Header logo is


2020


no image
Algorithmic recourse under imperfect causal knowledge: a probabilistic approach

Karimi*, A., von Kügelgen*, J., Schölkopf, B., Valera, I.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020, *equal contribution (conference) Accepted

ei

arXiv [BibTex]

2020


arXiv [BibTex]


no image
Self-Paced Deep Reinforcement Learning

Klink, P., D’Eramo, C., Peters, J., Pajarinen, J.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Probabilistic Linear Solvers for Machine Learning

Wenger, J., Hennig, P.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Barking up the right tree: an approach to search over molecule synthesis DAGs

Bradshaw, J., Paige, B., Kusner, M., Segler, M., Hernández-Lobato, J. M.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Learning Kernel Tests Without Data Splitting

Kübler, J., Jitkrittum, W., Schölkopf, B., Muandet, K.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Dual Instrumental Variable Regression

Muandet, K., Mehrjou, A., Lee, S. K., Raj, A.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
A Measure-Theoretic Approach to Kernel Conditional Mean Embeddings

Park, J., Muandet, K.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
MATE: Plugging in Model Awareness to Task Embedding for Meta Learning

Chen, X., Wang, Z., Tang, S., Muandet, K.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Object-Centric Learning with Slot Attention

Locatello, F., Weissenborn, D., Unterthiner, T., Mahendran, A., Heigold, G., Uszkoreit, J., Dosovitskiy, A., Kipf, T.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Relative gradient optimization of the Jacobian term in unsupervised deep learning

Gresele, L., Fissore, G., Javaloy, A., Schölkopf, B., Hyvarinen, A.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Causal analysis of Covid-19 Spread in Germany

Mastakouri, A., Schölkopf, B.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Modeling Shared responses in Neuroimaging Studies through MultiView ICA

Richard, H., Gresele, L., Hyvarinen, A., Thirion, B., Gramfort, A., Ablin, P.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Stochastic Stein Discrepancies

Gorham, J., Raj, A., Mackey, L.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


no image
Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining

Tripp, A., Daxberger, E., Hernández-Lobato, J. M.

Advances in Neural Information Processing Systems 33, 34th Annual Conference on Neural Information Processing Systems, December 2020 (conference) Accepted

ei

[BibTex]

[BibTex]


Utilizing Interviews and Thematic Analysis to Uncover Specifications for a Companion Robot
Utilizing Interviews and Thematic Analysis to Uncover Specifications for a Companion Robot

Burns, R. B., Seifi, H., Lee, H., Kuchenbecker, K. J.

Workshop paper (2 pages) presented at the ICSR Workshop on Enriching HRI Research with Qualitative Methods, Virtual, November 2020 (misc)

Abstract
We will share our experiences designing and conducting structured video-conferencing interviews with autism specialists and utilizing thematic analysis to create qualitative requirements and quantitative specifications for a touch-perceiving robot companion tailored for children with autism. We will also explain how we wrote about our qualitative approaches for a journal setting.

hi

link (url) [BibTex]

link (url) [BibTex]


Grasping Field: Learning Implicit Representations for Human Grasps
Grasping Field: Learning Implicit Representations for Human Grasps

Karunratanakul, K., Yang, J., Zhang, Y., Black, M., Muandet, K., Tang, S.

In International Conference on 3D Vision (3DV), November 2020 (inproceedings)

Abstract
Robotic grasping of house-hold objects has made remarkable progress in recent years. Yet, human grasps are still difficult to synthesize realistically. There are several key reasons: (1) the human hand has many degrees of freedom (more than robotic manipulators); (2) the synthesized hand should conform to the surface of the object; and (3) it should interact with the object in a semantically and physically plausible manner. To make progress in this direction, we draw inspiration from the recent progress on learning-based implicit representations for 3D object reconstruction. Specifically, we propose an expressive representation for human grasp modelling that is efficient and easy to integrate with deep neural networks. Our insight is that every point in a three-dimensional space can be characterized by the signed distances to the surface of the hand and the object, respectively. Consequently, the hand, the object, and the contact area can be represented by implicit surfaces in a common space, in which the proximity between the hand and the object can be modelled explicitly. We name this 3D to 2D mapping as Grasping Field, parameterize it with a deep neural network, and learn it from data. We demonstrate that the proposed grasping field is an effective and expressive representation for human grasp generation. Specifically, our generative model is able to synthesize high-quality human grasps, given only on a 3D object point cloud. The extensive experiments demonstrate that our generative model compares favorably with a strong baseline and approaches the level of natural human grasps. Furthermore, based on the grasping field representation, we propose a deep network for the challenging task of 3D hand-object interaction reconstruction from a single RGB image. Our method improves the physical plausibility of the hand-object contact reconstruction and achieves comparable performance for 3D hand reconstruction compared to state-of-the-art methods. Our model and code are available for research purpose at https://github.com/korrawe/grasping_field.

ei ps

pdf arXiv code [BibTex]


{GIF}: Generative Interpretable Faces
GIF: Generative Interpretable Faces

Ghosh, P., Gupta, P. S., Uziel, R., Ranjan, A., Black, M. J., Bolkart, T.

In International Conference on 3D Vision (3DV), November 2020 (inproceedings)

Abstract
Photo-realistic visualization and animation of expressive human faces have been a long standing challenge. 3D face modeling methods provide parametric control but generates unrealistic images, on the other hand, generative 2D models like GANs (Generative Adversarial Networks) output photo-realistic face images, but lack explicit control. Recent methods gain partial control, either by attempting to disentangle different factors in an unsupervised manner, or by adding control post hoc to a pre-trained model. Unconditional GANs, however, may entangle factors that are hard to undo later. We condition our generative model on pre-defined control parameters to encourage disentanglement in the generation process. Specifically, we condition StyleGAN2 on FLAME, a generative 3D face model. While conditioning on FLAME parameters yields unsatisfactory results, we find that conditioning on rendered FLAME geometry and photometric details works well. This gives us a generative 2D face model named GIF (Generative Interpretable Faces) that offers FLAME's parametric control. Here, interpretable refers to the semantic meaning of different parameters. Given FLAME parameters for shape, pose, expressions, parameters for appearance, lighting, and an additional style vector, GIF outputs photo-realistic face images. We perform an AMT based perceptual study to quantitatively and qualitatively evaluate how well GIF follows its conditioning. The code, data, and trained model are publicly available for research purposes at http://gif.is.tue.mpg.de

ps

pdf project code [BibTex]

pdf project code [BibTex]


{PLACE}: Proximity Learning of Articulation and Contact in {3D} Environments
PLACE: Proximity Learning of Articulation and Contact in 3D Environments

Zhang, S., Zhang, Y., Ma, Q., Black, M. J., Tang, S.

In International Conference on 3D Vision (3DV), November 2020 (inproceedings)

Abstract
High fidelity digital 3D environments have been proposed in recent years, however, it remains extremely challenging to automatically equip such environment with realistic human bodies. Existing work utilizes images, depth or semantic maps to represent the scene, and parametric human models to represent 3D bodies. While being straight-forward, their generated human-scene interactions often lack of naturalness and physical plausibility. Our key observation is that humans interact with the world through body-scene contact. To synthesize realistic human-scene interactions, it is essential to effectively represent the physical contact and proximity between the body and the world. To that end, we propose a novel interaction generation method, named PLACE(Proximity Learning of Articulation and Contact in 3D Environments), which explicitly models the proximity between the human body and the 3D scene around it. Specifically, given a set of basis points on a scene mesh, we leverage a conditional variational autoencoder to synthesize the minimum distances from the basis points to the human body surface. The generated proximal relationship exhibits which region of the scene is in contact with the person. Furthermore, based on such synthesized proximity, we are able to effectively obtain expressive 3D human bodies that interact with the 3D scene naturally. Our perceptual study shows that PLACE significantly improves the state-of-the-art method, approaching the realism of real human-scene interaction. We believe our method makes an important step towards the fully automatic synthesis of realistic 3D human bodies in 3D scenes. The code and model are available for research at https://sanweiliti.github.io/PLACE/PLACE.html

ps

pdf arXiv project code [BibTex]

pdf arXiv project code [BibTex]


Postural stability in human running with step-down perturbations: an experimental and numerical study
Postural stability in human running with step-down perturbations: an experimental and numerical study

Özge Drama, , Johanna Vielemeyer, , Alexander Badri-Spröwitz, , Müller, R.

Royal Society Open Science, 7, November 2020 (article)

Abstract
Postural stability is one of the most crucial elements in bipedal locomotion. Bipeds are dynamically unstable and need to maintain their trunk upright against the rotations induced by the ground reaction forces (GRFs), especially when running. Gait studies report that the GRF vectors focus around a virtual point above the center of mass (VPA), while the trunk moves forward in pitch axis during the stance phase of human running. However, a recent simulation study suggests that a virtual point below the center of mass (VPB) might be present in human running, since a VPA yields backward trunk rotation during the stance phase. In this work, we perform a gait analysis to investigate the existence and location of the VP in human running at 5 m s−1, and support our findings numerically using the spring-loaded inverted pendulum model with a trunk (TSLIP). We extend our analysis to include perturbations in terrain height (visible and camouflaged), and investigate the response of the VP mechanism to step-down perturbations both experimentally and numerically. Our experimental results show that the human running gait displays a VPB of ≈ −30 cm and a forward trunk motion during the stance phase. The camouflaged step-down perturbations affect the location of the VPB. Our simulation results suggest that the VPB is able to encounter the step-down perturbations and bring the system back to its initial equilibrium state.

dlg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Sampling on networks: estimating spectral centrality measures and their impact in evaluating other relevant network measures

Ruggeri, N., De Bacco, C.

Applied Network Science, 5:81, October 2020 (article)

Abstract
We perform an extensive analysis of how sampling impacts the estimate of several relevant network measures. In particular, we focus on how a sampling strategy optimized to recover a particular spectral centrality measure impacts other topological quantities. Our goal is on one hand to extend the analysis of the behavior of TCEC [Ruggeri2019], a theoretically-grounded sampling method for eigenvector centrality estimation. On the other hand, to demonstrate more broadly how sampling can impact the estimation of relevant network properties like centrality measures different than the one aimed at optimizing, community structure and node attribute distribution. Finally, we adapt the theoretical framework behind TCEC for the case of PageRank centrality and propose a sampling algorithm aimed at optimizing its estimation. We show that, while the theoretical derivation can be suitably adapted to cover this case, the resulting algorithm suffers of a high computational complexity that requires further approximations compared to the eigenvector centrality case.

pio

Code Preprint pdf DOI [BibTex]


no image
Optimal transport for multi-commodity routing on networks

Lonardi, A., Facca, E., Putti, M., De Bacco, C.

October 2020 (article) Submitted

Abstract
We present a model for finding optimal multi-commodity flows on networks based on optimal transport theory. The model relies on solving a dynamical system of equations. We prove that its stationary solution is equivalent to the solution of an optimization problem that generalizes the one-commodity framework. In particular, it generalizes previous results in terms of optimality, scaling, and phase transitions obtained in the one-commodity case. Remarkably, for a suitable range of parameters, the optimal topologies have loops. This is radically different to the one-commodity case, where within an analogous parameter range the optimal topologies are trees. This important result is a consequence of the extension of Kirkchoff's law to the multi-commodity case, which enforces the distinction between fluxes of the different commodities. Our results provide new insights into the nature and properties of optimal network topologies. In particular, they show that loops can arise as a consequence of distinguishing different flow types, and complement previous results where loops, in the one-commodity case, were arising as a consequence of imposing dynamical rules to the sources and sinks or when enforcing robustness to damage. Finally, we provide an efficient implementation for each of the two equivalent numerical frameworks, both of which achieve a computational complexity that is more efficient than that of standard optimization methods based on gradient descent. As a result, our model is not merely abstract but can be efficiently applied to large datasets. We give an example of concrete application by studying the network of the Paris metro.

pio

Code Preprint [BibTex]


AirCapRL: Autonomous Aerial Human Motion Capture Using Deep Reinforcement Learning
AirCapRL: Autonomous Aerial Human Motion Capture Using Deep Reinforcement Learning

Tallamraju, R., Saini, N., Bonetto, E., Pabst, M., Liu, Y. T., Black, M., Ahmad, A.

IEEE Robotics and Automation Letters, IEEE Robotics and Automation Letters, 5(4):6678 - 6685, IEEE, October 2020, Also accepted and presented in the 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). (article)

Abstract
In this letter, we introduce a deep reinforcement learning (DRL) based multi-robot formation controller for the task of autonomous aerial human motion capture (MoCap). We focus on vision-based MoCap, where the objective is to estimate the trajectory of body pose, and shape of a single moving person using multiple micro aerial vehicles. State-of-the-art solutions to this problem are based on classical control methods, which depend on hand-crafted system, and observation models. Such models are difficult to derive, and generalize across different systems. Moreover, the non-linearities, and non-convexities of these models lead to sub-optimal controls. In our work, we formulate this problem as a sequential decision making task to achieve the vision-based motion capture objectives, and solve it using a deep neural network-based RL method. We leverage proximal policy optimization (PPO) to train a stochastic decentralized control policy for formation control. The neural network is trained in a parallelized setup in synthetic environments. We performed extensive simulation experiments to validate our approach. Finally, real-robot experiments demonstrate that our policies generalize to real world conditions.

ps

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
MYND: Unsupervised Evaluation of Novel BCI Control Strategies on Consumer Hardware

Hohmann, M. R., Konieczny, L., Hackl, M., Wirth, B., Zaman, T., Enficiaud, R., Grosse-Wentrup, M., Schölkopf, B.

Proceedings of the 33rd Annual ACM Symposium on User Interface Software and Technology (UIST), October 2020 (conference) Accepted

ei

arXiv DOI [BibTex]

arXiv DOI [BibTex]


no image
Dynamic Analysis of Doubly Curved Composite Panels Using Lamination Parameters and Spectral-Tchebychev Method

Serhat, G., Anamagh, M. R., Bediz, B., Basdogan, I.

Computers & Structures, 239, pages: 106294, October 2020 (article)

Abstract
Efficient modeling and optimization techniques are required to overcome the high design complexity and computational costs concerning the engineering of composite structures. In this paper, a modeling framework for the dynamic analysis of doubly curved composite panels is developed. Lamination parameters are used to characterize the stiffness properties of the laminate, and the responses are calculated through the two-dimensional spectral-Tchebychev method. The proposed framework combines the computational efficiency advantages of both lamination parameters formulation and spectral-Tchebychev method which is extended for dynamic analysis of curved composite laminates. Compared to the finite element method, the developed model significantly decreases the computation duration, thereby leading to analysis speed-ups up to 40 folds. In the case studies, fundamental frequency contours for the doubly curved composite panels are obtained in lamination parameters space for the first time. The results show that, unlike flat or singly curved laminates, the maximum frequency design points for doubly curved panels can be inside the feasible region of lamination parameters requiring multiple layer angles. The fundamental mode shapes for the maximum frequency designs are also computed to investigate the influence of panel curvatures on the vibration patterns, which can exhibit mode switching phenomenon.

hi

DOI [BibTex]

DOI [BibTex]


Label Efficient Visual Abstractions for Autonomous Driving
Label Efficient Visual Abstractions for Autonomous Driving

Behl, A., Chitta, K., Prakash, A., Ohn-Bar, E., Geiger, A.

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, October 2020 (conference)

Abstract
It is well known that semantic segmentation can be used as an effective intermediate representation for learning driving policies. However, the task of street scene semantic segmentation requires expensive annotations. Furthermore, segmentation algorithms are often trained irrespective of the actual driving task, using auxiliary image-space loss functions which are not guaranteed to maximize driving metrics such as safety or distance traveled per intervention. In this work, we seek to quantify the impact of reducing segmentation annotation costs on learned behavior cloning agents. We analyze several segmentation-based intermediate representations. We use these visual abstractions to systematically study the trade-off between annotation efficiency and driving performance, ie, the types of classes labeled, the number of image samples used to learn the visual abstraction model, and their granularity (eg, object masks vs. 2D bounding boxes). Our analysis uncovers several practical insights into how segmentation-based visual abstractions can be exploited in a more label efficient manner. Surprisingly, we find that state-of-the-art driving performance can be achieved with orders of magnitude reduction in annotation cost. Beyond label efficiency, we find several additional training benefits when leveraging visual abstractions, such as a significant reduction in the variance of the learned policy when compared to state-of-the-art end-to-end driving models.

avg

pdf slides video Project Page [BibTex]

pdf slides video Project Page [BibTex]


Learning a statistical full spine model from partial observations
Learning a statistical full spine model from partial observations

Meng, D., Keller, M., Boyer, E., Black, M., Pujades, S.

In Shape in Medical Imaging, pages: 122,133, (Editors: Reuter, Martin and Wachinger, Christian and Lombaert, Hervé and Paniagua, Beatriz and Goksel, Orcun and Rekik, Islem), Springer International Publishing, October 2020 (inproceedings)

Abstract
The study of the morphology of the human spine has attracted research attention for its many potential applications, such as image segmentation, bio-mechanics or pathology detection. However, as of today there is no publicly available statistical model of the 3D surface of the full spine. This is mainly due to the lack of openly available 3D data where the full spine is imaged and segmented. In this paper we propose to learn a statistical surface model of the full-spine (7 cervical, 12 thoracic and 5 lumbar vertebrae) from partial and incomplete views of the spine. In order to deal with the partial observations we use probabilistic principal component analysis (PPCA) to learn a surface shape model of the full spine. Quantitative evaluation demonstrates that the obtained model faithfully captures the shape of the population in a low dimensional space and generalizes to left out data. Furthermore, we show that the model faithfully captures the global correlations among the vertebrae shape. Given a partial observation of the spine, i.e. a few vertebrae, the model can predict the shape of unseen vertebrae with a mean error under 3 mm. The full-spine statistical model is trained on the VerSe 2019 public dataset and is publicly made available to the community for non-commercial purposes. (https://gitlab.inria.fr/spine/spine_model)

ps

Gitlab Code PDF DOI [BibTex]

Gitlab Code PDF DOI [BibTex]


Chiroptical spectroscopy of a freely diffusing single nanoparticle
Chiroptical spectroscopy of a freely diffusing single nanoparticle

Sachs, J., Günther, J., Mark, A. G., Fischer, P.

Nature Communications, 11(4513), September 2020 (article)

Abstract
Chiral plasmonic nanoparticles can exhibit strong chiroptical signals compared to the corresponding molecular response. Observations are, however, generally restricted to measurements on stationary single particles with a fixed orientation, which complicates the spectral analysis. Here, we report the spectroscopic observation of a freely diffusing single chiral nanoparticle in solution. By acquiring time-resolved circular differential scattering signals we show that the spectral interpretation is significantly simplified. We experimentally demonstrate the equivalence between time-averaged chiral spectra observed for an individual nanostructure and the corresponding ensemble spectra, and thereby demonstrate the ergodic principle for chiroptical spectroscopy. We also show how it is possible for an achiral particle to yield an instantaneous chiroptical response, whereas the time-averaged signals are an unequivocal measure of chirality. Time-resolved chiroptical spectroscopy on a freely moving chiral nanoparticle advances the field of single-particle spectroscopy, and is a means to obtain the true signature of the nanoparticle’s chirality.

pf

link (url) DOI [BibTex]


no image
Community detection with node attributes in multilayer networks

Contisciani, M., Power, E. A., De Bacco, C.

Nature Scientific Reports, 10, pages: 15736, September 2020 (article)

pio

Code Preprint pdf [BibTex]

Code Preprint pdf [BibTex]


Microchannels with Self-Pumping Walls
Microchannels with Self-Pumping Walls

Yu, T., Athanassiadis, A., Popescu, M., Chikkadi, V., Güth, A., Singh, D., Qiu, T., Fischer, P.

ACS Nano, September 2020 (article)

Abstract
When asymmetric Janus micromotors are immobilized on a surface, they act as chemically powered micropumps, turning chemical energy from the fluid into a bulk flow. However, such pumps have previously produced only localized recirculating flows, which cannot be used to pump fluid in one direction. Here, we demonstrate that an array of three-dimensional, photochemically active Au/TiO2 Janus pillars can pump water. Upon UV illumination, a water-splitting reaction rapidly creates a directional bulk flow above the active surface. By lining a 2D microchannel with such active surfaces, various flow profiles are created within the channels. Analytical and numerical models of a channel with active surfaces predict flow profiles that agree very well with the experimental results. The light-driven active surfaces provide a way to wirelessly pump fluids at small scales and could be used for real-time, localized flow control in complex microfluidic networks.

pf

link (url) DOI [BibTex]


Scalable Fabrication of Molybdenum Disulfide Nanostructures and their Assembly
Scalable Fabrication of Molybdenum Disulfide Nanostructures and their Assembly

Huang, Y., Yu, K., Li, H., Liang, Z., Walker, D., Ferreira, P., Fischer, P., Fan, D.

Adv. Mat., (2003439), September 2020 (article)

Abstract
Molybdenum disulfide (MoS2) is a multifunctional material that can be used for various applications. In the single‐crystalline form, MoS2 shows superior electronic properties. It is also an exceptionally useful nanomaterial in its polycrystalline form with applications in catalysis, energy storage, water treatment, and gas sensing. Here, the scalable fabrication of longitudinal MoS2 nanostructures, i.e., nanoribbons, and their oxide hybrids with tunable dimensions in a rational and well‐reproducible fashion, is reported. The nanoribbons, obtained at different reaction stages, that is, MoO3, MoS2/MoO2 hybrid, and MoS2, are fully characterized. The growth method presented herein has a high yield and is particularly robust. The MoS2 nanoribbons can readily be removed from its substrate and dispersed in solution. It is shown that functionalized MoS2 nanoribbons can be manipulated in solution and assembled in controlled patterns and directly on microelectrodes with UV‐click‐chemistry. Owing to the high chemical purity and polycrystalline nature, the MoS2 nanostructures demonstrate rapid optoelectronic response to wavelengths from 450 to 750 nm, and successfully remove mercury contaminants from water. The scalable fabrication and manipulation followed by light‐directed assembly of MoS2 nanoribbons, and their unique properties, will be inspiring for device fabrication and applications of the transition metal dichalcogenides.

pf

link (url) [BibTex]

link (url) [BibTex]


Spatial ultrasound modulation by digitally controlling microbubble arrays
Spatial ultrasound modulation by digitally controlling microbubble arrays

Ma, Z., Melde, K., Athanassiadis, A. G., Schau, M., Richter, H., Qiu, T., Fischer, P.

Nature Communications, 11(4537), September 2020 (article)

Abstract
Acoustic waves, capable of transmitting through optically opaque objects, have been widely used in biomedical imaging, industrial sensing and particle manipulation. High-fidelity wavefront shaping is essential to further improve performance in these applications. An acoustic analog to the successful spatial light modulator (SLM) in optics would be highly desirable. To date there have been no techniques shown that provide effective and dynamic modulation of a sound wave and which also support scale-up to a high number of individually addressable pixels. In the present study, we introduce a dynamic spatial ultrasound modulator (SUM),which dynamically reshapes incident plane waves into complex acoustic images. Its trans-mission function is set with a digitally generated pattern of microbubbles controlled by a complementary metal–oxide–semiconductor (CMOS) chip, which results in a binary amplitude acoustic hologram. We employ this device to project sequentially changing acoustic images and demonstrate the first dynamic parallel assembly of microparticles using a SUM.

pf

link (url) DOI [BibTex]


Characterization of a Magnetic Levitation Haptic Interface for Realistic Tool-Based Interactions
Characterization of a Magnetic Levitation Haptic Interface for Realistic Tool-Based Interactions

Lee, H., Tombak, G. I., Park, G., Kuchenbecker, K. J.

Work-in-progress poster presented at EuroHaptics, Leiden, The Netherlands, September 2020 (misc)

Abstract
We introduce our recent study on the characterization of a commercial magnetic levitation haptic interface (MagLev 200, Butterfly Haptics LLC) for realistic high-bandwidth interactions. This device’s haptic rendering scheme can provide strong 6-DoF (force and torque) feedback without friction at all poses in its small workspace. The objective of our study is to enable the device to accurately render realistic multidimensional vibrotactile stimuli measured from a stylus-like tool. Our approach is to characterize the dynamics between the commanded wrench and the resulting translational acceleration across the frequency range of interest. To this end, we first custom-designed and attached a pen-shaped manipulandum (11.5 cm, aluminum) to the top of the MagLev 200’s end-effector for better usability in grasping. An accelerometer (ADXL354, Analog Devices) was rigidly mounted inside the manipulandum. Then, we collected a data set where the input is a 30-second-long force and/or torque signal commanded as a sweep function from 10 to 500 Hz; the output is the corresponding acceleration measurement, which we collected both with and without a user holding the handle. We succeeded at fitting both non-parametric and parametric versions of the transfer functions for both scenarios, with a fitting accuracy of about 95% for the parametric transfer functions. In the future, we plan to find the best method of applying the inverse parametric transfer function to our system. We will then employ that compensation method in a user study to evaluate the realism of different algorithms for reducing the dimensionality of tool-based vibrotactile cues.

hi

link (url) [BibTex]

link (url) [BibTex]


A little damping goes a long way: a simulation study of how damping influences task-level stability in running
A little damping goes a long way: a simulation study of how damping influences task-level stability in running

Heim, S., Millard, M., Mouel, C. L., Badri-Spröwitz, A.

Biology Letters, 16(9), September 2020 (article)

Abstract
It is currently unclear if damping plays a functional role in legged locomotion, and simple models often do not include damping terms. We present a new model with a damping term that is isolated from other parameters: that is, the damping term can be adjusted without retuning other model parameters for nominal motion. We systematically compare how increased damping affects stability in the face of unexpected ground-height perturbations. Unlike most studies, we focus on task-level stability: instead of observing whether trajectories converge towards a nominal limit-cycle, we quantify the ability to avoid falls using a recently developed mathematical measure. This measure allows trajectories to be compared quantitatively instead of only being separated into a binary classification of ‘stable' or ‘unstable'. Our simulation study shows that increased damping contributes significantly to task-level stability; however, this benefit quickly plateaus after only a small amount of damping. These results suggest that the low intrinsic damping values observed experimentally may have stability benefits and are not simply minimized for energetic reasons. All Python code and data needed to generate our results are available open source.

dlg ics

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Tactile Textiles: An Assortment of Fabric-Based Tactile Sensors for Contact Force and Contact Location
Tactile Textiles: An Assortment of Fabric-Based Tactile Sensors for Contact Force and Contact Location

Burns, R. B., Thomas, N., Lee, H., Faulkner, R., Kuchenbecker, K. J.

Hands-on demonstration presented at EuroHaptics, Leiden, The Netherlands, September 2020, Rachael Bevill Burns, Neha Thomas, and Hyosang Lee contributed equally to this publication (misc)

Abstract
Fabric-based tactile sensors are promising for the construction of robotic skin due to their soft and flexible nature. Conductive fabric layers can be used to form piezoresistive structures that are sensitive to contact force and/or contact location. This demonstration showcases three diverse fabric-based tactile sensors we have created. The first detects dynamic tactile events anywhere within a region on a robot’s body. The second design measures the precise location at which a single low-force contact is applied. The third sensor uses electrical resistance tomography to output both the force and location of multiple simultaneous contacts applied across a surface.

hi

Project Page Project Page [BibTex]

Project Page Project Page [BibTex]


no image
Estimating Human Handshape by Feeling the Wrist

Forte, M., Young, E. M., Kuchenbecker, K. J.

Work-in-progress poster presented at EuroHaptics, Leiden, The Netherlands, September 2020 (misc)

hi

[BibTex]

[BibTex]


Combining learned and analytical models for predicting action effects from sensory data
Combining learned and analytical models for predicting action effects from sensory data

Kloss, A., Schaal, S., Bohg, J.

International Journal of Robotics Research, September 2020 (article)

Abstract
One of the most basic skills a robot should possess is predicting the effect of physical interactions with objects in the environment. This enables optimal action selection to reach a certain goal state. Traditionally, dynamics are approximated by physics-based analytical models. These models rely on specific state representations that may be hard to obtain from raw sensory data, especially if no knowledge of the object shape is assumed. More recently, we have seen learning approaches that can predict the effect of complex physical interactions directly from sensory input. It is however an open question how far these models generalize beyond their training data. In this work, we investigate the advantages and limitations of neural network based learning approaches for predicting the effects of actions based on sensory input and show how analytical and learned models can be combined to leverage the best of both worlds. As physical interaction task, we use planar pushing, for which there exists a well-known analytical model and a large real-world dataset. We propose to use a convolutional neural network to convert raw depth images or organized point clouds into a suitable representation for the analytical model and compare this approach to using neural networks for both, perception and prediction. A systematic evaluation of the proposed approach on a very large real-world dataset shows two main advantages of the hybrid architecture. Compared to a pure neural network, it significantly (i) reduces required training data and (ii) improves generalization to novel physical interaction.

am

arXiv pdf link (url) DOI [BibTex]


no image
Optimal Sensor Placement for Recording the Contact Vibrations of a Medical Tool

Gourishetti, R., Serhat, G., Kuchenbecker, K. J.

Work in Progress poster presented at EuroHaptics, Leiden, The Netherlands, EuroHaptics 2020, September 2020 (misc)

[BibTex]

[BibTex]


Sweat Softens the Outermost Layer of the Human Finger Pad: Evidence from Simulations and Experiments
Sweat Softens the Outermost Layer of the Human Finger Pad: Evidence from Simulations and Experiments

Nam, S., Kuchenbecker, K. J.

Work-in-progress poster presented at EuroHaptics, Leiden, The Netherlands, September 2020, Award for best poster in 2020 (misc)

hi

Project Page [BibTex]

Project Page [BibTex]


no image
Intermediate Ridges Amplify Mechanoreceptor Strains in Static and Dynamic Touch

Serhat, G., Kuchenbecker, K. J.

Work-in-progress poster presented at EuroHaptics, Leiden, The Netherlands, September 2020 (misc)

hi

[BibTex]

[BibTex]


no image
Seeing Through Touch: Contact-Location Sensing and Tactile Feedback for Prosthetic Hands

Thomas, N., Kuchenbecker, K. J.

Work-in-progress poster presented at EuroHaptics, Leiden, The Netherlands, September 2020 (misc)

Abstract
Locating and picking up an object without vision is a simple task for able-bodied people, due in part to their rich tactile perception capabilities. The same cannot be said for users of standard myoelectric prostheses, who must rely largely on visual cues to successfully interact with the environment. To enable prosthesis users to locate and grasp objects without looking at them, we propose two changes: adding specialized contact-location sensing to the dorsal and palmar aspects of the prosthetic hand’s fingers, and providing the user with tactile feedback of where an object touches the fingers. To evaluate the potential utility of these changes, we developed a simple, sensitive, fabric-based tactile sensor which provides continuous contact location information via a change in voltage of a voltage divider circuit. This sensor was wrapped around the fingers of a commercial prosthetic hand (Ottobock SensorHand Speed). Using an ATI Nano17 force sensor, we characterized the tactile sensor’s response to normal force at distributed contact locations and obtained an average detection threshold of 0.63 +/- 0.26 N. We also confirmed that the voltage-to-location mapping is linear (R squared = 0.99). Sensor signals were adapted to the stationary vibrotactile funneling illusion to provide haptic feedback of contact location. These preliminary results indicate a promising system that imitates a key aspect of the sensory capabilities of the intact hand. Future work includes testing the system in a modified reach-grasp-and-lift study, in which participants must accomplish the task blindfolded.

hi

[BibTex]

[BibTex]


A Gamified App that Helps People Overcome Self-Limiting Beliefs by Promoting Metacognition
A Gamified App that Helps People Overcome Self-Limiting Beliefs by Promoting Metacognition

Amo, V., Lieder, F.

SIG 8 Meets SIG 16, September 2020 (conference) Accepted

Abstract
Previous research has shown that approaching learning with a growth mindset is key for maintaining motivation and overcoming setbacks. Mindsets are systems of beliefs that people hold to be true. They influence a person's attitudes, thoughts, and emotions when they learn something new or encounter challenges. In clinical psychology, metareasoning (reflecting on one's mental processes) and meta-awareness (recognizing thoughts as mental events instead of equating them to reality) have proven effective for overcoming maladaptive thinking styles. Hence, they are potentially an effective method for overcoming self-limiting beliefs in other domains as well. However, the potential of integrating assisted metacognition into mindset interventions has not been explored yet. Here, we propose that guiding and training people on how to leverage metareasoning and meta-awareness for overcoming self-limiting beliefs can significantly enhance the effectiveness of mindset interventions. To test this hypothesis, we develop a gamified mobile application that guides and trains people to use metacognitive strategies based on Cognitive Restructuring (CR) and Acceptance Commitment Therapy (ACT) techniques. The application helps users to identify and overcome self-limiting beliefs by working with aversive emotions when they are triggered by fixed mindsets in real-life situations. Our app aims to help people sustain their motivation to learn when they face inner obstacles (e.g. anxiety, frustration, and demotivation). We expect the application to be an effective tool for helping people better understand and develop the metacognitive skills of emotion regulation and self-regulation that are needed to overcome self-limiting beliefs and develop growth mindsets.

re

A gamified app that helps people overcome self-limiting beliefs by promoting metacognition [BibTex]


no image
Haptify: a Comprehensive Benchmarking System for Grounded Force-Feedback Haptic Devices

Fazlollahi, F., Kuchenbecker, K. J.

Work-in-progress poster presented at EuroHaptics, Leiden, The Netherlands, September 2020 (misc)

hi

[BibTex]

[BibTex]


Characterization of active matter in dense suspensions with heterodyne laser Doppler velocimetry
Characterization of active matter in dense suspensions with heterodyne laser Doppler velocimetry

Sachs, J., Kottapalli, S. N., Fischer, P., Botin, D., Palberg, T.

Colloid and Polymer Science, August 2020 (article)

Abstract
We present a novel approach for characterizing the properties and performance of active matter in dilute suspension as well as in crowded environments. We use Super-Heterodyne Laser-Doppler-Velocimetry (SH-LDV) to study large ensembles of catalytically active Janus particles moving under UV illumination. SH-LDV facilitates a model-free determination of the swimming speed and direction, with excellent ensemble averaging. In addition, we obtain information on the distribution of the catalytic activity. Moreover, SH-LDV operates away from walls and permits a facile correction for multiple scattering contributions. It thus allows for studies of concentrated suspensions of swimmers or of systems where swimmers propel actively in an environment crowded by passive particles. We demonstrate the versatility and the scope of the method with a few selected examples. We anticipate that SH-LDV complements established methods and paves the way for systematic measurements at previously inaccessible boundary conditions.

pf

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Effective Viscous Damping Enables Morphological Computation in Legged Locomotion
Effective Viscous Damping Enables Morphological Computation in Legged Locomotion

Mo, A., Izzi, F., Haeufle, D. F. B., Badri-Spröwitz, A.

Frontiers Robots and Ai, 7:110, August 2020 (article)

Abstract
Muscle models and animal observations suggest that physical damping is beneficial for stabilization. Still, only a few implementations of mechanical damping exist in compliant robotic legged locomotion. It remains unclear how physical damping can be exploited for locomotion tasks, while its advantages as sensor-free, adaptive force- and negative work-producing actuators are promising. In a simplified numerical leg model, we studied the energy dissipation from viscous and Coulomb damping during vertical drops with ground-level perturbations. A parallel spring-damper is engaged between touch-down and mid-stance, and its damper auto-disengages during mid-stance and takeoff. Our simulations indicate that an adjustable and viscous damper is desired. In hardware we explored effective viscous damping and adjustability and quantified the dissipated energy. We tested two mechanical, leg-mounted damping mechanisms; a commercial hydraulic damper, and a custom-made pneumatic damper. The pneumatic damper exploits a rolling diaphragm with an adjustable orifice, minimizing Coulomb damping effects while permitting adjustable resistance. Experimental results show that the leg-mounted, hydraulic damper exhibits the most effective viscous damping. Adjusting the orifice setting did not result in substantial changes of dissipated energy per drop, unlike adjusting damping parameters in the numerical model. Consequently, we also emphasize the importance of characterizing physical dampers during real legged impacts to evaluate their effectiveness for compliant legged locomotion.

dlg

Youtube link (url) DOI [BibTex]

Youtube link (url) DOI [BibTex]


Convolutional Occupancy Networks
Convolutional Occupancy Networks

Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.

In European Conference on Computer Vision (ECCV), Springer International Publishing, Cham, August 2020 (inproceedings)

Abstract
Recently, implicit neural representations have gained popularity for learning-based 3D reconstruction. While demonstrating promising results, most implicit approaches are limited to comparably simple geometry of single objects and do not scale to more complicated or large-scale scenes. The key limiting factor of implicit methods is their simple fully-connected network architecture which does not allow for integrating local information in the observations or incorporating inductive biases such as translational equivariance. In this paper, we propose Convolutional Occupancy Networks, a more flexible implicit representation for detailed reconstruction of objects and 3D scenes. By combining convolutional encoders with implicit occupancy decoders, our model incorporates inductive biases, enabling structured reasoning in 3D space. We investigate the effectiveness of the proposed representation by reconstructing complex geometry from noisy point clouds and low-resolution voxel representations. We empirically find that our method enables the fine-grained implicit 3D reconstruction of single objects, scales to large indoor scenes, and generalizes well from synthetic to real data.

avg

pdf suppmat video Project Page [BibTex]

pdf suppmat video Project Page [BibTex]


no image
Model-Agnostic Counterfactual Explanations for Consequential Decisions

Karimi, A., Barthe, G., Balle, B., Valera, I.

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 108, pages: 895-905, Proceedings of Machine Learning Research, (Editors: Silvia Chiappa and Roberto Calandra), PMLR, August 2020 (conference)

ei plg

arXiv link (url) [BibTex]

arXiv link (url) [BibTex]


no image
More Powerful Selective Kernel Tests for Feature Selection

Lim, J. N., Yamada, M., Jitkrittum, W., Terada, Y., Matsui, S., Shimodaira, H.

Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS), 108, pages: 820-830, Proceedings of Machine Learning Research, (Editors: Silvia Chiappa and Roberto Calandra), PMLR, August 2020 (conference)

ei

arXiv link (url) [BibTex]

arXiv link (url) [BibTex]


no image
Bayesian Online Prediction of Change Points

Agudelo-España, D., Gomez-Gonzalez, S., Bauer, S., Schölkopf, B., Peters, J.

Proceedings of the 36th International Conference on Uncertainty in Artificial Intelligence (UAI), 124, pages: 320-329, Proceedings of Machine Learning Research, (Editors: Jonas Peters and David Sontag), PMLR, August 2020 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]


no image
Semi-supervised learning, causality, and the conditional cluster assumption

von Kügelgen, J., Mey, A., Loog, M., Schölkopf, B.

Proceedings of the 36th International Conference on Uncertainty in Artificial Intelligence (UAI) , 124, pages: 1-10, Proceedings of Machine Learning Research, (Editors: Jonas Peters and David Sontag), PMLR, August 2020 (conference)

ei

link (url) [BibTex]

link (url) [BibTex]