Institute Homepage
Institute Homepage DE Sign In

Publications

DEPARTMENTS

Emperical Interference

Haptic Intelligence

Modern Magnetic Systems

Perceiving Systems

Physical Intelligence

Robotic Materials

Social Foundations of Computation

Research Groups

Autonomous Vision

Autonomous Learning

Bioinspired Autonomous Miniature Robots

Dynamic Locomotion

Embodied Vision

Human Aspects of Machine Learning

Intelligent Control Systems

Learning and Dynamical Systems

Locomotion in Biorobotic and Somatic Systems

Micro, Nano, and Molecular Systems

Movement Generation and Control

Neural Capture and Synthesis

Physics for Inference and Optimization

Organizational Leadership and Diversity

Probabilistic Learning Group

Topics

Robot Learning

Conference Paper

2022

Autonomous Learning

Robotics

AI

Career

Award

Theory of Inhomogeneous Condensed Matter Bachelor Thesis Pattern forming systems under confinement Maihöfer, M. Universität Stuttgart, Stuttgart, 2018 BibTeX
Theory of Inhomogeneous Condensed Matter Article Phase coexistence in a monolayer of active particles induced by Marangoni flows Domínguez, A., Popescu, M. N. Soft Matter, 14(39):8017-8029, Royal Society of Chemistry, Cambridge, UK, 2018 DOI BibTeX
Empirical Inference Poster Photorealistic Video Super Resolution Pérez-Pellitero, E., Sajjadi, M. S. M., Hirsch, M., Schölkopf, B. Workshop and Challenge on Perceptual Image Restoration and Manipulation (PIRM) at the 15th European Conference on Computer Vision (ECCV), 2018 (Published) BibTeX
Empirical Inference Article Phylogenetic convolutional neural networks in metagenomics Fioravanti*, D., Giarratano*, Y., Maggio*, V., Agostinelli, C., Chierici, M., Jurman, G., Furlanello, C. BMC Bioinformatics, 19(2):49 pages, 2018, *equal contribution (Published) DOI BibTeX
Materials Article Plasticity in inhomogeneously strained Au nanowires studied by Laue microdiffraction Ren, Z., Cornelius, T. W., Leclere, C., Davydok, A., Mieha, J. S., Robach, O., Richter, G., Thomas, O. Mrs Advances, 3(39):2331-2339, 2018 DOI BibTeX
Theory of Inhomogeneous Condensed Matter Article Power spectral density of a single Brownian trajectory: what one can and cannot learn from it Krapf, D., Marinari, E., Metzler, R., Oshanin, G., Xu, X., Squarcini, A. New Journal of Physics, 20:023029, IOP Publishing, Bristol, 2018 DOI BibTeX
Statistical Learning Theory Conference Paper 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 BibTeX
Empirical Inference Article Prediction of Glucose Tolerance without an Oral Glucose Tolerance Test Babbar, R., Heni, M., Peter, A., Hrabě de Angelis, M., Häring, H., Fritsche, A., Preissl, H., Schölkopf, B., Wagner, R. Frontiers in Endocrinology, 9:article no. 82, 2018 (Published) DOI BibTeX
Empirical Inference Probabilistic Numerics Ph.D. Thesis Probabilistic Approaches to Stochastic Optimization Mahsereci, M. Eberhard Karls Universität Tübingen, Germany, 2018 (Published) URL BibTeX
Empirical Inference Probabilistic Learning Group Conference Paper Probabilistic Deep Learning using Random Sum-Product Networks Peharz, R., Vergari, A., Stelzner, K., Molina, A., Trapp, M., Kersting, K., Ghahramani, Z. 2018 (Submitted) arXiv BibTeX
Empirical Inference Probabilistic Numerics Ph.D. Thesis Probabilistic Ordinary Differential Equation Solvers — Theory and Applications Schober, M. Eberhard Karls Universität Tübingen, Germany, 2018 (Published) BibTeX
Theory of Inhomogeneous Condensed Matter Article Probing interface localization-delocalization transitions by colloids Kondrat, S., Vasilyev, O., Dietrich, S. Journal of Physics: Condensed Matter, 30(41):414002, IOP Publishing, Bristol, 2018 DOI BibTeX
Empirical Inference Article Quantum machine learning: a classical perspective Ciliberto, C., Herbster, M., Ialongo, A. D., Pontil, M., Rocchetto, A., Severini, S., Wossnig, L. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 474(2209):article no. 20170551, 2018 (Published) DOI URL BibTeX
Autonomous Vision Conference Paper RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials Paschalidou, D., Ulusoy, A. O., Schmitt, C., Gool, L., 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
In this paper, we consider the problem of reconstructing a dense 3D model using images captured from different views. Recent methods based on convolutional neural networks (CNN) allow learning the entire task from data. However, they do not incorporate the physics of image formation such as perspective geometry and occlusion. Instead, classical approaches based on Markov Random Fields (MRF) with ray-potentials explicitly model these physical processes, but they cannot cope with large surface appearance variations across different viewpoints. In this paper, we propose RayNet, which combines the strengths of both frameworks. RayNet integrates a CNN that learns view-invariant feature representations with an MRF that explicitly encodes the physics of perspective projection and occlusion. We train RayNet end-to-end using empirical risk minimization. We thoroughly evaluate our approach on challenging real-world datasets and demonstrate its benefits over a piece-wise trained baseline, hand-crafted models as well as other learning-based approaches.
pdf suppmat Video Project Page code Poster BibTeX
Empirical Inference Master Thesis Reinforcement Learning for High-Speed Robotics with Muscular Actuation Guist, S. Ruprecht-Karls-Universität Heidelberg , 2018 (Published) BibTeX
Empirical Inference Poster Retinal image quality of the human eye across the visual field Meding, K., Hirsch, M., Wichmann, F. A. 14th Biannual Conference of the German Society for Cognitive Science (KOGWIS 2018), 2018 (Published) BibTeX
Theory of Inhomogeneous Condensed Matter Article Rheological behavior of colloidal suspension with long-range interactions Arietaleaniz, S., Malgaretti, P., Pagonabarraga, I., Hidalgo, R. C. Physical Review E, 98(4):042603, American Physical Society, Melville, NY, 2018 DOI BibTeX
Autonomous Learning Conference Paper Robust Affordable 3D Haptic Sensation via Learning Deformation Patterns Sun, H., Martius, G. Proceedings International Conference on Humanoid Robots, 846-853, IEEE, New York, NY, USA, 2018 IEEE-RAS International Conference on Humanoid Robots, 2018, Oral Presentation
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.
DOI BibTeX
Conference Paper Robust and Cheap 3D Haptic Sensation using Deformation Patterns and Machine Learning Sun, H., Martius, G. In IEEE-RAS International Conference on Humanoid Robots (Humanoids 2018), 2018, to appear BibTeX
Physical Intelligence Article Seed-mediated synthesis of plasmonic gold nanoribbons using cancer cells for hyperthermia applications Singh, A. V., Alapan, Y., Jahnke, T., Laux, P., Luch, A., Aghakhani, A., Kharratian, S., Onbasli, M. C., Bill, J., Sitti, M. Journal of Materials Chemistry B, 6(46):7573-7581, 2018 BibTeX
Theory of Inhomogeneous Condensed Matter Article Self-diffusiophoresis induced by fluid interfaces Malgaretti, P., Popescu, M. N., Dietrich, S. Soft Matter, 14(8):1375-1388, Royal Society of Chemistry, Cambridge, UK, 2018 DOI BibTeX
Autonomous Vision Conference Paper Semantic Visual Localization Schönberger, J., Pollefeys, M., Geiger, A., Sattler, T. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE Computer Society, IEEE International Conference on Computer Vision and Pattern Recognition (CVPR), 2018
Robust visual localization under a wide range of viewing conditions is a fundamental problem in computer vision. Handling the difficult cases of this problem is not only very challenging but also of high practical relevance, eg, in the context of life-long localization for augmented reality or autonomous robots. In this paper, we propose a novel approach based on a joint 3D geometric and semantic understanding of the world, enabling it to succeed under conditions where previous approaches failed. Our method leverages a novel generative model for descriptor learning, trained on semantic scene completion as an auxiliary task. The resulting 3D descriptors are robust to missing observations by encoding high-level 3D geometric and semantic information. Experiments on several challenging large-scale localization datasets demonstrate reliable localization under extreme viewpoint, illumination, and geometry changes.
pdf suppmat Poster BibTeX
Theory of Inhomogeneous Condensed Matter Article Shape-dependent guidance of active Janus particles by chemically patterned surfaces Uspal, W. E., Popescu, M. N., Tasinkevych, M., Dietrich, S. New Journal of Physics, 20:015013, IOP Publishing, Bristol, 2018 DOI BibTeX
Theory of Inhomogeneous Condensed Matter Article Shear-density coupling for a compressible single-component yield-stress fluid Gross, M., Varnik, F. Soft Matter, 14(22):4577-4590, Royal Society of Chemistry, Cambridge, UK, 2018 DOI BibTeX
Theory of Inhomogeneous Condensed Matter Article Spontaneous symmetry breaking of charge-regulated surfaces Majee, A., Bier, M., Podgornik, R. Soft Matter, 14(6):985-991, Royal Society of Chemistry, Cambridge, UK, 2018 DOI BibTeX
Theory of Inhomogeneous Condensed Matter Article Stresses in non-equilibrium fluids: Exact formulation and coarse-grained theory Krüger, M., Solon, A., Démery, V., Rohwer, C. M., Dean, D. S. The Journal of Chemical Physics, 148(8):084503, American Institute of Physics, Woodbury, N.Y., 2018 DOI BibTeX
Theory of Inhomogeneous Condensed Matter Article Structure of interfaces at phase coexistence. Theory and numerics Delfino, G., Selke, W., Squarcini, A. Journal of Statistical Mechanics: Theory and Experiment, 2018:053203, Institute of Physics Publishing, Bristol, England, 2018 DOI BibTeX
Theory of Inhomogeneous Condensed Matter Bachelor Thesis Surface structure of liquid crystals Sattler, A. Universität Stuttgart, Stuttgart, 2018 BibTeX
Theory of Inhomogeneous Condensed Matter Article Surface-induced nonequilibrium dynamics and critical Casimir forces for model B in film geometry Gross, M., Gambassi, A., Dietrich, S. Physical Review E, 98(3):032103, American Physical Society, Melville, NY, 2018 DOI BibTeX
Autonomous Learning Conference Paper Systematic self-exploration of behaviors for robots in a dynamical systems framework Pinneri, C., Martius, G. In Proc. Artificial Life XI, 319-326, MIT Press, Cambridge, MA, 2018
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.
DOI URL BibTeX
Perceiving Systems Article Temporal Human Action Segmentation via Dynamic Clustering Zhang, Y., Sun, H., Tang, S., Neumann, H. arXiv preprint arXiv:1803.05790, 2018
We present an effective dynamic clustering algorithm for the task of temporal human action segmentation, which has comprehensive applications such as robotics, motion analysis, and patient monitoring. Our proposed algorithm is unsupervised, fast, generic to process various types of features, and applica- ble in both the online and offline settings. We perform extensive experiments of processing data streams, and show that our algorithm achieves the state-of- the-art results for both online and offline settings.
URL BibTeX
Materials Article Three-point bending behavior of a Au nanowire studied by in-situ Laue micro-diffraction Ren, Z., Cornelius, T. W., Leclere, C., Davydok, A., Micha, J. S., Robach, O., Richter, G., Thomas, O. Journal of Applied Physics, 124(18), 2018 DOI BibTeX
Physical Intelligence Article Three‐dimensional patterning in biomedicine: Importance and applications in neuropharmacology Singh, A. V., Gharat, T., Batuwangala, M., Park, B. W., Endlein, T., Sitti, M. Journal of Biomedical Materials Research Part B: Applied Biomaterials, 106(3):1369-1382, 2018 BibTeX
Empirical Inference Book Chapter Transfer Learning for BCIs Jayaram, V., Fiebig, K., Peters, J., Grosse-Wentrup, M. In Brain–Computer Interfaces Handbook, 425-442, 22, (Editors: Chang S. Nam, Anton Nijholt and Fabien Lotte), CRC Press, 2018 (Published) BibTeX
Theory of Inhomogeneous Condensed Matter Article Transient dynamics of electric double-layer capacitors: Exact expressions within the Debye-Falkenhagen approximation Janssen, M., Bier, M. Physical Review E, 97(5):052616, American Physical Society, Melville, NY, 2018 DOI BibTeX
Theory of Inhomogeneous Condensed Matter Article Two time scales for self and collective diffusion near the critical point in a simple patchy model for proteins with floating bonds Bleibel, J., Habiger, M., Lütje, M., Hirschmann, F., Roosen-Runge, F., Seydel, T., Zhang, F., Schreiber, F., Oettel, M. Soft Matter, 14(39):8006-8016, Royal Society of Chemistry, Cambridge, UK, 2018 DOI BibTeX
Movement Generation and Control Autonomous Motion Conference Paper Unsupervised Contact Learning for Humanoid Estimation and Control Rotella, N., Schaal, S., Righetti, L. In 2018 IEEE International Conference on Robotics and Automation (ICRA), 411-417, IEEE, Brisbane, Australia, 2018
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.
DOI URL BibTeX
Dynamic Locomotion Bachelor Thesis Untersuchung und Charakterisierung von Teilelementen der Modifikation im Lumbosacralbereich von Vögeln Richter, J. Hochschule Harz, 2018 BibTeX
Empirical Inference Conference Paper Utilizing Human Feedback in POMDP Execution and Specification Hoelscher, J., Koert, D., Peters, J., Pajarinen, J. IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids), 104-111, IEEE, 2018 (Published) DOI BibTeX
Theory of Inhomogeneous Condensed Matter Article Vapor nucleation paths in lyophobic nanopores Tinti, A., Giacomello, A., Casciola, C. M. European Physical Journal E, 41(4):52, Springer, Berlin, 2018 DOI BibTeX
Empirical Inference Probabilistic Learning Group Article Visualizing and understanding Sum-Product Networks Vergari, A., Di Mauro, N., Esposito, F. Machine Learning, 2018 (Published) DOI BibTeX
Theory of Inhomogeneous Condensed Matter Article Wetting transition of a cylindrical cavity engraved on a hydrophobic surface Kim, H., Ha, M. Y., Jang, J. The Journal of Physical Chemistry C, 122(4):2122-2126, American Chemical Society, Washington, D.C., 2018 DOI BibTeX
Autonomous Vision Conference Paper Which Training Methods for GANs do actually Converge? Mescheder, L., Geiger, A., Nowozin, S. International Conference on Machine learning (ICML), 2018
Recent work has shown local convergence of GAN training for absolutely continuous data and generator distributions. In this paper, we show that the requirement of absolute continuity is necessary: we describe a simple yet prototypical counterexample showing that in the more realistic case of distributions that are not absolutely continuous, unregularized GAN training is not always convergent. Furthermore, we discuss regularization strategies that were recently proposed to stabilize GAN training. Our analysis shows that GAN training with instance noise or zero-centered gradient penalties converges. On the other hand, we show that Wasserstein-GANs and WGAN-GP with a finite number of discriminator updates per generator update do not always converge to the equilibrium point. We discuss these results, leading us to a new explanation for the stability problems of GAN training. Based on our analysis, we extend our convergence results to more general GANs and prove local convergence for simplified gradient penalties even if the generator and data distributions lie on lower dimensional manifolds. We find these penalties to work well in practice and use them to learn high-resolution generative image models for a variety of datasets with little hyperparameter tuning.
code video paper supplement slides poster BibTeX
Empirical Inference Conference Paper k–SVRG: Variance Reduction for Large Scale Optimization Raj, A., Stich, S. In 2018 (Submitted) BibTeX
Miscellaneous 10\microm isotropic voxels acquired with a CMOS-based planar microcoil at 14.1T: Preliminary results Pérez Rodas, M., Handwerker, J., Merkle, H., Pohmann, R., Anders, J., Scheffler, K. Joint Annual Meeting ISMRM-ESMRMB 2018, 2018
{The quest for high resolution MR have push the technology to miniaturization. Thus, microcoils have been used for imaging with very high resolution. Here, we have designed and constructed a fully integrated CMOS NMR transceiver containing an on-chip microcoil, integrated amplifiers and demodulator for the high-frequency MR signal. In the present work, the initial microimaging results of this fully-integrated NMR transceiver in a 14.1 T animal scanner are presented. The on-chip microcoil allows imaging with a spatial resolution down to 10 $\micro$m with an SNR of 64 and with an improvement in SNR/volume ratio of 150 compared to a 10 mm surface coil.}
BibTeX
Miscellaneous 32-Channel Combined Surface Loop / \textquotedblleftVertical”Loop Tight-Fit Array Provides for Full-Brain Coverage, High Transmit Performance, and SNR Improvement at 9.4T: an Alternative to Surface Loop / Dipole Antenna Combination Avdievich, N., Giapitzakis, I., Henning, A. Joint Annual Meeting ISMRM-ESMRMB 2018, 2018
{Tight-fit human head ultra-high field (UHF,\textgreater7T) transceiver (TxRx) surface loop phased arrays improve transmit (Tx)-efficiency in comparison to Tx-only arrays, which are larger to fit receive (Rx)-only arrays inside. A drawback of the TxRx-design is that the number of array elements is restricted by the number of available RF Tx-channels (commonly \textless16), which limits the Rx-performance. A new 32-element tight-fit human head array, which consists of 18 TxRx-loops and 14 Rx-only vertical loops, was constructed. The array provides for full-brain coverage, \textasciitilde50 greater B , and \textasciitilde30 greater SNR near the brain center as compared to common Tx-only/ Rx-only (ToRo) array.}
BibTeX
Miscellaneous 3D CEST MRI of human brain at 9.4T reveals vessel correlation of the effect at -1.7 ppm Zaiss, M., Bause, J., Deshmane, A., Herz, K., Scheffler, K. Joint Annual Meeting ISMRM-ESMRMB 2018, 2018
{In vivo CEST imaging at 9.4T reveals that the peak at -1.7 ppm which was recently associated with red blood cells is spatially localized to blood vessels. A 3D CEST sequence with high resolution and dense sampling of the Z-spectrum shows that only the -1.7 ppm contrast is vascularly localized.}
BibTeX
Modern Magnetic Systems Article 3d nanofabrication of high-resolution multilayer Fresnel zone plates Sanli, U. T., Jiao, C., Baluktsian, M., Grévent, C., Hahn, K., Wang, Y., Srot, V., Richter, G., Bykova, I., Weigand, M., Schütz, G., Keskinbora, K. {Advanced Science}, 5(9), Wiley-VCH, Weinheim, 2018 DOI BibTeX
Proceedings 3rd Workshop on Eye Tracking and Visualization (ETVIS \textquotesingle18) 53, Warsaw, Poland, 2018 BibTeX
Miscellaneous 9.4T Human fMRI Study Reveals that Real World Motion Perception Does Not Involve Laminar Organization in V1 and V5/MT Molaei-Vaneghi, F., Zaretskaya, N., Scheffler, K., Bartels, A. 2018 BibTeX