Publications | Max Planck Institute for Intelligent Systems

229 results (View BibTeX file of all listed publications)

2018

Swimming Back and Forth Using Planar Flagellar Propulsion at Low Reynolds Numbers

Khalil, I. S. M., Tabak, A. F., Hamed, Y., Mitwally, M. E., Tawakol, M., Klingner, A., Sitti, M.

Advanced Science, 5(2):1700461, 2018 (article)

Abstract

Abstract Peritrichously flagellated Escherichia coli swim back and forth by wrapping their flagella together in a helical bundle. However, other monotrichous bacteria cannot swim back and forth with a single flagellum and planar wave propagation. Quantifying this observation, a magnetically driven soft two‐tailed microrobot capable of reversing its swimming direction without making a U‐turn trajectory or actively modifying the direction of wave propagation is designed and developed. The microrobot contains magnetic microparticles within the polymer matrix of its head and consists of two collinear, unequal, and opposite ultrathin tails. It is driven and steered using a uniform magnetic field along the direction of motion with a sinusoidally varying orthogonal component. Distinct reversal frequencies that enable selective and independent excitation of the first or the second tail of the microrobot based on their tail length ratio are found. While the first tail provides a propulsive force below one of the reversal frequencies, the second is almost passive, and the net propulsive force achieves flagellated motion along one direction. On the other hand, the second tail achieves flagellated propulsion along the opposite direction above the reversal frequency.

link (url) DOI [BibTex]

2018

pi Khalil, I. S. M., Tabak, A. F., Hamed, Y., Mitwally, M. E., Tawakol, M., Klingner, A., Sitti, M. Swimming Back and Forth Using Planar Flagellar Propulsion at Low Reynolds Numbers Advanced Science, 5(2):1700461, 2018 (article)

link (url) DOI [BibTex]

Non-factorised Variational Inference in Dynamical Systems

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

1st Symposion on Advances in Approximate Bayesian Inference, December 2018 (conference)

PDF link (url) [BibTex]

ei Ialongo, A. D., Van Der Wilk, M., Hensman, J., Rasmussen, C. E. Non-factorised Variational Inference in Dynamical Systems 1st Symposion on Advances in Approximate Bayesian Inference, December 2018 (conference)

PDF link (url) [BibTex]

Enhancing the Accuracy and Fairness of Human Decision Making

Valera, I., Singla, A., Gomez Rodriguez, M.

Advances in Neural Information Processing Systems 31, pages: 1774-1783, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

arXiv link (url) Project Page [BibTex]

ei Valera, I., Singla, A., Gomez Rodriguez, M. Enhancing the Accuracy and Fairness of Human Decision Making Advances in Neural Information Processing Systems 31, pages: 1774-1783, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

arXiv link (url) Project Page [BibTex]

Consolidating the Meta-Learning Zoo: A Unifying Perspective as Posterior Predictive Inference

Gordon*, J., Bronskill*, J., Bauer*, M., Nowozin, S., Turner, R. E.

Workshop on Meta-Learning (MetaLearn 2018) at the 32nd Conference on Neural Information Processing Systems, December 2018, *equal contribution (conference)

link (url) [BibTex]

ei Gordon*, J., Bronskill*, J., Bauer*, M., Nowozin, S., Turner, R. E. Consolidating the Meta-Learning Zoo: A Unifying Perspective as Posterior Predictive Inference Workshop on Meta-Learning (MetaLearn 2018) at the 32nd Conference on Neural Information Processing Systems, December 2018, *equal contribution (conference)

link (url) [BibTex]

Versa: Versatile and Efficient Few-shot Learning

Gordon*, J., Bronskill*, J., Bauer*, M., Nowozin, S., Turner, R. E.

Third Workshop on Bayesian Deep Learning at the 32nd Conference on Neural Information Processing Systems, December 2018, *equal contribution (conference)

link (url) [BibTex]

ei Gordon*, J., Bronskill*, J., Bauer*, M., Nowozin, S., Turner, R. E. Versa: Versatile and Efficient Few-shot Learning Third Workshop on Bayesian Deep Learning at the 32nd Conference on Neural Information Processing Systems, December 2018, *equal contribution (conference)

link (url) [BibTex]

DP-MAC: The Differentially Private Method of Auxiliary Coordinates for Deep Learning

Harder, F., Köhler, J., Welling, M., Park, M.

Workshop on Privacy Preserving Machine Learning at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) Project Page [BibTex]

ei Harder, F., Köhler, J., Welling, M., Park, M. DP-MAC: The Differentially Private Method of Auxiliary Coordinates for Deep Learning Workshop on Privacy Preserving Machine Learning at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) Project Page [BibTex]

Boosting Black Box Variational Inference

Locatello*, F., Dresdner*, G., R., K., Valera, I., Rätsch, G.

Advances in Neural Information Processing Systems 31, pages: 3405-3415, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018, *equal contribution (conference)

arXiv link (url) Project Page [BibTex]

ei Locatello*, F., Dresdner*, G., R., K., Valera, I., Rätsch, G. Boosting Black Box Variational Inference Advances in Neural Information Processing Systems 31, pages: 3405-3415, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018, *equal contribution (conference)

arXiv link (url) Project Page [BibTex]

Deep Nonlinear Non-Gaussian Filtering for Dynamical Systems

Mehrjou, A., Schölkopf, B.

Workshop: Infer to Control: Probabilistic Reinforcement Learning and Structured Control at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

PDF link (url) [BibTex]

ei Mehrjou, A., Schölkopf, B. Deep Nonlinear Non-Gaussian Filtering for Dynamical Systems Workshop: Infer to Control: Probabilistic Reinforcement Learning and Structured Control at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

PDF link (url) [BibTex]

Resampled Priors for Variational Autoencoders

Bauer, M., Mnih, A.

Third Workshop on Bayesian Deep Learning at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) [BibTex]

ei Bauer, M., Mnih, A. Resampled Priors for Variational Autoencoders Third Workshop on Bayesian Deep Learning at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) [BibTex]

Learning Invariances using the Marginal Likelihood

van der Wilk, M., Bauer, M., John, S. T., Hensman, J.

Advances in Neural Information Processing Systems 31, pages: 9960-9970, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) Project Page [BibTex]

ei van der Wilk, M., Bauer, M., John, S. T., Hensman, J. Learning Invariances using the Marginal Likelihood Advances in Neural Information Processing Systems 31, pages: 9960-9970, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) Project Page [BibTex]

Data-Efficient Hierarchical Reinforcement Learning

Nachum, O., Gu, S., Lee, H., Levine, S.

Advances in Neural Information Processing Systems 31, pages: 3307-3317, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) Project Page [BibTex]

ei Nachum, O., Gu, S., Lee, H., Levine, S. Data-Efficient Hierarchical Reinforcement Learning Advances in Neural Information Processing Systems 31, pages: 3307-3317, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) Project Page [BibTex]

Generalisation in humans and deep neural networks

Geirhos, R., Temme, C. R. M., Rauber, J., Schütt, H., Bethge, M., Wichmann, F. A.

Advances in Neural Information Processing Systems 31, pages: 7549-7561, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) [BibTex]

ei Geirhos, R., Temme, C. R. M., Rauber, J., Schütt, H., Bethge, M., Wichmann, F. A. Generalisation in humans and deep neural networks Advances in Neural Information Processing Systems 31, pages: 7549-7561, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) [BibTex]

Parallel and functionally segregated processing of task phase and conscious content in the prefrontal cortex

Kapoor, V., Besserve, M., Logothetis, N. K., Panagiotaropoulos, T. I.

Communications Biology, 1(215):1-12, December 2018 (article)

link (url) DOI Project Page [BibTex]

ei Kapoor, V., Besserve, M., Logothetis, N. K., Panagiotaropoulos, T. I. Parallel and functionally segregated processing of task phase and conscious content in the prefrontal cortex Communications Biology, 1(215):1-12, December 2018 (article)

link (url) DOI Project Page [BibTex]

A Computational Camera with Programmable Optics for Snapshot High Resolution Multispectral Imaging

Chen, J., Hirsch, M., Eberhardt, B., Lensch, H. P. A.

Computer Vision - ACCV 2018 - 14th Asian Conference on Computer Vision, December 2018 (conference) Accepted

[BibTex]

ei Chen, J., Hirsch, M., Eberhardt, B., Lensch, H. P. A. A Computational Camera with Programmable Optics for Snapshot High Resolution Multispectral Imaging Computer Vision - ACCV 2018 - 14th Asian Conference on Computer Vision, December 2018 (conference) Accepted

[BibTex]

Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models

Neitz, A., Parascandolo, G., Bauer, S., Schölkopf, B.

Advances in Neural Information Processing Systems 31, pages: 9838-9848, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

arXiv link (url) [BibTex]

ei Neitz, A., Parascandolo, G., Bauer, S., Schölkopf, B. Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models Advances in Neural Information Processing Systems 31, pages: 9838-9848, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

arXiv link (url) [BibTex]

Assessing Generative Models via Precision and Recall

Sajjadi, M. S. M., Bachem, O., Lucic, M., Bousquet, O., Gelly, S.

Advances in Neural Information Processing Systems 31, pages: 5234-5243, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

arXiv link (url) [BibTex]

ei Sajjadi, M. S. M., Bachem, O., Lucic, M., Bousquet, O., Gelly, S. Assessing Generative Models via Precision and Recall Advances in Neural Information Processing Systems 31, pages: 5234-5243, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

arXiv link (url) [BibTex]

Efficient Encoding of Dynamical Systems through Local Approximations

Solowjow, F., Mehrjou, A., Schölkopf, B., Trimpe, S.

In Proceedings of the 57th IEEE International Conference on Decision and Control (CDC), pages: 6073 - 6079 , Miami, Fl, USA, December 2018 (inproceedings)

ei ics

arXiv PDF DOI Project Page [BibTex]

ei ics Solowjow, F., Mehrjou, A., Schölkopf, B., Trimpe, S. Efficient Encoding of Dynamical Systems through Local Approximations In Proceedings of the 57th IEEE International Conference on Decision and Control (CDC), pages: 6073 - 6079 , Miami, Fl, USA, December 2018 (inproceedings)

arXiv PDF DOI Project Page [BibTex]

Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)

Groh*, F., Wieschollek*, P., Lensch, H. P. A.

Computer Vision - ACCV 2018 - 14th Asian Conference on Computer Vision, December 2018, *equal contribution (conference) Accepted

[BibTex]

ei Groh*, F., Wieschollek*, P., Lensch, H. P. A. Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds) Computer Vision - ACCV 2018 - 14th Asian Conference on Computer Vision, December 2018, *equal contribution (conference) Accepted

[BibTex]

Bayesian Nonparametric Hawkes Processes

Kapoor, J., Vergari, A., Gomez Rodriguez, M., Valera, I.

Bayesian Nonparametrics workshop at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

PDF link (url) [BibTex]

ei Kapoor, J., Vergari, A., Gomez Rodriguez, M., Valera, I. Bayesian Nonparametric Hawkes Processes Bayesian Nonparametrics workshop at the 32nd Conference on Neural Information Processing Systems, December 2018 (conference)

PDF link (url) [BibTex]

Customized Multi-Person Tracker

Ma, L., Tang, S., Black, M. J., Gool, L. V.

In Computer Vision – ACCV 2018, Springer International Publishing, Asian Conference on Computer Vision, December 2018 (inproceedings)

PDF Project Page [BibTex]

ps Ma, L., Tang, S., Black, M. J., Gool, L. V. Customized Multi-Person Tracker In Computer Vision – ACCV 2018, Springer International Publishing, Asian Conference on Computer Vision, December 2018 (inproceedings)

PDF Project Page [BibTex]

Informative Features for Model Comparison

Jitkrittum, W., Kanagawa, H., Sangkloy, P., Hays, J., Schölkopf, B., Gretton, A.

Advances in Neural Information Processing Systems 31, pages: 816-827, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) Project Page [BibTex]

ei Jitkrittum, W., Kanagawa, H., Sangkloy, P., Hays, J., Schölkopf, B., Gretton, A. Informative Features for Model Comparison Advances in Neural Information Processing Systems 31, pages: 816-827, (Editors: S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett), Curran Associates, Inc., 32nd Annual Conference on Neural Information Processing Systems, December 2018 (conference)

link (url) Project Page [BibTex]

Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time

Huang, Y., Kaufmann, M., Aksan, E., Black, M. J., Hilliges, O., Pons-Moll, G.

ACM Transactions on Graphics, (Proc. SIGGRAPH Asia), 37, pages: 185:1-185:15, ACM, November 2018, Two first authors contributed equally (article)

Abstract

We demonstrate a novel deep neural network capable of reconstructing human full body pose in real-time from 6 Inertial Measurement Units (IMUs) worn on the user's body. In doing so, we address several difficult challenges. First, the problem is severely under-constrained as multiple pose parameters produce the same IMU orientations. Second, capturing IMU data in conjunction with ground-truth poses is expensive and difficult to do in many target application scenarios (e.g., outdoors). Third, modeling temporal dependencies through non-linear optimization has proven effective in prior work but makes real-time prediction infeasible. To address this important limitation, we learn the temporal pose priors using deep learning. To learn from sufficient data, we synthesize IMU data from motion capture datasets. A bi-directional RNN architecture leverages past and future information that is available at training time. At test time, we deploy the network in a sliding window fashion, retaining real time capabilities. To evaluate our method, we recorded DIP-IMU, a dataset consisting of 10 subjects wearing 17 IMUs for validation in 64 sequences with 330,000 time instants; this constitutes the largest IMU dataset publicly available. We quantitatively evaluate our approach on multiple datasets and show results from a real-time implementation. DIP-IMU and the code are available for research purposes.

data code pdf preprint video DOI Project Page [BibTex]

ps Huang, Y., Kaufmann, M., Aksan, E., Black, M. J., Hilliges, O., Pons-Moll, G. Deep Inertial Poser: Learning to Reconstruct Human Pose from Sparse Inertial Measurements in Real Time ACM Transactions on Graphics, (Proc. SIGGRAPH Asia), 37, pages: 185:1-185:15, ACM, November 2018, Two first authors contributed equally (article)

data code pdf preprint video DOI Project Page [BibTex]

Universal Custom Complex Magnetic Spring Design Methodology

Woodward, M. A., Sitti, M.

IEEE Transactions on Magnetics, 54(1):1-13, October 2018 (article)

Abstract

A design methodology is presented for creating custom complex magnetic springs through the design of force-displacement curves. This methodology results in a magnet configuration, which will produce a desired force-displacement relationship. Initially, the problem is formulated and solved as a system of linear equations. Then, given the limited likelihood of a single solution being feasibly manufactured, key parameters of the solution are extracted and varied to create a family of solutions. Finally, these solutions are refined using numerical optimization. Given the properties of magnets, this methodology can create any well-defined function of force versus displacement and is model-independent. To demonstrate this flexibility, a number of example magnetic springs are designed; one of which, designed for use in a jumping-gliding robot's shape memory alloy actuated clutch, is manufactured and experimentally characterized. Due to the scaling of magnetic forces, the displacement region which these magnetic springs are most applicable is that of millimeters and below. However, this region is well situated for miniature robots and smart material actuators, where a tailored magnetic spring, designed to compliment a component, can enhance its performance while adding new functionality. The methodology is also expendable to variable interactions and multi-dimensional magnetic field design.

DOI [BibTex]

pi Woodward, M. A., Sitti, M. Universal Custom Complex Magnetic Spring Design Methodology IEEE Transactions on Magnetics, 54(1):1-13, October 2018 (article)

DOI [BibTex]

On the Integration of Optical Flow and Action Recognition

Sevilla-Lara, L., Liao, Y., Güney, F., Jampani, V., Geiger, A., Black, M. J.

In German Conference on Pattern Recognition (GCPR), LNCS 11269, pages: 281-297, Springer, Cham, October 2018 (inproceedings)

Abstract

Most of the top performing action recognition methods use optical flow as a "black box" input. Here we take a deeper look at the combination of flow and action recognition, and investigate why optical flow is helpful, what makes a flow method good for action recognition, and how we can make it better. In particular, we investigate the impact of different flow algorithms and input transformations to better understand how these affect a state-of-the-art action recognition method. Furthermore, we fine tune two neural-network flow methods end-to-end on the most widely used action recognition dataset (UCF101). Based on these experiments, we make the following five observations: 1) optical flow is useful for action recognition because it is invariant to appearance, 2) optical flow methods are optimized to minimize end-point-error (EPE), but the EPE of current methods is not well correlated with action recognition performance, 3) for the flow methods tested, accuracy at boundaries and at small displacements is most correlated with action recognition performance, 4) training optical flow to minimize classification error instead of minimizing EPE improves recognition performance, and 5) optical flow learned for the task of action recognition differs from traditional optical flow especially inside the human body and at the boundary of the body. These observations may encourage optical flow researchers to look beyond EPE as a goal and guide action recognition researchers to seek better motion cues, leading to a tighter integration of the optical flow and action recognition communities.

avg ps

arXiv DOI [BibTex]

avg ps Sevilla-Lara, L., Liao, Y., Güney, F., Jampani, V., Geiger, A., Black, M. J. On the Integration of Optical Flow and Action Recognition In German Conference on Pattern Recognition (GCPR), LNCS 11269, pages: 281-297, Springer, Cham, October 2018 (inproceedings)

arXiv DOI [BibTex]

Regularizing Reinforcement Learning with State Abstraction

Akrour, R., Veiga, F., Peters, J., Neuman, G.

Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2018 (conference) Accepted

link (url) Project Page [BibTex]

ei Akrour, R., Veiga, F., Peters, J., Neuman, G. Regularizing Reinforcement Learning with State Abstraction Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), October 2018 (conference) Accepted

link (url) Project Page [BibTex]

A Value-Driven Eldercare Robot: Virtual and Physical Instantiations of a Case-Supported Principle-Based Behavior Paradigm

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

Proceedings of the IEEE, pages: 1,15, October 2018 (article)

Abstract

In this paper, a case-supported principle-based behavior paradigm is proposed to help ensure ethical behavior of autonomous machines. We argue that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. Such a consensus is likely to emerge in many areas in which autonomous systems are apt to be deployed and for the actions they are liable to undertake. We believe that this is the case since we are more likely to agree on how machines ought to treat us than on how human beings ought to treat one another. Given such a consensus, particular cases of ethical dilemmas where ethicists agree on the ethically relevant features and the right course of action can be used to help discover principles that balance these features when they are in conflict. Such principles not only help ensure ethical behavior of complex and dynamic systems but also can serve as a basis for justification of this behavior. The requirements, methods, implementation, and evaluation components of the paradigm are detailed as well as its instantiation in both a simulated and real robot functioning in the domain of eldercare.

link (url) DOI [BibTex]

am Anderson, M., Anderson, S., Berenz, V. A Value-Driven Eldercare Robot: Virtual and Physical Instantiations of a Case-Supported Principle-Based Behavior Paradigm Proceedings of the IEEE, pages: 1,15, October 2018 (article)

link (url) DOI [BibTex]

Deep Neural Network-based Cooperative Visual Tracking through Multiple Micro Aerial Vehicles

Price, E., Lawless, G., Ludwig, R., Martinovic, I., Buelthoff, H. H., Black, M. J., Ahmad, A.

IEEE Robotics and Automation Letters, Robotics and Automation Letters, 3(4):3193-3200, IEEE, October 2018, Also accepted and presented in the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). (article)

Abstract

Multi-camera tracking of humans and animals in outdoor environments is a relevant and challenging problem. Our approach to it involves a team of cooperating micro aerial vehicles (MAVs) with on-board cameras only. DNNs often fail at objects with small scale or far away from the camera, which are typical characteristics of a scenario with aerial robots. Thus, the core problem addressed in this paper is how to achieve on-board, online, continuous and accurate vision-based detections using DNNs for visual person tracking through MAVs. Our solution leverages cooperation among multiple MAVs and active selection of most informative regions of image. We demonstrate the efficiency of our approach through simulations with up to 16 robots and real robot experiments involving two aerial robots tracking a person, while maintaining an active perception-driven formation. ROS-based source code is provided for the benefit of the community.

Published Version link (url) DOI [BibTex]

ps Price, E., Lawless, G., Ludwig, R., Martinovic, I., Buelthoff, H. H., Black, M. J., Ahmad, A. Deep Neural Network-based Cooperative Visual Tracking through Multiple Micro Aerial Vehicles IEEE Robotics and Automation Letters, Robotics and Automation Letters, 3(4):3193-3200, IEEE, October 2018, Also accepted and presented in the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). (article)

Published Version link (url) DOI [BibTex]

Learning to Categorize Bug Reports with LSTM Networks

Gondaliya, K., Peters, J., Rueckert, E.

Proceedings of the 10th International Conference on Advances in System Testing and Validation Lifecycle (VALID), pages: 7-12, October 2018 (conference)

link (url) [BibTex]

ei Gondaliya, K., Peters, J., Rueckert, E. Learning to Categorize Bug Reports with LSTM Networks Proceedings of the 10th International Conference on Advances in System Testing and Validation Lifecycle (VALID), pages: 7-12, October 2018 (conference)

link (url) [BibTex]

Domain Randomization for Simulation-Based Policy Optimization with Transferability Assessment

Muratore, F., Treede, F., Gienger, M., Peters, J.

2nd Annual Conference on Robot Learning (CoRL), 87, pages: 700-713, Proceedings of Machine Learning Research, PMLR, October 2018 (conference)

link (url) Project Page [BibTex]

ei Muratore, F., Treede, F., Gienger, M., Peters, J. Domain Randomization for Simulation-Based Policy Optimization with Transferability Assessment 2nd Annual Conference on Robot Learning (CoRL), 87, pages: 700-713, Proceedings of Machine Learning Research, PMLR, October 2018 (conference)

link (url) Project Page [BibTex]

Reinforcement Learning of Phase Oscillators for Fast Adaptation to Moving Targets

Maeda, G., Koc, O., Morimoto, J.

Proceedings of The 2nd Conference on Robot Learning (CoRL), 87, pages: 630-640, (Editors: Aude Billard, Anca Dragan, Jan Peters, Jun Morimoto ), PMLR, October 2018 (conference)

link (url) Project Page [BibTex]

ei Maeda, G., Koc, O., Morimoto, J. Reinforcement Learning of Phase Oscillators for Fast Adaptation to Moving Targets Proceedings of The 2nd Conference on Robot Learning (CoRL), 87, pages: 630-640, (Editors: Aude Billard, Anca Dragan, Jan Peters, Jun Morimoto ), PMLR, October 2018 (conference)

link (url) Project Page [BibTex]

Control of Musculoskeletal Systems using Learned Dynamics Models

Büchler, D., Calandra, R., Schölkopf, B., Peters, J.

IEEE Robotics and Automation Letters, Robotics and Automation Letters, 3(4):3161-3168, IEEE, 2018 (article)

Abstract

Controlling musculoskeletal systems, especially robots actuated by pneumatic artificial muscles, is a challenging task due to nonlinearities, hysteresis effects, massive actuator de- lay and unobservable dependencies such as temperature. Despite such difficulties, muscular systems offer many beneficial prop- erties to achieve human-comparable performance in uncertain and fast-changing tasks. For example, muscles are backdrivable and provide variable stiffness while offering high forces to reach high accelerations. In addition, the embodied intelligence deriving from the compliance might reduce the control demands for specific tasks. In this paper, we address the problem of how to accurately control musculoskeletal robots. To address this issue, we propose to learn probabilistic forward dynamics models using Gaussian processes and, subsequently, to employ these models for control. However, Gaussian processes dynamics models cannot be set-up for our musculoskeletal robot as for traditional motor- driven robots because of unclear state composition etc. We hence empirically study and discuss in detail how to tune these approaches to complex musculoskeletal robots and their specific challenges. Moreover, we show that our model can be used to accurately control an antagonistic pair of pneumatic artificial muscles for a trajectory tracking task while considering only one- step-ahead predictions of the forward model and incorporating model uncertainty.

RAL18final link (url) DOI Project Page [BibTex]

ei Büchler, D., Calandra, R., Schölkopf, B., Peters, J. Control of Musculoskeletal Systems using Learned Dynamics Models IEEE Robotics and Automation Letters, Robotics and Automation Letters, 3(4):3161-3168, IEEE, 2018 (article)

RAL18final link (url) DOI Project Page [BibTex]

Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation

Wulff, J., Black, M. J.

In German Conference on Pattern Recognition (GCPR), LNCS 11269, pages: 567-582, Springer, Cham, October 2018 (inproceedings)

Abstract

The difficulty of annotating training data is a major obstacle to using CNNs for low-level tasks in video. Synthetic data often does not generalize to real videos, while unsupervised methods require heuristic n losses. Proxy tasks can overcome these issues, and start by training a network for a task for which annotation is easier or which can be trained unsupervised. The trained network is then fine-tuned for the original task using small amounts of ground truth data. Here, we investigate frame interpolation as a proxy task for optical flow. Using real movies, we train a CNN unsupervised for temporal interpolation. Such a network implicitly estimates motion, but cannot handle untextured regions. By fine-tuning on small amounts of ground truth flow, the network can learn to fill in homogeneous regions and compute full optical flow fields. Using this unsupervised pre-training, our network outperforms similar architectures that were trained supervised using synthetic optical flow.

pdf arXiv DOI Project Page [BibTex]

ps Wulff, J., Black, M. J. Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation In German Conference on Pattern Recognition (GCPR), LNCS 11269, pages: 567-582, Springer, Cham, October 2018 (inproceedings)

pdf arXiv DOI Project Page [BibTex]

Constraint-Space Projection Direct Policy Search

Akrour, R., Peters, J., Neuman, G.

14th European Workshop on Reinforcement Learning (EWRL), October 2018 (conference)

link (url) Project Page [BibTex]

ei Akrour, R., Peters, J., Neuman, G. Constraint-Space Projection Direct Policy Search 14th European Workshop on Reinforcement Learning (EWRL), October 2018 (conference)

link (url) Project Page [BibTex]

Mobile Microrobots for Active Therapeutic Delivery

Pelin Erkoc, , I Ceren Yasa, , Hakan Ceylan, , Oncay Yasa, , Yunus Alapan, , Sitti, M.

Advanced Therapeutics, pages: 1800064, October 2018 (article)

DOI [BibTex]

pi Pelin Erkoc, , I Ceren Yasa, , Hakan Ceylan, , Oncay Yasa, , Yunus Alapan, , Sitti, M. Mobile Microrobots for Active Therapeutic Delivery Advanced Therapeutics, pages: 1800064, October 2018 (article)

DOI [BibTex]

First Impressions of Personality Traits From Body Shapes

Hu, Y., Parde, C. J., Hill, M. Q., Mahmood, N., O’Toole, A. J.

Psychological Science, 29(12):1969-–1983, October 2018 (article)

Abstract

People infer the personalities of others from their facial appearance. Whether they do so from body shapes is less studied. We explored personality inferences made from body shapes. Participants rated personality traits for male and female bodies generated with a three-dimensional body model. Multivariate spaces created from these ratings indicated that people evaluate bodies on valence and agency in ways that directly contrast positive and negative traits from the Big Five domains. Body-trait stereotypes based on the trait ratings revealed a myriad of diverse body shapes that typify individual traits. Personality-trait profiles were predicted reliably from a subset of the body-shape features used to specify the three-dimensional bodies. Body features related to extraversion and conscientiousness were predicted with the highest consensus, followed by openness traits. This study provides the first comprehensive look at the range, diversity, and reliability of personality inferences that people make from body shapes.

publisher site pdf DOI [BibTex]

ps Hu, Y., Parde, C. J., Hill, M. Q., Mahmood, N., O’Toole, A. J. First Impressions of Personality Traits From Body Shapes Psychological Science, 29(12):1969-–1983, October 2018 (article)

publisher site pdf DOI [BibTex]

Human Motion Parsing by Hierarchical Dynamic Clustering

Zhang, Y., Tang, S., Sun, H., Neumann, H.

In Proceedings of the British Machine Vision Conference (BMVC), pages: 269, BMVA Press, 29th British Machine Vision Conference, September 2018 (inproceedings)

Abstract

Parsing continuous human motion into meaningful segments plays an essential role in various applications. In this work, we propose a hierarchical dynamic clustering framework to derive action clusters from a sequence of local features in an unsuper- vised bottom-up manner. We systematically investigate the modules in this framework and particularly propose diverse temporal pooling schemes, in order to realize accurate temporal action localization. We demonstrate our method on two motion parsing tasks: temporal action segmentation and abnormal behavior detection. The experimental results indicate that the proposed framework is significantly more effective than the other related state-of-the-art methods on several datasets.

pdf Project Page [BibTex]

ps Zhang, Y., Tang, S., Sun, H., Neumann, H. Human Motion Parsing by Hierarchical Dynamic Clustering In Proceedings of the British Machine Vision Conference (BMVC), pages: 269, BMVA Press, 29th British Machine Vision Conference, September 2018 (inproceedings)

pdf Project Page [BibTex]

Spatio-temporal Transformer Network for Video Restoration

Kim, T. H., Sajjadi, M. S. M., Hirsch, M., Schölkopf, B.

15th European Conference on Computer Vision (ECCV), Part III, 11207, pages: 111-127, Lecture Notes in Computer Science, (Editors: Vittorio Ferrari, Martial Hebert,Cristian Sminchisescu and Yair Weiss), Springer, September 2018 (conference)

DOI [BibTex]

ei Kim, T. H., Sajjadi, M. S. M., Hirsch, M., Schölkopf, B. Spatio-temporal Transformer Network for Video Restoration 15th European Conference on Computer Vision (ECCV), Part III, 11207, pages: 111-127, Lecture Notes in Computer Science, (Editors: Vittorio Ferrari, Martial Hebert,Cristian Sminchisescu and Yair Weiss), Springer, September 2018 (conference)

DOI [BibTex]

Separating Reflection and Transmission Images in the Wild

Wieschollek, P., Gallo, O., Gu, J., Kautz, J.

European Conference on Computer Vision (ECCV), September 2018 (conference)

link (url) [BibTex]

ei Wieschollek, P., Gallo, O., Gu, J., Kautz, J. Separating Reflection and Transmission Images in the Wild European Conference on Computer Vision (ECCV), September 2018 (conference)

link (url) [BibTex]

Generating 3D Faces using Convolutional Mesh Autoencoders

Ranjan, A., Bolkart, T., Sanyal, S., Black, M. J.

In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, vol 11207, pages: 725-741, Springer, Cham, September 2018 (inproceedings)

Abstract

Learned 3D representations of human faces are useful for computer vision problems such as 3D face tracking and reconstruction from images, as well as graphics applications such as character generation and animation. Traditional models learn a latent representation of a face using linear subspaces or higher-order tensor generalizations. Due to this linearity, they can not capture extreme deformations and non-linear expressions. To address this, we introduce a versatile model that learns a non-linear representation of a face using spectral convolutions on a mesh surface. We introduce mesh sampling operations that enable a hierarchical mesh representation that captures non-linear variations in shape and expression at multiple scales within the model. In a variational setting, our model samples diverse realistic 3D faces from a multivariate Gaussian distribution. Our training data consists of 20,466 meshes of extreme expressions captured over 12 different subjects. Despite limited training data, our trained model outperforms state-of-the-art face models with 50% lower reconstruction error, while using 75% fewer parameters. We also show that, replacing the expression space of an existing state-of-the-art face model with our autoencoder, achieves a lower reconstruction error. Our data, model and code are available at http://coma.is.tue.mpg.de/.

Code (tensorflow) Code (pytorch) Project Page paper supplementary DOI Project Page Project Page [BibTex]

ps Ranjan, A., Bolkart, T., Sanyal, S., Black, M. J. Generating 3D Faces using Convolutional Mesh Autoencoders In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, vol 11207, pages: 725-741, Springer, Cham, September 2018 (inproceedings)

Code (tensorflow) Code (pytorch) Project Page paper supplementary DOI Project Page Project Page [BibTex]

Part-Aligned Bilinear Representations for Person Re-identification

Suh, Y., Wang, J., Tang, S., Mei, T., Lee, K. M.

In European Conference on Computer Vision (ECCV), 11218, pages: 418-437, Springer, Cham, September 2018 (inproceedings)

Abstract

Comparing the appearance of corresponding body parts is essential for person re-identification. However, body parts are frequently misaligned be- tween detected boxes, due to the detection errors and the pose/viewpoint changes. In this paper, we propose a network that learns a part-aligned representation for person re-identification. Our model consists of a two-stream network, which gen- erates appearance and body part feature maps respectively, and a bilinear-pooling layer that fuses two feature maps to an image descriptor. We show that it results in a compact descriptor, where the inner product between two image descriptors is equivalent to an aggregation of the local appearance similarities of the cor- responding body parts, and thereby significantly reduces the part misalignment problem. Our approach is advantageous over other pose-guided representations by learning part descriptors optimal for person re-identification. Training the net- work does not require any part annotation on the person re-identification dataset. Instead, we simply initialize the part sub-stream using a pre-trained sub-network of an existing pose estimation network and train the whole network to minimize the re-identification loss. We validate the effectiveness of our approach by demon- strating its superiority over the state-of-the-art methods on the standard bench- mark datasets including Market-1501, CUHK03, CUHK01 and DukeMTMC, and standard video dataset MARS.

pdf supplementary DOI Project Page [BibTex]

ps Suh, Y., Wang, J., Tang, S., Mei, T., Lee, K. M. Part-Aligned Bilinear Representations for Person Re-identification In European Conference on Computer Vision (ECCV), 11218, pages: 418-437, Springer, Cham, September 2018 (inproceedings)

pdf supplementary DOI Project Page [BibTex]

Microalga‐Powered Microswimmers toward Active Cargo Delivery

Yasa, O., Erkoc, P., Alapan, Y., Sitti, M.

Advanced Materials, pages: 1804130, September 2018 (article)

Microalga‐Powered Microswimmers toward Active Cargo Delivery DOI Project Page [BibTex]

pi Yasa, O., Erkoc, P., Alapan, Y., Sitti, M. Microalga‐Powered Microswimmers toward Active Cargo Delivery Advanced Materials, pages: 1804130, September 2018 (article)

Microalga‐Powered Microswimmers toward Active Cargo Delivery DOI Project Page [BibTex]

Risk-Sensitivity in Simulation Based Online Planning

Schmid, K., Belzner, L., Kiermeier, M., Neitz, A., Phan, T., Gabor, T., Linnhoff, C.

KI 2018: Advances in Artificial Intelligence - 41st German Conference on AI, pages: 229-240, (Editors: F. Trollmann and A. Y. Turhan), Springer, Cham, September 2018 (conference)

DOI [BibTex]

ei Schmid, K., Belzner, L., Kiermeier, M., Neitz, A., Phan, T., Gabor, T., Linnhoff, C. Risk-Sensitivity in Simulation Based Online Planning KI 2018: Advances in Artificial Intelligence - 41st German Conference on AI, pages: 229-240, (Editors: F. Trollmann and A. Y. Turhan), Springer, Cham, September 2018 (conference)

DOI [BibTex]

Playful: Reactive Programming for Orchestrating Robotic Behavior

Berenz, V., Schaal, S.

IEEE Robotics Automation Magazine, 25(3):49-60, September 2018 (article) In press

Abstract

For many service robots, reactivity to changes in their surroundings is a must. However, developing software suitable for dynamic environments is difficult. Existing robotic middleware allows engineers to design behavior graphs by organizing communication between components. But because these graphs are structurally inflexible, they hardly support the development of complex reactive behavior. To address this limitation, we propose Playful, a software platform that applies reactive programming to the specification of robotic behavior.

playful website playful_IEEE_RAM link (url) DOI [BibTex]

am Berenz, V., Schaal, S. Playful: Reactive Programming for Orchestrating Robotic Behavior IEEE Robotics Automation Magazine, 25(3):49-60, September 2018 (article) In press

playful website playful_IEEE_RAM link (url) DOI [BibTex]

Learning Human Optical Flow

Ranjan, A., Romero, J., Black, M. J.

In 29th British Machine Vision Conference, September 2018 (inproceedings)

Abstract

The optical flow of humans is well known to be useful for the analysis of human action. Given this, we devise an optical flow algorithm specifically for human motion and show that it is superior to generic flow methods. Designing a method by hand is impractical, so we develop a new training database of image sequences with ground truth optical flow. For this we use a 3D model of the human body and motion capture data to synthesize realistic flow fields. We then train a convolutional neural network to estimate human flow fields from pairs of images. Since many applications in human motion analysis depend on speed, and we anticipate mobile applications, we base our method on SpyNet with several modifications. We demonstrate that our trained network is more accurate than a wide range of top methods on held-out test data and that it generalizes well to real image sequences. When combined with a person detector/tracker, the approach provides a full solution to the problem of 2D human flow estimation. Both the code and the dataset are available for research.

video code pdf link (url) Project Page Project Page [BibTex]

ps Ranjan, A., Romero, J., Black, M. J. Learning Human Optical Flow In 29th British Machine Vision Conference, September 2018 (inproceedings)

video code pdf link (url) Project Page Project Page [BibTex]

The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution

Gondal, M. W., Schölkopf, B., Hirsch, M.

Workshop and Challenge on Perceptual Image Restoration and Manipulation (PIRM) at the 15th European Conference on Computer Vision (ECCV), September 2018 (conference)

arXiv URL [BibTex]

ei Gondal, M. W., Schölkopf, B., Hirsch, M. The Unreasonable Effectiveness of Texture Transfer for Single Image Super-resolution Workshop and Challenge on Perceptual Image Restoration and Manipulation (PIRM) at the 15th European Conference on Computer Vision (ECCV), September 2018 (conference)

arXiv URL [BibTex]

Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation

(Best Student Paper Award)

Omran, M., Lassner, C., Pons-Moll, G., Gehler, P. V., Schiele, B.

In 3DV, September 2018 (inproceedings)

Abstract

Direct prediction of 3D body pose and shape remains a challenge even for highly parameterized deep learning models. Mapping from the 2D image space to the prediction space is difficult: perspective ambiguities make the loss function noisy and training data is scarce. In this paper, we propose a novel approach (Neural Body Fitting (NBF)). It integrates a statistical body model within a CNN, leveraging reliable bottom-up semantic body part segmentation and robust top-down body model constraints. NBF is fully differentiable and can be trained using 2D and 3D annotations. In detailed experiments, we analyze how the components of our model affect performance, especially the use of part segmentations as an explicit intermediate representation, and present a robust, efficiently trainable framework for 3D human pose estimation from 2D images with competitive results on standard benchmarks. Code is available at https://github.com/mohomran/neural_body_fitting

arXiv code Project Page [BibTex]

ps Omran, M., Lassner, C., Pons-Moll, G., Gehler, P. V., Schiele, B. Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation In 3DV, September 2018 (inproceedings)

arXiv code Project Page [BibTex]

ClusterNet: Instance Segmentation in RGB-D Images

Shao, L., Tian, Y., Bohg, J.

arXiv, September 2018, Submitted to ICRA'19 (article) Submitted

Abstract

We propose a method for instance-level segmentation that uses RGB-D data as input and provides detailed information about the location, geometry and number of {\em individual\/} objects in the scene. This level of understanding is fundamental for autonomous robots. It enables safe and robust decision-making under the large uncertainty of the real-world. In our model, we propose to use the first and second order moments of the object occupancy function to represent an object instance. We train an hourglass Deep Neural Network (DNN) where each pixel in the output votes for the 3D position of the corresponding object center and for the object's size and pose. The final instance segmentation is achieved through clustering in the space of moments. The object-centric training loss is defined on the output of the clustering. Our method outperforms the state-of-the-art instance segmentation method on our synthesized dataset. We show that our method generalizes well on real-world data achieving visually better segmentation results.

link (url) [BibTex]

am Shao, L., Tian, Y., Bohg, J. ClusterNet: Instance Segmentation in RGB-D Images arXiv, September 2018, Submitted to ICRA'19 (article) Submitted

link (url) [BibTex]

Unsupervised Learning of Multi-Frame Optical Flow with Occlusions

Janai, J., Güney, F., Ranjan, A., Black, M. J., Geiger, A.

In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, vol 11220, pages: 713-731, Springer, Cham, September 2018 (inproceedings)

avg ps

pdf suppmat Video Project Page DOI Project Page [BibTex]

avg ps Janai, J., Güney, F., Ranjan, A., Black, M. J., Geiger, A. Unsupervised Learning of Multi-Frame Optical Flow with Occlusions In European Conference on Computer Vision (ECCV), Lecture Notes in Computer Science, vol 11220, pages: 713-731, Springer, Cham, September 2018 (inproceedings)

pdf suppmat Video Project Page DOI Project Page [BibTex]

Leveraging Contact Forces for Learning to Grasp

Merzic, H., Bogdanovic, M., Kappler, D., Righetti, L., Bohg, J.

arXiv, September 2018, Submitted to ICRA'19 (article) Submitted

Abstract

Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two- fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.

am mg

video arXiv [BibTex]