Institute Homepage
Institute Homepage EN 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

Autonomous Motion Intelligent Control Systems Article 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 (Published)
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.
PDF DOI BibTeX
Empirical Inference Conference Paper Active Nearest-Neighbor Learning in Metric Spaces Kontorovich, A., Sabato, S., Urner, R. Advances in Neural Information Processing Systems 29 (NIPS 2016), 856-864, (Editors: D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett), Curran Associates, Inc., 30th Annual Conference on Neural Information Processing Systems, December 2016 (Published) URL BibTeX
Empirical Inference Conference Paper Catching heuristics are optimal control policies Belousov, B., Neumann, G., Rothkopf, C., Peters, J. Advances in Neural Information Processing Systems 29 (NIPS 2016), 1426-1434, (Editors: D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett), Curran Associates, Inc., 30th Annual Conference on Neural Information Processing Systems, December 2016 (Published) URL BibTeX
Empirical Inference Conference Paper Consistent Kernel Mean Estimation for Functions of Random Variables Simon-Gabriel*, C. J., Ścibior*, A., Tolstikhin, I., Schölkopf, B. Advances in Neural Information Processing Systems 29 (NIPS 2016), 1732-1740, (Editors: D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett), Curran Associates, Inc., 30th Annual Conference on Neural Information Processing Systems, December 2016, *joint first authors (Published) URL BibTeX
Empirical Inference Conference Paper Lifelong Learning with Weighted Majority Votes Pentina, A., Urner, R. Advances in Neural Information Processing Systems 29 (NIPS 2016), 3612-3620, (Editors: D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett), Curran Associates, Inc., 30th Annual Conference on Neural Information Processing Systems, December 2016 (Published) URL BibTeX
Empirical Inference Conference Paper Local-utopia Policy Selection for Multi-objective Reinforcement Learning Parisi, S., Blank, A., Viernickel, T., Peters, J. In IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL), 1-7, IEEE, December 2016 (Published) DOI BibTeX
Empirical Inference Conference Paper Minimax Estimation of Maximum Mean Discrepancy with Radial Kernels Tolstikhin, I., Sriperumbudur, B. K., Schölkopf, B. Advances in Neural Information Processing Systems 29 (NIPS 2016), 1930-1938, (Editors: D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett), Curran Associates, Inc., 30th Annual Conference on Neural Information Processing Systems, December 2016 (Published) URL BibTeX
Theory of Inhomogeneous Condensed Matter Article Nonsingular defects and self-assembly of colloidal particles in cholesteric liquid crystals Trivedi, R. P., Tasinkevych, M., Smalyukh, I. Physical Review E, 94(6):062703, American Physical Society, Melville, NY, December 2016 (Published) DOI BibTeX
Autonomous Motion Intelligent Control Systems Conference Paper Predictive and Self Triggering for Event-based State Estimation Trimpe, S. In Proceedings of the 55th IEEE Conference on Decision and Control (CDC), 3098-3105, Las Vegas, NV, USA, December 2016 (Published) arXiv PDF DOI BibTeX
Perceiving Systems Patent Skinned multi-person linear model Black, M., Loper, M., Mahmood, N., Pons-Moll, G., Romero, J. December 2016, Application PCT/EP2016/064610
The invention comprises a learned model of human body shape and pose dependent shape variation that is more accurate than previous models and is compatible with existing graphics pipelines. Our Skinned Multi-Person Linear model (SMPL) is a skinned vertex based model that accurately represents a wide variety of body shapes in natural human poses. The parameters of the model are learned from data including the rest pose template, blend weights, pose-dependent blend shapes, identity- dependent blend shapes, and a regressor from vertices to joint locations. Unlike previous models, the pose-dependent blend shapes are a linear function of the elements of the pose rotation matrices. This simple formulation enables training the entire model from a relatively large number of aligned 3D meshes of different people in different poses. The invention quantitatively evaluates variants of SMPL using linear or dual- quaternion blend skinning and show that both are more accurate than a Blend SCAPE model trained on the same data. In a further embodiment, the invention realistically models dynamic soft-tissue deformations. Because it is based on blend skinning, SMPL is compatible with existing rendering engines and we make it available for research purposes.
Google Patents BibTeX
Empirical Inference Conference Paper Understanding Probabilistic Sparse Gaussian Process Approximations Bauer, M., van der Wilk, M., Rasmussen, C. E. Advances in Neural Information Processing Systems 29 (NIPS 2016), 1533-1541, (Editors: D. D. Lee, M. Sugiyama, U. V. Luxburg, I. Guyon, and R. Garnett), Curran Associates, Inc., 30th Annual Conference on Neural Information Processing Systems, December 2016 (Published) URL BibTeX
Micro, Nano, and Molecular Systems Article Wireless actuation with functional acoustic surfaces Qiu, T., Palagi, S., Mark, A. G., Melde, K., Adams, F., Fischer, P. Appl. Phys. Lett., 109(19):191602, November 2016, APL Editor's pick. APL News. (Published)
Miniaturization calls for micro-actuators that can be powered wirelessly and addressed individually. Here, we develop functional surfaces consisting of arrays of acoustically resonant microcavities, and we demonstrate their application as two-dimensional wireless actuators. When remotely powered by an acoustic field, the surfaces provide highly directional propulsive forces in fluids through acoustic streaming. A maximal force of similar to 0.45mN is measured on a 4 x 4 mm(2) functional surface. The response of the surfaces with bubbles of different sizes is characterized experimentally. This shows a marked peak around the micro-bubbles' resonance frequency, as estimated by both an analytical model and numerical simulations. The strong frequency dependence can be exploited to address different surfaces with different acoustic frequencies, thus achieving wireless actuation with multiple degrees of freedom. The use of the functional surfaces as wireless ready-to-attach actuators is demonstrated by implementing a wireless and bidirectional miniaturized rotary motor, which is 2.6 x 2.6 x 5 mm(3) in size and generates a stall torque of similar to 0.5 mN.mm. The adoption of micro-structured surfaces as wireless actuators opens new possibilities in the development of miniaturized devices and tools for fluidic environments that are accessible by low intensity ultrasound fields.
DOI URL BibTeX
Empirical Inference Conference Paper Anticipative Interaction Primitives for Human-Robot Collaboration Maeda, G., Maloo, A., Ewerton, M., Lioutikov, R., Peters, J. AAAI Fall Symposium Series. Shared Autonomy in Research and Practice, 325-330, November 2016 (Published) URL BibTeX
Physical Intelligence Article Bioengineered and biohybrid bacteria-based systems for drug delivery Hosseinidoust, Z., Mostaghaci, B., Yasa, O., Park, B., Singh, A. V., Sitti, M. Advanced Drug Delivery Reviews, 106:27-44, November 2016 DOI BibTeX
Perceiving Systems Article Creating body shapes from verbal descriptions by linking similarity spaces Hill, M. Q., Streuber, S., Hahn, C. A., Black, M. J., O’Toole, A. J. Psychological Science, 27(11):1486-1497, November 2016
Brief verbal descriptions of bodies (e.g. curvy, long-legged) can elicit vivid mental images. The ease with which we create these mental images belies the complexity of three-dimensional body shapes. We explored the relationship between body shapes and body descriptions and show that a small number of words can be used to generate categorically accurate representations of three-dimensional bodies. The dimensions of body shape variation that emerged in a language-based similarity space were related to major dimensions of variation computed directly from three-dimensional laser scans of 2094 bodies. This allowed us to generate three-dimensional models of people in the shape space using only their coordinates on analogous dimensions in the language-based description space. Human descriptions of photographed bodies and their corresponding models matched closely. The natural mapping between the spaces illustrates the role of language as a concise code for body shape, capturing perceptually salient global and local body features.
pdf BibTeX
Empirical Inference Conference Paper Deep Spiking Networks for Model-based Planning in Humanoids Tanneberg, D., Paraschos, A., Peters, J., Rueckert, E. IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 656-661, IEEE, November 2016 (Published) DOI BibTeX
Empirical Inference Conference Paper Demonstration Based Trajectory Optimization for Generalizable Robot Motions Koert, D., Maeda, G., Lioutikov, R., Neumann, G., Peters, J. IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 515-522, IEEE, November 2016 (Published) DOI BibTeX
Empirical Inference Conference Paper Incremental Imitation Learning of Context-Dependent Motor Skills Ewerton, M., Maeda, G., Kollegger, G., Wiemeyer, J., Peters, J. IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids), 351-358, IEEE, November 2016 (Published) DOI BibTeX
Empirical Inference Autonomous Motion Conference Paper 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), 650-655, November 2016 (Published) final DOI URL BibTeX
Theory of Inhomogeneous Condensed Matter Article Long range correlations generated by phase separation. Exact results from field theory Delfino, G., Squarcini, A. Journal of High Energy Physics, 2016(11):119, Società italiana di fisica, Bologna, Italy, November 2016 (Published) DOI BibTeX
Micro, Nano, and Molecular Systems Article Nanomotors Alarcon-Correa, M., Walker (Schamel), D., Qiu, T., Fischer, P. Eur. Phys. J.-Special Topics, 225(11-12):2241-2254, November 2016 (Published)
This minireview discusses whether catalytically active macromolecules and abiotic nanocolloids, that are smaller than motile bacteria, can self-propel. Kinematic reversibility at low Reynolds number demands that self-propelling colloids must break symmetry. Methods that permit the synthesis and fabrication of Janus nanocolloids are therefore briefly surveyed, as well as means that permit the analysis of the nanocolloids' motion. Finally, recent work is reviewed which shows that nanoagents are small enough to penetrate the complex inhomogeneous polymeric network of biological fluids and gels, which exhibit diverse rheological behaviors.
DOI BibTeX
Micro, Nano, and Molecular Systems Article Structured light enables biomimetic swimming and versatile locomotion of photoresponsive soft microrobots Palagi, S., Mark, A. G., Reigh, S. Y., Melde, K., Qiu, T., Zeng, H., Parmeggiani, C., Martella, D., Sanchez-Castillo, A., Kapernaum, N., Giesselmann, F., Wiersma, D. S., Lauga, E., Fischer, P. Nature Materials, 15(6):647–653, November 2016, Max Planck press release, Nature News & Views. (Published)
Microorganisms move in challenging environments by periodic changes in body shape. In contrast, current artificial microrobots cannot actively deform, exhibiting at best passive bending under external fields. Here, by taking advantage of the wireless, scalable and spatiotemporally selective capabilities that light allows, we show that soft microrobots consisting of photoactive liquid-crystal elastomers can be driven by structured monochromatic light to perform sophisticated biomimetic motions. We realize continuum yet selectively addressable artificial microswimmers that generate travelling-wave motions to self-propel without external forces or torques, as well as microrobots capable of versatile locomotion behaviours on demand. Both theoretical predictions and experimental results confirm that multiple gaits, mimicking either symplectic or antiplectic metachrony of ciliate protozoa, can be achieved with single microswimmers. The principle of using structured light can be extended to other applications that require microscale actuation with sophisticated spatiotemporal coordination for advanced microrobotic technologies.
Video - Soft photo Micro-Swimmer DOI BibTeX
Autonomous Motion Conference Paper The Role of Measurement Uncertainty in Optimal Control for Contact Interactions Workshop on the Algorithmic Foundations of Robotics, 22, November 2016
Stochastic Optimal Control (SOC) typically considers noise only in the process model, i.e. unknown disturbances. However, in many robotic applications that involve interaction with the environment, such as locomotion and manipulation, uncertainty also comes from lack of pre- cise knowledge of the world, which is not an actual disturbance. We de- velop a computationally efficient SOC algorithm, based on risk-sensitive control, that takes into account uncertainty in the measurements. We include the dynamics of an observer in such a way that the control law explicitly depends on the current measurement uncertainty. We show that high measurement uncertainty leads to low impedance behaviors, a result in contrast with the effects of process noise variance that creates stiff behaviors. Simulation results on a simple 2D manipulator show that our controller can create better interaction with the environment under uncertain contact locations than traditional SOC approaches.
arXiv BibTeX
Empirical Inference Conference Paper Unifying distillation and privileged information Lopez-Paz, D., Schölkopf, B., Bottou, L., Vapnik, V. International Conference on Learning Representations (ICLR), November 2016 (Published) Arxiv BibTeX
Empirical Inference Autonomous Motion Conference Paper 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), 502-508, November 2016 (Published) DOI URL BibTeX
Physical Intelligence Conference Paper Steering control of a water-running robot using an active tail Kim, H., Jeong, K., Sitti, M., Seo, T. In Intelligent Robots and Systems (IROS), 2016 IEEE/RSJ International Conference on, 4945-4950, October 2016
Many highly dynamic novel mobile robots have been developed being inspired by animals. In this study, we are inspired by a basilisk lizard's ability to run and steer on water surface for a hexapedal robot. The robot has an active tail with a circular plate, which the robot rotates to steer on water. We dynamically modeled the platform and conducted simulations and experiments on steering locomotion with a bang-bang controller. The robot can steer on water by rotating the tail, and the controlled steering locomotion is stable. The dynamic modelling approximates the robot's steering locomotion and the trends of the simulations and experiments are similar, although there are errors between the desired and actual angles. The robot's maneuverability on water can be improved through further research.
DOI BibTeX
Physical Intelligence Article A 5-D localization method for a magnetically manipulated untethered robot using a 2-D array of Hall-effect sensors Son, D., Yim, S., Sitti, M. IEEE/ASME Transactions on Mechatronics, 21(2):708-716, October 2016
This paper introduces a new five-dimensional localization method for an untethered meso-scale magnetic robot, which is manipulated by a computer-controlled electromagnetic system. The developed magnetic localization setup is a two-dimensional array of mono-axial Hall-effect sensors, which measure the perpendicular magnetic fields at their given positions. We introduce two steps for localizing a magnetic robot more accurately. First, the dipole modeled magnetic field of the electromagnet is subtracted from the measured data in order to determine the robot's magnetic field. Secondly, the subtracted magnetic field is twice differentiated in the perpendicular direction of the array, so that the effect of the electromagnetic field in the localization process is minimized. Five variables regarding the position and orientation of the robot are determined by minimizing the error between the measured magnetic field and the modeled magnetic field in an optimization method. The resulting position error is 2.1±0.8 mm and angular error is 6.7±4.3° within the applicable range (5 cm) of magnetic field sensors at 200 Hz. The proposed localization method would be used for the position feedback control of untethered magnetic devices or robots for medical applications in the future.
DOI BibTeX
Empirical Inference Autonomous Motion Conference Paper A New Trajectory Generation Framework in Robotic Table Tennis Koc, O., Maeda, G., Peters, J. Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 3750-3756, October 2016 (Published) DOI URL BibTeX
Empirical Inference Conference Paper Active Tactile Object Exploration with Gaussian Processes Yi, Z., Calandra, R., Veiga, F., van Hoof, H., Hermans, T., Zhang, Y., Peters, J. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 4925-4930, IEEE, October 2016 (Published) DOI BibTeX
Empirical Inference Conference Paper Adaptive Training Strategies for BCIs Sharma, D., Tanneberg, D., Grosse-Wentrup, M., Peters, J., Rueckert, E. Cybathlon Symposium, October 2016 (Published) URL BibTeX
Perceiving Systems Autonomous Motion Conference Paper Barrista - Caffe Well-Served Lassner, C., Kappler, D., Kiefel, M., Gehler, P. In ACM Multimedia Open Source Software Competition, ACM OSSC16, October 2016 (Published)
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.
pdf DOI URL BibTeX
Empirical Inference Conference Paper Experiments with Hierarchical Reinforcement Learning of Multiple Grasping Policies Osa, T., Peters, J., Neumann, G. International Symposium on Experimental Robotics (ISER), 1:160-172, Springer Proceedings in Advanced Robotics, (Editors: Dana Kulic, Yoshihiko Nakamura, Oussama Khatib and Gentiane Venture), Springer, October 2016 (Published) DOI BibTeX
Physical Intelligence Article High-Performance Multiresponsive Paper Actuators Amjadi, M., Sitti, M. ACS Nano, 10(11):10202-10210, October 2016
There is an increasing demand for soft actuators because of their importance in soft robotics, artificial muscles, biomimetic devices, and beyond. However, the development of soft actuators capable of low-voltage operation, powerful actuation, and programmable shape-changing is still challenging. In this work, we propose programmable bilayer actuators that operate based on the large hygroscopic contraction of the copy paper and simultaneously large thermal expansion of the polypropylene film upon increasing the temperature. The electrothermally activated bending actuators can function with low voltages (≤ 8 V), low input electric power per area (P ≤ 0.14 W cm–2), and low temperature changes (≤ 35 °C). They exhibit reversible shape-changing behavior with curvature radii up to 1.07 cm–1 and bending angle of 360°, accompanied by powerful actuation. Besides the electrical activation, they can be powered by humidity or light irradiation. We finally demonstrate the use of our paper actuators as a soft gripper robot and a lightweight paper wing for aerial robotics.
DOI BibTeX
Perceiving Systems Conference Paper Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M. J. In Computer Vision – ECCV 2016, 561-578, Lecture Notes in Computer Science, Springer International Publishing, 14th European Conference on Computer Vision, October 2016
We describe the first method to automatically estimate the 3D pose of the human body as well as its 3D shape from a single unconstrained image. We estimate a full 3D mesh and show that 2D joints alone carry a surprising amount of information about body shape. The problem is challenging because of the complexity of the human body, articulation, occlusion, clothing, lighting, and the inherent ambiguity in inferring 3D from 2D. To solve this, we fi rst use a recently published CNN-based method, DeepCut, to predict (bottom-up) the 2D body joint locations. We then fit (top-down) a recently published statistical body shape model, called SMPL, to the 2D joints. We do so by minimizing an objective function that penalizes the error between the projected 3D model joints and detected 2D joints. Because SMPL captures correlations in human shape across the population, we are able to robustly fi t it to very little data. We further leverage the 3D model to prevent solutions that cause interpenetration. We evaluate our method, SMPLify, on the Leeds Sports, HumanEva, and Human3.6M datasets, showing superior pose accuracy with respect to the state of the art.
pdf Video Sup Mat video Code Project ppt BibTeX
Empirical Inference Conference Paper 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:734-749, (Editors: Bastian Leibe, Jiri Matas, Nicu Sebe and Max Welling), Springer, October 2016 DOI BibTeX
Autonomous Motion Conference Paper Learning Where to Search Using Visual Attention Kloss, A., Kappler, D., Lensch, H. P. A., Butz, M. V., Schaal, S., Bohg, J. Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, IEEE, IROS, October 2016 (Published)
One of the central tasks for a household robot is searching for specific objects. It does not only require localizing the target object but also identifying promising search locations in the scene if the target is not immediately visible. As computation time and hardware resources are usually limited in robotics, it is desirable to avoid expensive visual processing steps that are exhaustively applied over the entire image. The human visual system can quickly select those image locations that have to be processed in detail for a given task. This allows us to cope with huge amounts of information and to efficiently deploy the limited capacities of our visual system. In this paper, we therefore propose to use human fixation data to train a top-down saliency model that predicts relevant image locations when searching for specific objects. We show that the learned model can successfully prune bounding box proposals without rejecting the ground truth object locations. In this aspect, the proposed model outperforms a model that is trained only on the ground truth segmentations of the target object instead of fixation data.
PDF BibTeX
Empirical Inference Conference Paper Multi-task logistic regression in brain-computer interfaces Fiebig, K., Jayaram, V., Peters, J., Grosse-Wentrup, M. 6th Workshop on Brain-Machine Interface Systems at IEEE International Conference on Systems, Man, and Cybernetics (SMC 2016), 002307-002312, IEEE, October 2016 (Published) DOI URL BibTeX
Autonomous Motion Conference Paper Parameter Learning for Improving Binary Descriptor Matching Sankaran, B., Ramalingam, S., Taguchi, Y. In International Conference on Intelligent Robots and Systems (IROS) 2016, IEEE/RSJ International Conference on Intelligent Robots and Systems, October 2016 (Published)
Binary descriptors allow fast detection and matching algorithms in computer vision problems. Though binary descriptors can be computed at almost two orders of magnitude faster than traditional gradient based descriptors, they suffer from poor matching accuracy in challenging conditions. In this paper we propose three improvements for binary descriptors in their computation and matching that enhance their performance in comparison to traditional binary and non-binary descriptors without compromising their speed. This is achieved by learning some weights and threshold parameters that allow customized matching under some variations such as lighting and viewpoint. Our suggested improvements can be easily applied to any binary descriptor. We demonstrate our approach on the ORB (Oriented FAST and Rotated BRIEF) descriptor and compare its performance with the traditional ORB and SIFT descriptors on a wide variety of datasets. In all instances, our enhancements outperform standard ORB and is comparable to SIFT.
BibTeX
Empirical Inference Conference Paper Probabilistic Decomposition of Sequential Force Interaction Tasks into Movement Primitives Manschitz, S., Gienger, M., Kober, J., Peters, J. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 3920-3927, IEEE, October 2016 (Published) DOI BibTeX
Physical Intelligence Article Programmable assembly of heterogeneous microparts by an untethered mobile capillary microgripper Giltinan, J., Diller, E., Sitti, M. Lab on a Chip, 16(22):4445-4457, October 2016
At the sub-millimeter scale, capillary forces enable robust and reversible adhesion between biological organisms and varied substrates. Current human-engineered mobile untethered micromanipulation systems rely on forces which scale poorly or utilize gripper-part designs that promote manipulation. Capillary forces, alternatively, are dependent upon the surface chemistry (which is scale independent) and contact perimeter, which conforms to the part surface. We report a mobile capillary microgripper that is able to pick and place parts of various materials and geometries, and is thus ideal for microassembly tasks that cannot be accomplished by large tethered manipulators. We achieve the programmable assembly of sub-millimeter parts in an enclosed three-dimensional aqueous environment by creating a capillary bridge between the targeted part and a synthetic, untethered, mobile body. The parts include both hydrophilic and hydrophobic components: hydrogel, kapton, human hair, and biological tissue. The 200 μm untethered system can be controlled with five-degrees-of-freedom and advances progress towards autonomous desktop manufacturing for tissue engineering, complex micromachines, microfluidic devices, and meta-materials.
DOI BibTeX
Empirical Inference Conference Paper Stable Reinforcement Learning with Autoencoders for Tactile and Visual Data van Hoof, H., Chen, N., Karl, M., van der Smagt, P., Peters, J. Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems (IROS), 3928-3934, IEEE, October 2016 (Published) DOI BibTeX
Theory of Inhomogeneous Condensed Matter Article Structure and dynamics of binary liquid mixtures near their continuous demixing transitions Roy, S., Höfling, F., Dietrich, S. The Journal of Chemical Physics, 145(4):134505, American Institute of Physics, Woodbury, N.Y., October 2016 DOI BibTeX
Perceiving Systems Autonomous Motion Conference Paper Superpixel Convolutional Networks using Bilateral Inceptions Gadde, R., Jampani, V., Kiefel, M., Kappler, D., Gehler, P. In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, Springer, 14th European Conference on Computer Vision, October 2016
In this paper we propose a CNN architecture for semantic image segmentation. We introduce a new “bilateral inception” module that can be inserted in existing CNN architectures and performs bilateral filtering, at multiple feature-scales, between superpixels in an image. The feature spaces for bilateral filtering and other parameters of the module are learned end-to-end using standard backpropagation techniques. The bilateral inception module addresses two issues that arise with general CNN segmentation architectures. First, this module propagates information between (super) pixels while respecting image edges, thus using the structured information of the problem for improved results. Second, the layer recovers a full resolution segmentation result from the lower resolution solution of a CNN. In the experiments, we modify several existing CNN architectures by inserting our inception modules between the last CNN (1 × 1 convolution) layers. Empirical results on three different datasets show reliable improvements not only in comparison to the baseline networks, but also in comparison to several dense-pixel prediction techniques such as CRFs, while being competitive in time.
pdf supplementary poster BibTeX
Micro, Nano, and Molecular Systems Article A loop-gap resonator for chirality-sensitive nuclear magneto-electric resonance (NMER) Garbacz, P., Fischer, P., Kraemer, S. J. Chem. Phys., 145(10):104201, September 2016 (Published)
Direct detection of molecular chirality is practically impossible by methods of standard nuclear magnetic resonance (NMR) that is based on interactions involving magnetic-dipole and magnetic-field operators. However, theoretical studies provide a possible direct probe of chirality by exploiting an enantiomer selective additional coupling involving magnetic-dipole, magnetic-field, and electric field operators. This offers a way for direct experimental detection of chirality by nuclear magneto-electric resonance (NMER). This method uses both resonant magnetic and electric radiofrequency (RF) fields. The weakness of the chiral interaction though requires a large electric RF field and a small transverse RF magnetic field over the sample volume, which is a non-trivial constraint. In this study, we present a detailed study of the NMER concept and a possible experimental realization based on a loop-gap resonator. For this original device, the basic principle and numerical studies as well as fabrication and measurements of the frequency dependence of the scattering parameter are reported. By simulating the NMER spin dynamics for our device and taking the F-19 NMER signal of enantiomer-pure 1,1,1-trifluoropropan-2-ol, we predict a chirality induced NMER signal that accounts for 1%-5% of the standard achiral NMR signal. Published by AIP Publishing.
DOI BibTeX
Physical Intelligence Article Bacteria-Driven Particles: Patterned and Specific Attachment of Bacteria on Biohybrid Bacteria-Driven Microswimmers (Adv. Healthcare Mater. 18/2016) Singh, A. V., Sitti, M. Advanced Healthcare Materials, 5(18):2306-2306, September 2016
On page 2325, Ajay Vikram Singh and Metin Sitti propose a facile surface patterning technique and a specific, strong biotin–streptavidin bonding of bacteria on patterned surfaces to fabricate Janus particles that are propelled by the attached bacteria. Such bacteria-driven Janus microswimmers could be used for future medicine in targeted drug delivery and environmental remediation.
DOI BibTeX
Empirical Inference Conference Paper Bidirektionale Interaktion zwischen Mensch und Roboter beim Bewegungslernen (BIMROB) Kollegger, G., Ewerton, M., Peters, J., Wiemeyer, J. 11. Symposium der DVS Sportinformatik, September 2016 (Published) URL BibTeX
Micro, Nano, and Molecular Systems Article Capture of 2D Microparticle Arrays via a UV-Triggered Thiol-yne “Click” Reaction Walker (Schamel), D., Singh, D. P., Fischer, P. Advanced Materials, 28(44):9846-9850, September 2016 (Published)
Immobilization of colloidal assemblies onto solid supports via a fast UV-triggered click-reaction is achieved. Transient assemblies of microparticles and colloidal materials can be captured and transferred to solid supports. The technique does not require complex reaction conditions, and is compatible with a variety of particle assembly methods.
DOI BibTeX
Physical Intelligence Article Composition-dependent underwater adhesion of catechol-bearing hydrogels Wu, H., Sariola, V., Zhao, J., Ding, H., Sitti, M., Bettinger, C. J. Polymer International, 65(11):1355-1359, September 2016
Interfacial adhesion-mediated transfer printing processes can integrate functional electronic microstructures with polymeric substrates that are bendable and stretchable. Transfer printing has also been extended to catechol-bearing adhesive hydrogels. This study presents indentation adhesion tests between catechol-bearing hydrogel substrates with catechol concentrations varying from 0 to 10% (mol/mol) and thin-film materials commonly used in microelectronic fabrication including polymers, noble metals and oxides. The results indicate that the interfacial adhesion of catechol-bearing hydrogels is positively correlated with the concentration of catechol-bearing monomers as well as the retraction velocity during transfer printing. This study can inform transfer printing processes for microfabricated structures to compliant hydrated substrates such as hygroscopic monomers, mesoporous polymer networks and hydrogels. © 2016 Society of Chemical Industry
DOI BibTeX
Empirical Inference Article Contextual Policy Search for Linear and Nonlinear Generalization of a Humanoid Walking Controller Abdolmaleki, A., Lau, N., Reis, L., Peters, J., Neumann, G. Journal of Intelligent & Robotic Systems, 83(3-4):393-408, (Editors: Luis Almeida, Lino Marques ), September 2016, Special Issue: Autonomous Robot Systems (Published) DOI BibTeX
Empirical Inference Conference Paper Depth Estimation Through a Generative Model of Light Field Synthesis Sajjadi, M. S. M., Köhler, R., Schölkopf, B., Hirsch, M. Pattern Recognition - 38th German Conference (GCPR), 9796:426-438, Lecture Notes in Computer Science, (Editors: Rosenhahn, B. and Andres, B.), Springer International Publishing, September 2016 Arxiv Project DOI URL BibTeX