Institute Homepage
Institute Homepage EN Sign In

Publications

DEPARTMENTS

Emperical Interference

Haptic Intelligence

Modern Magnetic Systems

Perceiving Systems

Physical Intelligence

Robotic Materials

Social Foundations of Computation

Research Groups

Autonomous Vision

Autonomous Learning

Bioinspired Autonomous Miniature Robots

Dynamic Locomotion

Embodied Vision

Human Aspects of Machine Learning

Intelligent Control Systems

Learning and Dynamical Systems

Locomotion in Biorobotic and Somatic Systems

Micro, Nano, and Molecular Systems

Movement Generation and Control

Neural Capture and Synthesis

Physics for Inference and Optimization

Organizational Leadership and Diversity

Probabilistic Learning Group

Topics

Robot Learning

Conference Paper

2022

Autonomous Learning

Robotics

AI

Career

Award

Micro, Nano, and Molecular Systems Article Role of symmetry in driven propulsion at low Reynolds number Sachs, J., Morozov, K. I., Kenneth, O., Qiu, T., Segreto, N., Fischer, P., Leshansky, A. M. Phys. Rev. E, 98(6):063105, American Physical Society, December 2018 (Published)
We theoretically and experimentally investigate low-Reynolds-number propulsion of geometrically achiral planar objects that possess a dipole moment and that are driven by a rotating magnetic field. Symmetry considerations (involving parity, $\widehat{P}$, and charge conjugation, $\widehat{C}$) establish correspondence between propulsive states depending on orientation of the dipolar moment. Although basic symmetry arguments do not forbid individual symmetric objects to efficiently propel due to spontaneous symmetry breaking, they suggest that the average ensemble velocity vanishes. Some additional arguments show, however, that highly symmetrical ($\widehat{P}$-even) objects exhibit no net propulsion while individual less symmetrical ($\widehat{C}\widehat{P}$-even) propellers do propel. Particular magnetization orientation, rendering the shape $\widehat{C}\widehat{P}$-odd, yields unidirectional motion typically associated with chiral structures, such as helices. If instead of a structure with a permanent dipole we consider a polarizable object, some of the arguments have to be modified. For instance, we demonstrate a truly achiral ($\widehat{P}$- and $\widehat{C}\widehat{P}$-even) planar shape with an induced electric dipole that can propel by electro-rotation. We thereby show that chirality is not essential for propulsion due to rotation-translation coupling at low Reynolds number.
DOI URL BibTeX
Physical Intelligence Article 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, December 2018
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.
DOI URL BibTeX
Empirical Inference Conference Paper 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, Part III, 11363:685-699, Lecture Notes in Computer Science, Springer, December 2018 (Published) DOI BibTeX
Empirical Inference Conference Paper Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models Neitz, A., Parascandolo, G., Bauer, S., Schölkopf, B. Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 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 (Published) arXiv URL BibTeX
Empirical Inference Conference Paper 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 (NeurIPS 2018), 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 (Published) arXiv URL BibTeX
Empirical Inference Probabilistic Learning Group Conference Paper 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 (Published) PDF URL BibTeX
Empirical Inference Probabilistic Learning Group Conference Paper Boosting Black Box Variational Inference Locatello*, F., Dresdner*, G., R., K., Valera, I., Rätsch, G. Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 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 (Published) arXiv URL BibTeX
Empirical Inference Conference Paper 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 (Published) URL BibTeX
Perceiving Systems Conference Paper Customized Multi-Person Tracker Ma, L., Tang, S., Black, M. J., Van Gool, L. In Computer Vision – ACCV 2018, Springer International Publishing, Asian Conference on Computer Vision, December 2018 PDF BibTeX
Empirical Inference Conference Paper 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 (Published) URL BibTeX
Empirical Inference Conference Paper Data-Efficient Hierarchical Reinforcement Learning Nachum, O., Gu, S., Lee, H., Levine, S. Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 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 (Published) URL BibTeX
Empirical Inference Conference Paper 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 (Published) PDF URL BibTeX
Intelligent Control Systems Autonomous Learning Conference Paper Deep Reinforcement Learning for Event-Triggered Control Baumann, D., Zhu, J., Martius, G., Trimpe, S. In Proceedings of the 57th IEEE International Conference on Decision and Control (CDC), 943-950, 57th IEEE International Conference on Decision and Control (CDC), December 2018 (Published) arXiv PDF DOI BibTeX
Intelligent Control Systems Empirical Inference Conference Paper 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), 6073 - 6079 , Miami, Fl, USA, December 2018 (Published) arXiv PDF DOI BibTeX
Empirical Inference Probabilistic Learning Group Conference Paper Enhancing the Accuracy and Fairness of Human Decision Making Valera, I., Singla, A., Gomez Rodriguez, M. Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 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 (Published) arXiv URL BibTeX
Empirical Inference Conference Paper 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 (NeurIPS 2018), 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 (Published) URL BibTeX
Empirical Inference Conference Paper Generalization in anti-causal learning Kilbertus*, N., Parascandolo*, G., Schölkopf*, B. NeurIPS 2018 Workshop on Critiquing and Correcting Trends in Machine Learning, December 2018, *authors are listed in alphabetical order arXiv URL BibTeX
Empirical Inference Conference Paper Informative Features for Model Comparison Jitkrittum, W., Kanagawa, H., Sangkloy, P., Hays, J., Schölkopf, B., Gretton, A. Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 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 (Published) URL BibTeX
Empirical Inference Conference Paper Learning Invariances using the Marginal Likelihood van der Wilk, M., Bauer, M., John, S. T., Hensman, J. Advances in Neural Information Processing Systems 31 (NeurIPS 2018), 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 (Published) URL BibTeX
Empirical Inference Conference Paper 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 (Published) PDF URL BibTeX
Empirical Inference Article 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 (Published) DOI URL BibTeX
Empirical Inference Conference Paper 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 (Published) URL BibTeX
Empirical Inference Conference Paper 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 (Published) URL BibTeX
Statistical Learning Theory Conference Paper When do random forests fail? Tang, C., Garreau, D., von Luxburg, U. In Proceedings Neural Information Processing Systems, Neural Information Processing Systems (NIPS 2018) , December 2018 BibTeX
Micro, Nano, and Molecular Systems Article Optical and Thermophoretic Control of Janus Nanopen Injection into Living Cells Maier, C. M., Huergo, M. A., Milosevic, S., Pernpeintner, C., Li, M., Singh, D. P., Walker, D., Fischer, P., Feldmann, J., Lohmüller, T. Nano Letters, 18:7935–7941, November 2018 (Accepted)
Devising strategies for the controlled injection of functional nanoparticles and reagents into living cells paves the way for novel applications in nanosurgery, sensing, and drug delivery. Here, we demonstrate the light-controlled guiding and injection of plasmonic Janus nanopens into living cells. The pens are made of a gold nanoparticle attached to a dielectric alumina shaft. Balancing optical and thermophoretic forces in an optical tweezer allows single Janus nanopens to be trapped and positioned on the surface of living cells. While the optical injection process involves strong heating of the plasmonic side, the temperature of the alumina stays significantly lower, thus allowing the functionalization with fluorescently labeled, single-stranded DNA and, hence, the spatially controlled injection of genetic material with an untethered nanocarrier.
DOI URL BibTeX
Movement Generation and Control Conference Paper A Whole-Body Model Predictive Control Scheme Including External Contact Forces and CoM Height Variations Mirjalili, R., Yousefi-koma, A., Shirazi, F. A., Nikkhah, A., Nazemi, F., Khadiv, M. Proceedings International Conference on Humanoid Robots, IEEE, Beijing, China, 2018 IEEE-RAS International Conference on Humanoid Robots, November 2018 (Published)
In this paper, we present an approach for generating a variety of whole-body motions for a humanoid robot. We extend the available Model Predictive Control (MPC) approaches for walking on flat terrain to plan for both vertical motion of the Center of Mass (CoM) and external contact forces consistent with a given task. The optimization problem is comprised of three stages, i. e. the CoM vertical motion, joint angles and contact forces planning. The choice of external contact (e. g. hand contact with the object or environment) among all available locations and the appropriate time to reach and maintain a contact are all computed automatically within the algorithm. The presented algorithm benefits from the simplicity of the Linear Inverted Pendulum Model (LIPM), while it overcomes the common limitations of this model and enables us to generate a variety of whole body motions through external contacts. Simulation and experimental implementation of several whole body actions in multi-contact scenarios on a humanoid robot show the capability of the proposed algorithm.
DOI URL BibTeX
Micro, Nano, and Molecular Systems Article A swarm of slippery micropropellers penetrates the vitreous body of the eye Wu, Z., Troll, J., Jeong, H. H., Wei, Q., Stang, M., Ziemssen, F., Wang, Z., Dong, M., Schnichels, S., Qiu, T., Fischer, P. Science Advances, 4(11):eaat4388, November 2018 (Published)
The intravitreal delivery of therapeutic agents promises major benefits in the field of ocular medicine. Traditional delivery methods rely on the random, passive diffusion of molecules, which do not allow for the rapid delivery of a concentrated cargo to a defined region at the posterior pole of the eye. The use of particles promises targeted delivery but faces the challenge that most tissues including the vitreous have a tight macromolecular matrix that acts as a barrier and prevents its penetration. Here, we demonstrate novel intravitreal delivery microvehicles slippery micropropellers that can be actively propelled through the vitreous humor to reach the retina. The propulsion is achieved by helical magnetic micropropellers that have a liquid layer coating to minimize adhesion to the surrounding biopolymeric network. The submicrometer diameter of the propellers enables the penetration of the biopolymeric network and the propulsion through the porcine vitreous body of the eye over centimeter distances. Clinical optical coherence tomography is used to monitor the movement of the propellers and confirm their arrival on the retina near the optic disc. Overcoming the adhesion forces and actively navigating a swarm of micropropellers in the dense vitreous humor promise practical applications in ophthalmology.
Video: Nanorobots propel through the eye DOI URL BibTeX
Haptic Intelligence Miscellaneous A Large-Scale Fabric-Based Tactile Sensor Using Electrical Resistance Tomography Lee, H., Park, K., Kim, J., Kuchenbecker, K. J. 107-109, Hands-on demonstration (3 pages) presented at AsiaHaptics, Incheon, South Korea, November 2018 (Published)
Large-scale tactile sensing is important for household robots and human-robot interaction because contacts can occur all over a robot’s body surface. This paper presents a new fabric-based tactile sensor that is straightforward to manufacture and can cover a large area. The tactile sensor is made of conductive and non-conductive fabric layers, and the electrodes are stitched with conductive thread, so the resulting device is flexible and stretchable. The sensor utilizes internal array electrodes and a reconstruction method called electrical resistance tomography (ERT) to achieve a high spatial resolution with a small number of electrodes. The developed sensor shows that only 16 electrodes can accurately estimate single and multiple contacts over a square that measures 20 cm by 20 cm.
DOI BibTeX
Perceiving Systems Article 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), 37:185:1-185:15, ACM, November 2018, Two first authors contributed equally
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 errata video DOI BibTeX
Intelligent Control Systems Conference Paper Depth Control of Underwater Robots using Sliding Modes and Gaussian Process Regression Lima, G. S., Bessa, W. M., Trimpe, S. In Proceeding of the 15th Latin American Robotics Symposium, João Pessoa, Brazil, 15th Latin American Robotics Symposium, November 2018 (Published)
The development of accurate control systems for underwater robotic vehicles relies on the adequate compensation for hydrodynamic effects. In this work, a new robust control scheme is presented for remotely operated underwater vehicles. In order to meet both robustness and tracking requirements, sliding mode control is combined with Gaussian process regression. The convergence properties of the closed-loop signals are analytically proven. Numerical results confirm the stronger improved performance of the proposed control scheme.
BibTeX
Movement Generation and Control Autonomous Motion Conference Paper Learning Task-Specific Dynamics to Improve Whole-Body Control Gams, A., Mason, S., Ude, A., Schaal, S., Righetti, L. In Hua, IEEE, Beijing, China, November 2018
In task-based inverse dynamics control, reference accelerations used to follow a desired plan can be broken down into feedforward and feedback trajectories. The feedback term accounts for tracking errors that are caused from inaccurate dynamic models or external disturbances. On underactuated, free-floating robots, such as humanoids, high feedback terms can be used to improve tracking accuracy; however, this can lead to very stiff behavior or poor tracking accuracy due to limited control bandwidth. In this paper, we show how to reduce the required contribution of the feedback controller by incorporating learned task-space reference accelerations. Thus, we i) improve the execution of the given specific task, and ii) offer the means to reduce feedback gains, providing for greater compliance of the system. With a systematic approach we also reduce heuristic tuning of the model parameters and feedback gains, often present in real-world experiments. In contrast to learning task-specific joint-torques, which might produce a similar effect but can lead to poor generalization, our approach directly learns the task-space dynamics of the center of mass of a humanoid robot. Simulated and real-world results on the lower part of the Sarcos Hermes humanoid robot demonstrate the applicability of the approach.
URL BibTeX
Autonomous Motion Article 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, 1,15, October 2018
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.
DOI URL BibTeX
Empirical Inference Conference Paper Constraint-Space Projection Direct Policy Search Akrour, R., Peters, J., Neuman, G. 14th European Workshop on Reinforcement Learning (EWRL), October 2018 (Published) URL BibTeX
Empirical Inference Article Control of Musculoskeletal Systems using Learned Dynamics Models Büchler, D., Calandra, R., Schölkopf, B., Peters, J. IEEE Robotics and Automation Letters, 3(4):3161-3168, IEEE, October 2018 (Published)
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 DOI URL BibTeX
Perceiving Systems Article 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). (Published)
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 DOI URL BibTeX
Empirical Inference Conference Paper 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), 87:700-713, Proceedings of Machine Learning Research, PMLR, October 2018 (Published) URL BibTeX
Perceiving Systems Article 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
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
Intelligent Control Systems Micro, Nano, and Molecular Systems Conference Paper Gait learning for soft microrobots controlled by light fields Rohr, A. V., Trimpe, S., Marco, A., Fischer, P., Palagi, S. In International Conference on Intelligent Robots and Systems (IROS) 2018, 6199-6206, Piscataway, NJ, USA, International Conference on Intelligent Robots and Systems, October 2018 (Published)
Soft microrobots based on photoresponsive materials and controlled by light fields can generate a variety of different gaits. This inherent flexibility can be exploited to maximize their locomotion performance in a given environment and used to adapt them to changing environments. However, because of the lack of accurate locomotion models, and given the intrinsic variability among microrobots, analytical control design is not possible. Common data-driven approaches, on the other hand, require running prohibitive numbers of experiments and lead to very sample-specific results. Here we propose a probabilistic learning approach for light-controlled soft microrobots based on Bayesian Optimization (BO) and Gaussian Processes (GPs). The proposed approach results in a learning scheme that is highly data-efficient, enabling gait optimization with a limited experimental budget, and robust against differences among microrobot samples. These features are obtained by designing the learning scheme through the comparison of different GP priors and BO settings on a semisynthetic data set. The developed learning scheme is validated in microrobot experiments, resulting in a 115% improvement in a microrobot’s locomotion performance with an experimental budget of only 20 tests. These encouraging results lead the way toward self-adaptive microrobotic systems based on lightcontrolled soft microrobots and probabilistic learning control.
arXiv IEEE Xplore DOI URL BibTeX
Movement Generation and Control Article Learning a Structured Neural Network Policy for a Hopping Task. Viereck, J., Kozolinsky, J., Herzog, A., Righetti, L. IEEE Robotics and Automation Letters, 3(4):4092-4099, October 2018 DOI URL BibTeX
Empirical Inference Conference Paper 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), 7-12, October 2018 (Published) URL BibTeX
Empirical Inference Conference Paper Mean squared advantage minimization as a consequence of entropic policy improvement regularization Belousov, B., Peters, J. European Workshop on Reinforcement Learning (EWRL), October 2018 (Published) URL BibTeX
Micro, Nano, and Molecular Systems Book Chapter Nanoscale robotic agents in biological fluids and tissues Palagi, S., Walker, D. Q. T., Fischer, P. In The Encyclopedia of Medical Robotics, 2:19-42, 2, (Editors: Desai, J. P. and Ferreira, A.), World Scientific, October 2018 (Published)
Nanorobots are untethered structures of sub-micron size that can be controlled in a non-trivial way. Such nanoscale robotic agents are envisioned to revolutionize medicine by enabling minimally invasive diagnostic and therapeutic procedures. To be useful, nanorobots must be operated in complex biological fluids and tissues, which are often difficult to penetrate. In this chapter, we first discuss potential medical applications of motile nanorobots. We briefly present the challenges related to swimming at such small scales and we survey the rheological properties of some biological fluids and tissues. We then review recent experimental results in the development of nanorobots and in particular their design, fabrication, actuation, and propulsion in complex biological fluids and tissues. Recent work shows that their nanoscale dimension is a clear asset for operation in biological tissues, since many biological tissues consist of networks of macromolecules that prevent the passage of larger micron-scale structures, but contain dynamic pores through which nanorobots can move.
DOI URL BibTeX
Perceiving Systems Autonomous Vision Conference Paper 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 11269:281-297, Springer, Cham, October 2018
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.
arXiv DOI BibTeX
Empirical Inference Conference Paper 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), 534-539, October 2018 (Published) DOI URL BibTeX
Empirical Inference Conference Paper 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), 87:630-640, (Editors: Aude Billard, Anca Dragan, Jan Peters, Jun Morimoto ), PMLR, October 2018 (Published) URL BibTeX
Haptic Intelligence Article Softness, Warmth, and Responsiveness Improve Robot Hugs Block, A. E., Kuchenbecker, K. J. International Journal of Social Robotics, 11(1):49-64, October 2018 (Published)
Hugs are one of the first forms of contact and affection humans experience. Due to their prevalence and health benefits, roboticists are naturally interested in having robots one day hug humans as seamlessly as humans hug other humans. This project's purpose is to evaluate human responses to different robot physical characteristics and hugging behaviors. Specifically, we aim to test the hypothesis that a soft, warm, touch-sensitive PR2 humanoid robot can provide humans with satisfying hugs by matching both their hugging pressure and their hugging duration. Thirty relatively young and rather technical participants experienced and evaluated twelve hugs with the robot, divided into three randomly ordered trials that focused on physical robot characteristics (single factor, three levels) and nine randomly ordered trials with low, medium, and high hug pressure and duration (two factors, three levels each). Analysis of the results showed that people significantly prefer soft, warm hugs over hard, cold hugs. Furthermore, users prefer hugs that physically squeeze them and release immediately when they are ready for the hug to end. Taking part in the experiment also significantly increased positive user opinions of robots and robot use.
DOI BibTeX
Perceiving Systems Conference Paper Temporal Interpolation as an Unsupervised Pretraining Task for Optical Flow Estimation Wulff, J., Black, M. J. In German Conference on Pattern Recognition (GCPR), LNCS 11269:567-582, Springer, Cham, October 2018
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 fi ne-tuning on small amounts of ground truth flow, the network can learn to fill in homogeneous regions and compute full optical flow fi elds. Using this unsupervised pre-training, our network outperforms similar architectures that were trained supervised using synthetic optical flow.
pdf arXiv DOI BibTeX
Autonomous Vision Conference Paper Towards Robust Visual Odometry with a Multi-Camera System Liu, P., Geppert, M., Heng, L., Sattler, T., Geiger, A., Pollefeys, M. In International Conference on Intelligent Robots and Systems (IROS) 2018, International Conference on Intelligent Robots and Systems, October 2018
We present a visual odometry (VO) algorithm for a multi-camera system and robust operation in challenging environments. Our algorithm consists of a pose tracker and a local mapper. The tracker estimates the current pose by minimizing photometric errors between the most recent keyframe and the current frame. The mapper initializes the depths of all sampled feature points using plane-sweeping stereo. To reduce pose drift, a sliding window optimizer is used to refine poses and structure jointly. Our formulation is flexible enough to support an arbitrary number of stereo cameras. We evaluate our algorithm thoroughly on five datasets. The datasets were captured in different conditions: daytime, night-time with near-infrared (NIR) illumination and night-time without NIR illumination. Experimental results show that a multi-camera setup makes the VO more robust to challenging environments, especially night-time conditions, in which a single stereo configuration fails easily due to the lack of features.
pdf BibTeX
Physical Intelligence Article Universal custom complex magnetic spring design methodology Woodward, M. A., Sitti, M. IEEE Transactions on Magnetics, 54(1): 8200213, October 2018
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
Micro, Nano, and Molecular Systems Article Fast spatial scanning of 3D ultrasound fields via thermography Melde, K., Qiu, T., Fischer, P. Applied Physics Letters, 113(13):133503, September 2018 (Published)
We propose and demonstrate a thermographic method that allows rapid scanning of ultrasound fields in a volume to yield 3D maps of the sound intensity. A thin sound-absorbing membrane is continuously translated through a volume of interest while a thermal camera records the evolution of its surface temperature. The temperature rise is a function of the absorbed sound intensity, such that the thermal image sequence can be combined to reveal the sound intensity distribution in the traversed volume. We demonstrate the mapping of ultrasound fields, which is several orders of magnitude faster than scanning with a hydrophone. Our results are in very good agreement with theoretical simulations.
DOI URL BibTeX