Header logo is


2018


no image
k–SVRG: Variance Reduction for Large Scale Optimization

Raj, A., Stich, S.

In 2018 (inproceedings) Submitted

ei

[BibTex]

2018


[BibTex]


no image
Collectives of Spinning Mobile Microrobots for Navigation and Object Manipulation at the Air-Water Interface

Wang, W., Kishore, V., Koens, L., Lauga, E., Sitti, M.

In 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages: 1-9, 2018 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Probabilistic Deep Learning using Random Sum-Product Networks

Peharz, R., Vergari, A., Stelzner, K., Molina, A., Trapp, M., Kersting, K., Ghahramani, Z.

2018 (conference) Submitted

ei

arXiv [BibTex]

arXiv [BibTex]


Thumb xl david paper teaser
Learning 3D Shape Completion from Laser Scan Data with Weak Supervision

Stutz, D., Geiger, A.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
3D shape completion from partial point clouds is a fundamental problem in computer vision and computer graphics. Recent approaches can be characterized as either data-driven or learning-based. Data-driven approaches rely on a shape model whose parameters are optimized to fit the observations. Learning-based approaches, in contrast, avoid the expensive optimization step and instead directly predict the complete shape from the incomplete observations using deep neural networks. However, full supervision is required which is often not available in practice. In this work, we propose a weakly-supervised learning-based approach to 3D shape completion which neither requires slow optimization nor direct supervision. While we also learn a shape prior on synthetic data, we amortize, ie, learn, maximum likelihood fitting using deep neural networks resulting in efficient shape completion without sacrificing accuracy. Tackling 3D shape completion of cars on ShapeNet and KITTI, we demonstrate that the proposed amortized maximum likelihood approach is able to compete with a fully supervised baseline and a state-of-the-art data-driven approach while being significantly faster. On ModelNet, we additionally show that the approach is able to generalize to other object categories as well.

avg

pdf suppmat Project Page Poster Project Page [BibTex]

pdf suppmat Project Page Poster Project Page [BibTex]


Thumb xl publication alife 2018
Systematic self-exploration of behaviors for robots in a dynamical systems framework

Pinneri, C., Martius, G.

In Proc. Artificial Life XI, pages: 319-326, MIT Press, Cambridge, MA, 2018 (inproceedings)

Abstract
One of the challenges of this century is to understand the neural mechanisms behind cognitive control and learning. Recent investigations propose biologically plausible synaptic mechanisms for self-organizing controllers, in the spirit of Hebbian learning. In particular, differential extrinsic plasticity (DEP) [Der and Martius, PNAS 2015], has proven to enable embodied agents to self-organize their individual sensorimotor development, and generate highly coordinated behaviors during their interaction with the environment. These behaviors are attractors of a dynamical system. In this paper, we use the DEP rule to generate attractors and we combine it with a “repelling potential” which allows the system to actively explore all its attractor behaviors in a systematic way. With a view to a self-determined exploration of goal-free behaviors, our framework enables switching between different motion patterns in an autonomous and sequential fashion. Our algorithm is able to recover all the attractor behaviors in a toy system and it is also effective in two simulated environments. A spherical robot discovers all its major rolling modes and a hexapod robot learns to locomote in 50 different ways in 30min.

al

link (url) DOI Project Page [BibTex]

link (url) DOI Project Page [BibTex]


no image
Measures of distortion for machine learning

Vankadara, L., von Luxburg, U.

In Proceedings Neural Information Processing Systems, Neural Information Processing Systems (NIPS 2018) , 2018 (inproceedings)

slt

Project Page [BibTex]

Project Page [BibTex]


no image
Endo-VMFuseNet: A Deep Visual-Magnetic Sensor Fusion Approach for Endoscopic Capsule Robots

Turan, M., Almalioglu, Y., Gilbert, H. B., Sari, A. E., Soylu, U., Sitti, M.

In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages: 1-7, 2018 (inproceedings)

pi

[BibTex]

[BibTex]


no image
A Differentially Private Kernel Two-Sample Test

Raj*, A., Law*, L., Sejdinovic*, D., Park, M.

2018, *equal contribution (conference) Submitted

ei

[BibTex]

[BibTex]


no image
Robust and Cheap 3D Haptic Sensation using Deformation Patterns and Machine Learning

Huanbo Sun, Georg Martius

In IEEE-RAS International Conference on Humanoid Robots (Humanoids 2018), 2018, to appear (inproceedings)

[BibTex]

[BibTex]


no image
Practical Methods for Graph Two-Sample Testing

Ghoshdastidar, D., von Luxburg, U.

In Proceedings Neural Information Processing Systems, Neural Information Processing Systems (NIPS 2018) , 2018 (inproceedings)

slt

Project Page [BibTex]

Project Page [BibTex]


no image
Endosensorfusion: Particle filtering-based multi-sensory data fusion with switching state-space model for endoscopic capsule robots

Turan, M., Almalioglu, Y., Gilbert, H., Araujo, H., Cemgil, T., Sitti, M.

In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages: 1-8, 2018 (inproceedings)

pi

[BibTex]

[BibTex]


Thumb xl benvisapp
Learning Transformation Invariant Representations with Weak Supervision

Coors, B., Condurache, A., Mertins, A., Geiger, A.

In International Conference on Computer Vision Theory and Applications, International Conference on Computer Vision Theory and Applications, 2018 (inproceedings)

Abstract
Deep convolutional neural networks are the current state-of-the-art solution to many computer vision tasks. However, their ability to handle large global and local image transformations is limited. Consequently, extensive data augmentation is often utilized to incorporate prior knowledge about desired invariances to geometric transformations such as rotations or scale changes. In this work, we combine data augmentation with an unsupervised loss which enforces similarity between the predictions of augmented copies of an input sample. Our loss acts as an effective regularizer which facilitates the learning of transformation invariant representations. We investigate the effectiveness of the proposed similarity loss on rotated MNIST and the German Traffic Sign Recognition Benchmark (GTSRB) in the context of different classification models including ladder networks. Our experiments demonstrate improvements with respect to the standard data augmentation approach for supervised and semi-supervised learning tasks, in particular in the presence of little annotated data. In addition, we analyze the performance of the proposed approach with respect to its hyperparameters, including the strength of the regularization as well as the layer where representation similarity is enforced.

avg

pdf [BibTex]

pdf [BibTex]


Thumb xl smalrteaser
Lions and Tigers and Bears: Capturing Non-Rigid, 3D, Articulated Shape from Images

Zuffi, S., Kanazawa, A., Black, M. J.

In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 2018 (inproceedings)

Abstract
Animals are widespread in nature and the analysis of their shape and motion is important in many fields and industries. Modeling 3D animal shape, however, is difficult because the 3D scanning methods used to capture human shape are not applicable to wild animals or natural settings. Consequently, we propose a method to capture the detailed 3D shape of animals from images alone. The articulated and deformable nature of animals makes this problem extremely challenging, particularly in unconstrained environments with moving and uncalibrated cameras. To make this possible, we use a strong prior model of articulated animal shape that we fit to the image data. We then deform the animal shape in a canonical reference pose such that it matches image evidence when articulated and projected into multiple images. Our method extracts significantly more 3D shape detail than previous methods and is able to model new species, including the shape of an extinct animal, using only a few video frames. Additionally, the projected 3D shapes are accurate enough to facilitate the extraction of a realistic texture map from multiple frames.

ps

pdf code/data 3D models Project Page [BibTex]

pdf code/data 3D models Project Page [BibTex]


Thumb xl featured pic
Learning equations for extrapolation and control

Sahoo, S. S., Lampert, C. H., Martius, G.

In Proc. 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, 2018, 80, pages: 4442-4450, http://proceedings.mlr.press/v80/sahoo18a/sahoo18a.pdf, (Editors: Dy, Jennifer and Krause, Andreas), PMLR, 2018 (inproceedings)

Abstract
We present an approach to identify concise equations from data using a shallow neural network approach. In contrast to ordinary black-box regression, this approach allows understanding functional relations and generalizing them from observed data to unseen parts of the parameter space. We show how to extend the class of learnable equations for a recently proposed equation learning network to include divisions, and we improve the learning and model selection strategy to be useful for challenging real-world data. For systems governed by analytical expressions, our method can in many cases identify the true underlying equation and extrapolate to unseen domains. We demonstrate its effectiveness by experiments on a cart-pendulum system, where only 2 random rollouts are required to learn the forward dynamics and successfully achieve the swing-up task.

al

Code Arxiv Poster Slides link (url) Project Page [BibTex]

Code Arxiv Poster Slides link (url) Project Page [BibTex]


no image
Denotational Validation of Higher-order Bayesian Inference

Ścibior, A., Kammar, O., Vákár, M., Staton, S., Yang, H., Cai, Y., Ostermann, K., Moss, S. K., Heunen, C., Ghahramani, Z.

Proceedings of the ACM on Principles of Programming Languages (POPL), 2(Article No. 60):1-29, ACM, 2018 (conference)

ei

DOI Project Page [BibTex]

DOI Project Page [BibTex]


Thumb xl sab
Robust Affordable 3D Haptic Sensation via Learning Deformation Patterns

Sun, H., Martius, G.

Proceedings International Conference on Humanoid Robots, pages: 846-853, IEEE, New York, NY, USA, 2018 IEEE-RAS International Conference on Humanoid Robots, 2018, Oral Presentation (conference)

Abstract
Haptic sensation is an important modality for interacting with the real world. This paper proposes a general framework of inferring haptic forces on the surface of a 3D structure from internal deformations using a small number of physical sensors instead of employing dense sensor arrays. Using machine learning techniques, we optimize the sensor number and their placement and are able to obtain high-precision force inference for a robotic limb using as few as 9 sensors. For the optimal and sparse placement of the measurement units (strain gauges), we employ data-driven methods based on data obtained by finite element simulation. We compare data-driven approaches with model-based methods relying on geometric distance and information criteria such as Entropy and Mutual Information. We validate our approach on a modified limb of the “Poppy” robot [1] and obtain 8 mm localization precision.

al

DOI Project Page [BibTex]

DOI Project Page [BibTex]


no image
On Time Optimization of Centroidal Momentum Dynamics

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

In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages: 5776-5782, IEEE, Brisbane, Australia, May 2018 (inproceedings)

Abstract
Recently, the centroidal momentum dynamics has received substantial attention to plan dynamically consistent motions for robots with arms and legs in multi-contact scenarios. However, it is also non convex which renders any optimization approach difficult and timing is usually kept fixed in most trajectory optimization techniques to not introduce additional non convexities to the problem. But this can limit the versatility of the algorithms. In our previous work, we proposed a convex relaxation of the problem that allowed to efficiently compute momentum trajectories and contact forces. However, our approach could not minimize a desired angular momentum objective which seriously limited its applicability. Noticing that the non-convexity introduced by the time variables is of similar nature as the centroidal dynamics one, we propose two convex relaxations to the problem based on trust regions and soft constraints. The resulting approaches can compute time-optimized dynamically consistent trajectories sufficiently fast to make the approach realtime capable. The performance of the algorithm is demonstrated in several multi-contact scenarios for a humanoid robot. In particular, we show that the proposed convex relaxation of the original problem finds solutions that are consistent with the original non-convex problem and illustrate how timing optimization allows to find motion plans that would be difficult to plan with fixed timing † †Implementation details and demos can be found in the source code available at https://git-amd.tuebingen.mpg.de/bponton/timeoptimization.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Direct observations of sub-100 nm spin wave propagation in magnonic wave-guides

Träger, N., Gruszecki, P., Lisiecki, F., Förster, J., Weigand, M., Kuswik, P., Dubowik, J., Schütz, G., Krawczyk, M., Gräfe, J.

In 2018 IEEE International Magnetics Conference (INTERMAG 2018), IEEE, Singapore, 2018 (inproceedings)

mms

DOI [BibTex]

DOI [BibTex]


no image
Emission and propagation of multi-dimensional spin waves in anisotropic spin textures

Sluka, V., Schneider, T., Gallardo, R. A., Kakay, A., Weigand, M., Warnatz, T., Mattheis, R., Roldan-Molina, A., Landeros, P., Tiberkevich, V., Slavin, A., Schütz, G., Erbe, A., Deac, A., Lindner, J., Raabe, J., Fassbender, J., Wintz, S.

2018 (misc)

mms

link (url) [BibTex]

link (url) [BibTex]


no image
PoTion: Pose MoTion Representation for Action Recognition

Choutas, Vasileios, Weinzaepfel, Philippe, Revaud, Jérôme, Schmid, Cordelia

In CVPR 2018 - IEEE Conference on Computer Vision and Pattern Recognition, pages: 1-10, IEEE, Salt Lake City, United States, June 2018 (inproceedings)

link (url) [BibTex]

link (url) [BibTex]


no image
Unsupervised Contact Learning for Humanoid Estimation and Control

Rotella, N., Schaal, S., Righetti, L.

In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages: 411-417, IEEE, Brisbane, Australia, 2018 (inproceedings)

Abstract
This work presents a method for contact state estimation using fuzzy clustering to learn contact probability for full, six-dimensional humanoid contacts. The data required for training is solely from proprioceptive sensors - endeffector contact wrench sensors and inertial measurement units (IMUs) - and the method is completely unsupervised. The resulting cluster means are used to efficiently compute the probability of contact in each of the six endeffector degrees of freedom (DoFs) independently. This clustering-based contact probability estimator is validated in a kinematics-based base state estimator in a simulation environment with realistic added sensor noise for locomotion over rough, low-friction terrain on which the robot is subject to foot slip and rotation. The proposed base state estimator which utilizes these six DoF contact probability estimates is shown to perform considerably better than that which determines kinematic contact constraints purely based on measured normal force.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Learning Task-Specific Dynamics to Improve Whole-Body Control

Gams, A., Mason, S., Ude, A., Schaal, S., Righetti, L.

In Hua, IEEE, Beijing, China, November 2018 (inproceedings)

Abstract
In task-based inverse dynamics control, reference accelerations used to follow a desired plan can be broken down into feedforward and feedback trajectories. The feedback term accounts for tracking errors that are caused from inaccurate dynamic models or external disturbances. On underactuated, free-floating robots, such as humanoids, high feedback terms can be used to improve tracking accuracy; however, this can lead to very stiff behavior or poor tracking accuracy due to limited control bandwidth. In this paper, we show how to reduce the required contribution of the feedback controller by incorporating learned task-space reference accelerations. Thus, we i) improve the execution of the given specific task, and ii) offer the means to reduce feedback gains, providing for greater compliance of the system. With a systematic approach we also reduce heuristic tuning of the model parameters and feedback gains, often present in real-world experiments. In contrast to learning task-specific joint-torques, which might produce a similar effect but can lead to poor generalization, our approach directly learns the task-space dynamics of the center of mass of a humanoid robot. Simulated and real-world results on the lower part of the Sarcos Hermes humanoid robot demonstrate the applicability of the approach.

am mg

link (url) [BibTex]

link (url) [BibTex]


no image
Thermal skyrmion diffusion applied in probabilistic computing

Zázvorka, J., Jakobs, F., Heinze, D., Keil, N., Kromin, S., Jaiswal, S., Litzius, K., Jakob, G., Virnau, P., Pinna, D., Everschor-Sitte, K., Donges, A., Nowak, U., Kläui, M.

2018 (misc)

mms

link (url) [BibTex]

link (url) [BibTex]


no image
An MPC Walking Framework With External Contact Forces

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

In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages: 1785-1790, IEEE, Brisbane, Australia, May 2018 (inproceedings)

Abstract
In this work, we present an extension to a linear Model Predictive Control (MPC) scheme that plans external contact forces for the robot when given multiple contact locations and their corresponding friction cone. To this end, we set up a two-step optimization problem. In the first optimization, we compute the Center of Mass (CoM) trajectory, foot step locations, and introduce slack variables to account for violating the imposed constraints on the Zero Moment Point (ZMP). We then use the slack variables to trigger the second optimization, in which we calculate the optimal external force that compensates for the ZMP tracking error. This optimization considers multiple contacts positions within the environment by formulating the problem as a Mixed Integer Quadratic Program (MIQP) that can be solved at a speed between 100-300 Hz. Once contact is created, the MIQP reduces to a single Quadratic Program (QP) that can be solved in real-time ({\textless}; 1kHz). Simulations show that the presented walking control scheme can withstand disturbances 2-3× larger with the additional force provided by a hand contact.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Interpreting FORC diagrams beyond the Preisach model: an experimental permalloy micro array investigation

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

In 2018 IEEE International Magnetics Conference (INTERMAG 2018), IEEE, Singapore, 2018 (inproceedings)

mms

DOI [BibTex]

DOI [BibTex]

2017


no image
Interpolated Policy Gradient: Merging On-Policy and Off-Policy Gradient Estimation for Deep Reinforcement Learning

Gu, S., Lillicrap, T., Turner, R. E., Ghahramani, Z., Schölkopf, B., Levine, S.

Advances in Neural Information Processing Systems 30, pages: 3849-3858, (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., 31st Annual Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) Project Page [BibTex]

2017


link (url) Project Page [BibTex]


no image
Boosting Variational Inference: an Optimization Perspective

Locatello, F., Khanna, R., Ghosh, J., Rätsch, G.

Workshop: Advances in Approximate Bayesian Inference at the 31st Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Learning Independent Causal Mechanisms

Parascandolo, G., Rojas-Carulla, M., Kilbertus, N., Schölkopf, B.

Workshop: Learning Disentangled Representations: from Perception to Control at the 31st Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Avoiding Discrimination through Causal Reasoning

Kilbertus, N., Rojas-Carulla, M., Parascandolo, G., Hardt, M., Janzing, D., Schölkopf, B.

Advances in Neural Information Processing Systems 30, pages: 656-666, (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., 31st Annual Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


no image
Greedy Algorithms for Cone Constrained Optimization with Convergence Guarantees

Locatello, F., Tschannen, M., Rätsch, G., Jaggi, M.

Advances in Neural Information Processing Systems 30, pages: 773-784, (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., 31st Annual Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


no image
AdaGAN: Boosting Generative Models

Tolstikhin, I., Gelly, S., Bousquet, O., Simon-Gabriel, C. J., Schölkopf, B.

Advances in Neural Information Processing Systems 30, pages: 5424-5433, (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., 31st Annual Conference on Neural Information Processing Systems, December 2017 (conference)

ei

arXiv link (url) Project Page [BibTex]

arXiv link (url) Project Page [BibTex]


Thumb xl larsnips
The Numerics of GANs

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

In Proceedings from the conference "Neural Information Processing Systems 2017., (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., Advances in Neural Information Processing Systems 30 (NIPS), December 2017 (inproceedings)

Abstract
In this paper, we analyze the numerics of common algorithms for training Generative Adversarial Networks (GANs). Using the formalism of smooth two-player games we analyze the associated gradient vector field of GAN training objectives. Our findings suggest that the convergence of current algorithms suffers due to two factors: i) presence of eigenvalues of the Jacobian of the gradient vector field with zero real-part, and ii) eigenvalues with big imaginary part. Using these findings, we design a new algorithm that overcomes some of these limitations and has better convergence properties. Experimentally, we demonstrate its superiority on training common GAN architectures and show convergence on GAN architectures that are known to be notoriously hard to train.

avg

pdf Project Page [BibTex]

pdf Project Page [BibTex]


no image
Safe Adaptive Importance Sampling

Stich, S. U., Raj, A., Jaggi, M.

Advances in Neural Information Processing Systems 30, pages: 4384-4394, (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., 31st Annual Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


Thumb xl amd intentiongan
Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets

Hausman, K., Chebotar, Y., Schaal, S., Sukhatme, G., Lim, J.

In Proceedings from the conference "Neural Information Processing Systems 2017., (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., Advances in Neural Information Processing Systems 30 (NIPS), December 2017 (inproceedings)

am

pdf video [BibTex]

pdf video [BibTex]


no image
ConvWave: Searching for Gravitational Waves with Fully Convolutional Neural Nets

Gebhard, T., Kilbertus, N., Parascandolo, G., Harry, I., Schölkopf, B.

Workshop on Deep Learning for Physical Sciences (DLPS) at the 31st Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


no image
From Parity to Preference-based Notions of Fairness in Classification

Zafar, M. B., Valera, I., Gomez Rodriguez, M., Gummadi, K., Weller, A.

Advances in Neural Information Processing Systems 30, pages: 229-239, (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., 31st Annual Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


Thumb xl fig toyex lqr1kernel 1
On the Design of LQR Kernels for Efficient Controller Learning

Marco, A., Hennig, P., Schaal, S., Trimpe, S.

Proceedings of the 56th IEEE Annual Conference on Decision and Control (CDC), pages: 5193-5200, IEEE, IEEE Conference on Decision and Control, December 2017 (conference)

Abstract
Finding optimal feedback controllers for nonlinear dynamic systems from data is hard. Recently, Bayesian optimization (BO) has been proposed as a powerful framework for direct controller tuning from experimental trials. For selecting the next query point and finding the global optimum, BO relies on a probabilistic description of the latent objective function, typically a Gaussian process (GP). As is shown herein, GPs with a common kernel choice can, however, lead to poor learning outcomes on standard quadratic control problems. For a first-order system, we construct two kernels that specifically leverage the structure of the well-known Linear Quadratic Regulator (LQR), yet retain the flexibility of Bayesian nonparametric learning. Simulations of uncertain linear and nonlinear systems demonstrate that the LQR kernels yield superior learning performance.

am ics pn

arXiv PDF On the Design of LQR Kernels for Efficient Controller Learning - CDC presentation DOI Project Page [BibTex]

arXiv PDF On the Design of LQR Kernels for Efficient Controller Learning - CDC presentation DOI Project Page [BibTex]


no image
Discriminative k-shot learning using probabilistic models

Bauer*, M., Rojas-Carulla*, M., Świątkowski, J. B., Schölkopf, B., Turner, R. E.

Second Workshop on Bayesian Deep Learning at the 31st Conference on Neural Information Processing Systems , December 2017, *equal contribution (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Closed-form Inference and Prediction in Gaussian Process State-Space Models

Ialongo, A. D., Van Der Wilk, M., Rasmussen, C. E.

Time Series Workshop at the 31st Conference on Neural Information Processing Systems, December 2017 (conference)

ei

PDF [BibTex]

PDF [BibTex]


no image
Learning Robust Video Synchronization without Annotations

Wieschollek, P., Freeman, I., Lensch, H. P. A.

16th IEEE International Conference on Machine Learning and Applications (ICMLA), pages: 92 - 100, (Editors: X. Chen, B. Luo, F. Luo, V. Palade, and M. A. Wani), IEEE, December 2017 (conference)

ei

DOI [BibTex]

DOI [BibTex]


no image
Optimizing human learning

Tabibian, B., Upadhyay, U., De, A., Zarezade, A., Schölkopf, B., Gomez Rodriguez, M.

Workshop on Teaching Machines, Robots, and Humans at the 31st Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Leveraging the Crowd to Detect and Reduce the Spread of Fake News and Misinformation

Kim, J., Tabibian, B., Oh, A., Schölkopf, B., Gomez Rodriguez, M.

Workshop on Prioritising Online Content at the 31st Conference on Neural Information Processing Systems, December 2017 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Synchronicity Trumps Mischief in Rhythmic Human-Robot Social-Physical Interaction

Fitter, N. T., Kuchenbecker, K. J.

In Proceedings of the International Symposium on Robotics Research (ISRR), Puerto Varas, Chile, December 2017 (inproceedings) In press

Abstract
Hand-clapping games and other forms of rhythmic social-physical interaction might help foster human-robot teamwork, but the design of such interactions has scarcely been explored. We leveraged our prior work to enable the Rethink Robotics Baxter Research Robot to competently play one-handed tempo-matching hand-clapping games with a human user. To understand how such a robot’s capabilities and behaviors affect user perception, we created four versions of this interaction: the hand clapping could be initiated by either the robot or the human, and the non-initiating partner could be either cooperative, yielding synchronous motion, or mischievously uncooperative. Twenty adults tested two clapping tempos in each of these four interaction modes in a random order, rating every trial on standardized scales. The study results showed that having the robot initiate the interaction gave it a more dominant perceived personality. Despite previous results on the intrigue of misbehaving robots, we found that moving synchronously with the robot almost always made the interaction more enjoyable, less mentally taxing, less physically demanding, and lower effort for users than asynchronous interactions caused by robot or human mischief. Taken together, our results indicate that cooperative rhythmic social-physical interaction has the potential to strengthen human-robot partnerships.

hi

[BibTex]

[BibTex]


no image
Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals

Tanneberg, D., Peters, J., Rueckert, E.

Proceedings of the 1st Annual Conference on Robot Learning (CoRL), pages: 167-174, Proceedings of Machine Learning Research, (Editors: Sergey Levine, Vincent Vanhoucke and Ken Goldberg), PMLR, November 2017 (conference)

ei

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


no image
Behind Distribution Shift: Mining Driving Forces of Changes and Causal Arrows

Huang, B., Zhang, K., Zhang, J., Sanchez-Romero, R., Glymour, C., Schölkopf, B.

IEEE 17th International Conference on Data Mining (ICDM), pages: 913-918, (Editors: Vijay Raghavan,Srinivas Aluru, George Karypis, Lucio Miele and Xindong Wu), November 2017 (conference)

ei

DOI [BibTex]

DOI [BibTex]


Thumb xl teaser
Optimizing Long-term Predictions for Model-based Policy Search

Doerr, A., Daniel, C., Nguyen-Tuong, D., Marco, A., Schaal, S., Toussaint, M., Trimpe, S.

Proceedings of 1st Annual Conference on Robot Learning (CoRL), 78, pages: 227-238, (Editors: Sergey Levine and Vincent Vanhoucke and Ken Goldberg), 1st Annual Conference on Robot Learning, November 2017 (conference)

Abstract
We propose a novel long-term optimization criterion to improve the robustness of model-based reinforcement learning in real-world scenarios. Learning a dynamics model to derive a solution promises much greater data-efficiency and reusability compared to model-free alternatives. In practice, however, modelbased RL suffers from various imperfections such as noisy input and output data, delays and unmeasured (latent) states. To achieve higher resilience against such effects, we propose to optimize a generative long-term prediction model directly with respect to the likelihood of observed trajectories as opposed to the common approach of optimizing a dynamics model for one-step-ahead predictions. We evaluate the proposed method on several artificial and real-world benchmark problems and compare it to PILCO, a model-based RL framework, in experiments on a manipulation robot. The results show that the proposed method is competitive compared to state-of-the-art model learning methods. In contrast to these more involved models, our model can directly be employed for policy search and outperforms a baseline method in the robot experiment.

am ics

PDF Project Page [BibTex]

PDF Project Page [BibTex]


no image
Efficient Online Adaptation with Stochastic Recurrent Neural Networks

Tanneberg, D., Peters, J., Rueckert, E.

IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids), pages: 198-204, IEEE, November 2017 (conference)

ei

DOI Project Page [BibTex]

DOI Project Page [BibTex]


no image
Learning inverse dynamics models in O(n) time with LSTM networks

Rueckert, E., Nakatenus, M., Tosatto, S., Peters, J.

IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids), pages: 811-816, IEEE, November 2017 (conference)

ei

DOI Project Page [BibTex]

DOI Project Page [BibTex]