., Gaunt, A., Brockschmidt, M., Nowozin, S., Tarlow, D.

5th International Conference on Learning Representations (ICLR), 2017 (conference) Accepted

ei

Arxiv [BibTex]

Arxiv [BibTex]


Multi-frame blind image deconvolution through split frequency - phase recovery

Gauci, A., Abela, J., Cachia, E., Hirsch, M., ZarbAdami, K.

Proc. SPIE 10225, Eighth International Conference on Graphic and Image Processing (ICGIP 2016), pages: 1022511, (Editors: Yulin Wang, Tuan D. Pham, Vit Vozenilek, David Zhang, Yi Xie), 2017 (conference)

ei

DOI [BibTex]

DOI [BibTex]


Thumb md web teaser eg
Sparse Inertial Poser: Automatic 3D Human Pose Estimation from Sparse IMUs

Marcard, T., Rosenhahn, B., Black, M. J., Pons-Moll, G.

Computer Graphics Forum 36(2), Proceedings of the 38th Annual Conference of the European Association for Computer Graphics (Eurographics), 2017 (article)

Abstract
We address the problem of making human motion capture in the wild more practical by using a small set of inertial sensors attached to the body. Since the problem is heavily under-constrained, previous methods either use a large number of sensors, which is intrusive, or they require additional video input. We take a different approach and constrain the problem by: (i) making use of a realistic statistical body model that includes anthropometric constraints and (ii) using a joint optimization framework to fit the model to orientation and acceleration measurements over multiple frames. The resulting tracker Sparse Inertial Poser (SIP) enables motion capture using only 6 sensors (attached to the wrists, lower legs, back and head) and works for arbitrary human motions. Experiments on the recently released TNT15 dataset show that, using the same number of sensors, SIP achieves higher accuracy than the dataset baseline without using any video data. We further demonstrate the effectiveness of SIP on newly recorded challenging motions in outdoor scenarios such as climbing or jumping over a wall

ps

video pdf [BibTex]

video pdf [BibTex]


Memristor-based control methods for a bio-inspired robot

Tetzlaff, R., Ascoli, A., Baumann, D., Hild, M.

International Conference on Memristive Materials, Devices & Systems, April 2017 (conference) Accepted

am

[BibTex]

[BibTex]


Thumb md coverhand wilson
Capturing Hand-Object Interaction and Reconstruction of Manipulated Objects

Tzionas, D.

University of Bonn, 2017 (phdthesis)

Abstract
Hand motion capture with an RGB-D sensor gained recently a lot of research attention, however, even most recent approaches focus on the case of a single isolated hand. We focus instead on hands that interact with other hands or with a rigid or articulated object. Our framework successfully captures motion in such scenarios by combining a generative model with discriminatively trained salient points, collision detection and physics simulation to achieve a low tracking error with physically plausible poses. All components are unified in a single objective function that can be optimized with standard optimization techniques. We initially assume a-priori knowledge of the object's shape and skeleton. In case of unknown object shape there are existing 3d reconstruction methods that capitalize on distinctive geometric or texture features. These methods though fail for textureless and highly symmetric objects like household articles, mechanical parts or toys. We show that extracting 3d hand motion for in-hand scanning effectively facilitates the reconstruction of such objects and we fuse the rich additional information of hands into a 3d reconstruction pipeline. Finally, although shape reconstruction is enough for rigid objects, there is a lack of tools that build rigged models of articulated objects that deform realistically using RGB-D data. We propose a method that creates a fully rigged model consisting of a watertight mesh, embedded skeleton and skinning weights by employing a combination of deformable mesh tracking, motion segmentation based on spectral clustering and skeletonization based on mean curvature flow.

ps

[BibTex]


Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets

Klein, A., Falkner, S., Bartels, S., Hennig, P., Hutter, F.

Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), 52, JMLR Workshop and Conference Proceedings, (Editors: Sign, Aarti and Zhu, Jerry), 2017 (conference) Accepted

pn

[BibTex]

[BibTex]


Thumb md img01
Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

Mescheder, L., Nowozin, S., Geiger, A.

Arxiv, 2017 (article)

Abstract
Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the expressiveness of the inference model used during training. We introduce Adversarial Variational Bayes (AVB), a technique for training Variational Autoencoders with arbitrarily expressive inference models. We achieve this by introducing an auxiliary discriminative network that allows to rephrase the maximum-likelihood-problem as a two-player game, hence establishing a principled connection between VAEs and Generative Adversarial Networks (GANs). We show that in the nonparametric limit our method yields an exact maximum-likelihood assignment for the parameters of the generative model, as well as the exact posterior distribution over the latent variables given an observation. Contrary to competing approaches which combine VAEs with GANs, our approach has a clear theoretical justification, retains most advantages of standard Variational Autoencoders and is easy to implement.

avg

pdf [BibTex]


Thumb md screen shot 2017 02 27 at 01.50.07
Trading Off Information and Costs: Reinforcement Learning from Simulations and Experiments with Bayesian Optimization

Marco, A., Berkenkamp, F., Hennig, P., Schoellig, A., Krause, A., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), IEEE International Conference on Robotics and Automation, May 2017 (inproceedings) Accepted

am pn

[BibTex]

[BibTex]


Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers

Doerr, A., Nguyen-Tuong, D., Marco, A., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2017 IEEE International Conference on Robotics and Automation, May 2017 (inproceedings) Accepted

am

[BibTex]

[BibTex]


Event-based State Estimation: An Emulation-based Approach

Trimpe, S.

IET Control Theory & Applications, 2017 (article) Accepted

Abstract
An event-based state estimation approach for reducing communication in a networked control system is proposed. Multiple distributed sensor agents observe a dynamic process and sporadically transmit their measurements to estimator agents over a shared bus network. Local event-triggering protocols ensure that data is transmitted only when necessary to meet a desired estimation accuracy. The event-based design is shown to emulate the performance of a centralised state observer design up to guaranteed bounds, but with reduced communication. The stability results for state estimation are extended to the distributed control system that results when the local estimates are used for feedback control. Results from numerical simulations and hardware experiments illustrate the effectiveness of the proposed approach in reducing network communication.

am

Supplementary material PDF DOI [BibTex]


Thumb md reliability icon
Distilling Information Reliability and Source Trustworthiness from Digital Traces

Tabibian, B., Valera, I., Farajtabar, M., Song, L., Schölkopf, B., Gomez Rodriguez, M.

Proceedings of the 26th International Conference on World Wide Web (WWW2017), 2017 (conference) Accepted

ei

Project [BibTex]

Project [BibTex]


DiSMEC – Distributed Sparse Machines for Extreme Multi-label Classification

Babbar, R., Schölkopf, B.

Proceedings of the Tenth ACM International Conference on Web Search and Data Mining (WSDM 2017), pages: 721-729, 2017 (conference)

ei

DOI [BibTex]

DOI [BibTex]


Thumb md fig  quali  arm
Probabilistic Articulated Real-Time Tracking for Robot Manipulation

Garcia Cifuentes, C., Issac, J., Wüthrich, M., Schaal, S., Bohg, J.

IEEE Robotics and Automation Letters (RA-L), 2(2):577-584, April 2017 (article)

Abstract
We propose a probabilistic filtering method which fuses joint measurements with depth images to yield a precise, real-time estimate of the end-effector pose in the camera frame. This avoids the need for frame transformations when using it in combination with visual object tracking methods. Precision is achieved by modeling and correcting biases in the joint measurements as well as inaccuracies in the robot model, such as poor extrinsic camera calibration. We make our method computationally efficient through a principled combination of Kalman filtering of the joint measurements and asynchronous depth-image updates based on the Coordinate Particle Filter. We quantitatively evaluate our approach on a dataset recorded from a real robotic platform, annotated with ground truth from a motion capture system. We show that our approach is robust and accurate even under challenging conditions such as fast motion, significant and long-term occlusions, and time-varying biases. We release the dataset along with open-source code of our approach to allow for quantitative comparison with alternative approaches.

am

arXiv video code and dataset PDF DOI Project Page [BibTex]

2016


The Mondrian Kernel

Balog, M., Lakshminarayanan, B., Ghahramani, Z., Roy, D., Teh, Y.

Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence (UAI), (Editors: Ihler, Alexander T. and Janzing, Dominik), 2016 (conference)

ei

Arxiv link (url) [BibTex]

2016


Arxiv link (url) [BibTex]


Learning High-Order Filters for Efficient Blind Deconvolution of Document Photographs

Xiao, L., Wang, J., Heidrich, W., Hirsch, M.

Computer Vision - ECCV 2016, Lecture Notes in Computer Science, LNCS 9907, Part III, pages: 734-749, (Editors: Bastian Leibe, Jiri Matas, Nicu Sebe and Max Welling), Springer, 2016 (conference)

ei

DOI [BibTex]

DOI [BibTex]


Thumb md img03
OctNet: Learning Deep 3D Representations at High Resolutions

Riegler, G., Ulusoy, A., Geiger, A.

Arxiv, 2016 (article)

Abstract
We present OctNet, a representation for deep learning with sparse 3D data. In contrast to existing models, our representation enables 3D convolutional networks which are both deep and high resolution. Towards this goal, we exploit the sparsity in the input data to hierarchically partition the space using a set of unbalanced octrees where each leaf node stores a pooled feature representation. This allows to focus memory allocation and computation to the relevant dense regions and enables deeper networks without compromising resolution. We demonstrate the utility of our OctNet representation by analyzing the impact of resolution on several 3D tasks including 3D object classification, orientation estimation and point cloud labeling.

avg

pdf [BibTex]


Thumb md img02
Probabilistic Duality for Parallel Gibbs Sampling without Graph Coloring

Mescheder, L., Nowozin, S., Geiger, A.

Arxiv, 2016 (article)

Abstract
We present a new notion of probabilistic duality for random variables involving mixture distributions. Using this notion, we show how to implement a highly-parallelizable Gibbs sampler for weakly coupled discrete pairwise graphical models with strictly positive factors that requires almost no preprocessing and is easy to implement. Moreover, we show how our method can be combined with blocking to improve mixing. Even though our method leads to inferior mixing times compared to a sequential Gibbs sampler, we argue that our method is still very useful for large dynamic networks, where factors are added and removed on a continuous basis, as it is hard to maintain a graph coloring in this setup. Similarly, our method is useful for parallelizing Gibbs sampling in graphical models that do not allow for graph colorings with a small number of colors such as densely connected graphs.

avg

pdf [BibTex]


easyGWAS: A Cloud-based Platform for Comparing the Results of Genome-wide Association Studies

Grimm, D., Roqueiro, D., Salome, P., Kleeberger, S., Greshake, B., Zhu, W., Liu, C., Lippert, C., Stegle, O., Schölkopf, B., Weigel, D., Borgwardt, K.

The Plant Cell, 2016 (article)

ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb md cabs diagnostics
Coupling Adaptive Batch Sizes with Learning Rates

Balles, L., Romero, J., Hennig, P.

arXiv preprint arXiv:1612.05086, 2016 (article)

Abstract
Mini-batch stochastic gradient descent and variants thereof have become standard for large-scale empirical risk minimization like the training of neural networks. These methods are usually used with a constant batch size chosen by simple empirical inspection. The batch size significantly influences the behavior of the stochastic optimization algorithm, though, since it determines the variance of the gradient estimates. This variance also changes over the optimization process; when using a constant batch size, stability and convergence is thus often enforced by means of a (manually tuned) decreasing learning rate schedule. We propose a practical method for dynamic batch size adaptation. It estimates the variance of the stochastic gradients and adapts the batch size to decrease the variance proportionally to the value of the objective function, removing the need for the aforementioned learning rate decrease. In contrast to recent related work, our algorithm couples the batch size to the learning rate, directly reflecting the known relationship between the two. On three image classification benchmarks, our batch size adaptation yields faster optimization convergence, while simultaneously simplifying learning rate tuning. A TensorFlow implementation is available.

ps pn

Code link (url) [BibTex]


Self-regulation of brain rhythms in the precuneus: a novel BCI paradigm for patients with ALS

Fomina, T., Lohmann, G., Erb, M., Ethofer, T., Schölkopf, B., Grosse-Wentrup, M.

Journal of Neural Engineering, 13(6):066021, 2016 (article)

ei

link (url) [BibTex]

link (url) [BibTex]


Stepping stabilization using a combination of DCM tracking and step adjustment

Khadiv, M., Kleff, S., Herzog, A., Moosavian, S., Schaal, S., Righetti, L.

4th RSI International Conference on Robotics and Mechatronics, 2016 (conference)

am

arxiv [BibTex]

arxiv [BibTex]


A Convex Model of Humanoid Momentum Dynamics for Multi-Contact Motion Generation

Ponton, B., Herzog, A., Schaal, S., Righetti, L.

Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, 2016 (conference)

am

arxiv video [BibTex]

arxiv video [BibTex]


Balancing and Walking Using Full Dynamics LQR Control with Contact Constraints

Mason, S., rotella, N., Schaal, S., Righetti, L.

Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, 2016 (conference)

am

[BibTex]

[BibTex]


Step Timing Adjustment: A Step Toward Generating Robust Gaits

Khadiv, M., Herzog, A., Moosavian, S., Righetti, L.

Proceedings of the 2016 IEEE-RAS International Conference on Humanoid Robots, 2016 (conference)

am

arxiv video [BibTex]

arxiv video [BibTex]


Thumb md iser small
Generalizing Regrasping with Supervised Policy Learning

Chebotar, Y., Hausman, K., Kroemer, O., Sukhatme, G., Schaal, S.

In International Symposium on Experimental Robotics (ISER) 2016, International Symposium on Experimental Robotics, 2016 (inproceedings)

am

pdf video [BibTex]

pdf video [BibTex]


Thumb md front small
Self-Supervised Regrasping using Spatio-Temporal Tactile Features and Reinforcement Learning

Chebotar, Y., Hausman, K., Su, Z., Sukhatme, G., Schaal, S.

In International Conference on Intelligent Robots and Systems (IROS) 2016, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2016 (inproceedings)

am

pdf video [BibTex]

pdf video [BibTex]


Thumb md testbed both
Moving-horizon Nonlinear Least Squares-based Multirobot Cooperative Perception

Ahmad, A., Bülthoff, H.

Robotics and Autonomous Systems, 83, pages: 275-286, 2016 (article)

Abstract
In this article we present an online estimator for multirobot cooperative localization and target tracking based on nonlinear least squares minimization. Our method not only makes the rigorous optimization-based approach applicable online but also allows the estimator to be stable and convergent. We do so by employing a moving horizon technique to nonlinear least squares minimization and a novel design of the arrival cost function that ensures stability and convergence of the estimator. Through an extensive set of real robot experiments, we demonstrate the robustness of our method as well as the optimality of the arrival cost function. The experiments include comparisons of our method with i) an extended Kalman filter-based online-estimator and ii) an offline-estimator based on full-trajectory nonlinear least squares.

ps

DOI [BibTex]

DOI [BibTex]


Thumb md cover
Dynamic baseline stereo vision-based cooperative target tracking

Ahmad, A., Ruff, E., Bülthoff, H.

In pages: 1728-1734, IEEE, 19th International Conference on Information Fusion (FUSION), 2016 (inproceedings)

Abstract
In this article we present a new method for multi-robot cooperative target tracking based on dynamic baseline stereo vision. The core novelty of our approach includes a computationally light-weight scheme to compute the 3D stereo measurements that exactly satisfy the epipolar constraints and a covariance intersection (CI)-based method to fuse the 3D measurements obtained by each individual robot. Using CI we are able to systematically integrate the robot localization uncertainties as well as the uncertainties in the measurements generated by the monocular camera images from each individual robot into the resulting stereo measurements. Through an extensive set of simulation and real robot results we show the robustness and accuracy of our approach with respect to ground truth. The source code related to this article is publicly accessible on our website and the datasets are available on request.

ps

[BibTex]

[BibTex]


Thumb md fundusphotoanthal
Deep Learning for Diabetic Retinopathy Diagnostics

Balles, L.

Heidelberg University, 2016, in cooperation with Bosch Corporate Research (mastersthesis)

PDF [BibTex]

PDF [BibTex]


Deep Learning for Diabetic Retinopathy Diagnostics

Balles, Lukas.

Heidelberg University, 2016 (mastersthesis)

[BibTex]

[BibTex]


BundleMAP: Anatomically Localized Classification, Regression, and Hypothesis Testing in Diffusion MRI

Khatami, M., Schmidt-Wilcke, T., Sundgren, P., Abbasloo, A., Schölkopf, B., Schultz, T.

Pattern Recognition, 2016 (article) In press

ei

DOI [BibTex]

DOI [BibTex]


Thumb md nonlinear approximate vs exact
A New Perspective and Extension of the Gaussian Filter

Wüthrich, M., Trimpe, S., Garcia Cifuentes, C., Kappler, D., Schaal, S.

The International Journal of Robotics Research, 35(14):1731-1749, December 2016 (article)

Abstract
The Gaussian Filter (GF) is one of the most widely used filtering algorithms; instances are the Extended Kalman Filter, the Unscented Kalman Filter and the Divided Difference Filter. The GF represents the belief of the current state by a Gaussian distribution, whose mean is an affine function of the measurement. We show that this representation can be too restrictive to accurately capture the dependences in systems with nonlinear observation models, and we investigate how the GF can be generalized to alleviate this problem. To this end, we view the GF as the solution to a constrained optimization problem. From this new perspective, the GF is seen as a special case of a much broader class of filters, obtained by relaxing the constraint on the form of the approximate posterior. On this basis, we outline some conditions which potential generalizations have to satisfy in order to maintain the computational efficiency of the GF. We propose one concrete generalization which corresponds to the standard GF using a pseudo measurement instead of the actual measurement. Extending an existing GF implementation in this manner is trivial. Nevertheless, we show that this small change can have a major impact on the estimation accuracy.

am

PDF DOI Project Page [BibTex]

PDF DOI Project Page [BibTex]


Predictive and Self Triggering for Event-based State Estimation

Trimpe, S.

In Proceedings of the 55th IEEE Conference on Decision and Control, pages: 3098-3105, Las Vegas, NV, USA, December 2016 (inproceedings)

am

arXiv PDF DOI [BibTex]

arXiv PDF DOI [BibTex]


Event-based Sampling for Reducing Communication Load in Realtime Human Motion Analysis by Wireless Inertial Sensor Networks

Laidig, D., Trimpe, S., Seel, T.

In Current Directions in Biomedical Engineering, 2(1), 2016 (inproceedings)

am

PDF DOI [BibTex]

PDF DOI [BibTex]


Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels

Tolstikhin, I., Sriperumbudur, B., Schölkopf, B.

Advances in Neural Information Processing Systems 29, 30th Annual Conference on Neural Information Processing Systems (NIPS), 2016 (conference) Accepted

ei

[BibTex]

[BibTex]


Consistent Kernel Mean Estimation for Functions of Random Variables

Scibior, A., Simon-Gabriel, C., Tolstikhin, I., Schölkopf, B.

Advances in Neural Information Processing Systems 29, 30th Annual Conference on Neural Information Processing Systems (NIPS), 2016 (conference) Accepted

ei

[BibTex]

[BibTex]


End-to-End Learning for Image Burst Deblurring

Wieschollek, P., Schölkopf, B., Lensch, H., Hirsch, M.

Computer Vision - ACCV 2016 - 13th Asian Conference on Computer Vision, 2016 (conference) Accepted

ei

[BibTex]

[BibTex]


The population of long-period transiting exoplanets

Foreman-Mackey, D., Morton, T., Hogg, D., Agol, E., Schölkopf, B.

The Astrophysical Journal, 2016 (article) Accepted

ei

[BibTex]

[BibTex]


Multi-task logistic regression in brain-computer interfaces

Fiebig, K., Jayaram, V., Peters, J., Grosse-Wentrup, M.

Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), IEEE, 2016 (conference) To be published

ei

link (url) [BibTex]

link (url) [BibTex]


Locally Weighted Regression for Control

Ting, J., Meier, F., Vijayakumar, S., Schaal, S.

In Encyclopedia of Machine Learning and Data Mining, pages: 1-14, Springer US, Boston, MA, 2016 (inbook)

am

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb md nao
Ensuring Ethical Behavior from Autonomous Systems

Anderson, M., Anderson, S., Berenz, V.

In Artificial Intelligence Applied to Assistive Technologies and Smart Environments, Papers from the 2016 AAAI Workshop, Phoenix, Arizona, USA, February 12, 2016, 2016 (inproceedings)

am

link (url) [BibTex]

link (url) [BibTex]


Jointly Learning Trajectory Generation and Hitting Point Prediction in Robot Table Tennis

Huang, Y., Büchler, D., Koc, O., Schölkopf, B., Peters, J.

16th IEEE-RAS International Conference on Humanoid Robots, Humanoids, 2016 (conference) Accepted

am ei

[BibTex]

[BibTex]


Using Probabilistic Movement Primitives for Striking Movements

Gomez-Gonzalez, S., Neumann, G., Schölkopf, B., Peters, J.

16th IEEE-RAS International Conference on Humanoid Robots, Humanoids, 2016 (conference) Accepted

am ei

[BibTex]

[BibTex]


Thumb md weak supervision
Weak Supervision for Detecting Object Classes from Activities

Srikantha, A., Gall, J.

Computer Vision and Image Understanding (CVIU), Elsevier, 2016 (article) In press

elsevier preprint link (url) DOI [BibTex]

elsevier preprint link (url) DOI [BibTex]


Thumb md barrista 2
Barrista - Caffe Well-Served

Lassner, C., Kappler, D., Kiefel, M., Gehler, P.

ACM Multimedia Open Source Software Competition, ACM OSSC16, October 2016 (proceedings) Accepted

Abstract
The caffe framework is one of the leading deep learning toolboxes in the machine learning and computer vision community. While it offers efficiency and configurability, it falls short of a full interface to Python. With increasingly involved procedures for training deep networks and reaching depths of hundreds of layers, creating configuration files and keeping them consistent becomes an error prone process. We introduce the barrista framework, offering full, pythonic control over caffe. It separates responsibilities and offers code to solve frequently occurring tasks for pre-processing, training and model inspection. It is compatible to all caffe versions since mid 2015 and can import and export .prototxt files. Examples are included, e.g., a deep residual network implemented in only 172 lines (for arbitrary depths), comparing to 2320 lines in the official implementation for the equivalent model.

am ps

pdf DOI [BibTex]

pdf DOI [BibTex]