Header logo is


2017


Thumb xl amd intentiongan
Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets

Hausman, K., Chebotar, Y., Schaal, S., Sukhatme, G., Lim, J.

In Proceedings from the conference "Neural Information Processing Systems 2017., (Editors: Guyon I. and Luxburg U.v. and Bengio S. and Wallach H. and Fergus R. and Vishwanathan S. and Garnett R.), Curran Associates, Inc., Advances in Neural Information Processing Systems 30 (NIPS), December 2017 (inproceedings)

am

pdf video [BibTex]

2017


pdf video [BibTex]


Thumb xl fig1
Active colloidal propulsion over a crystalline surface

Choudhury, U., Straube, A., Fischer, P., Gibbs, J., Höfling, F.

New Journal of Physics, 19, pages: 125010, December 2017 (article)

Abstract
We study both experimentally and theoretically the dynamics of chemically self-propelled Janus colloids moving atop a two-dimensional crystalline surface. The surface is a hexagonally close-packed monolayer of colloidal particles of the same size as the mobile one. The dynamics of the self-propelled colloid reflects the competition between hindered diffusion due to the periodic surface and enhanced diffusion due to active motion. Which contribution dominates depends on the propulsion strength, which can be systematically tuned by changing the concentration of a chemical fuel. The mean-square displacements obtained from the experiment exhibit enhanced diffusion at long lag times. Our experimental data are consistent with a Langevin model for the effectively two-dimensional translational motion of an active Brownian particle in a periodic potential, combining the confining effects of gravity and the crystalline surface with the free rotational diffusion of the colloid. Approximate analytical predictions are made for the mean-square displacement describing the crossover from free Brownian motion at short times to active diffusion at long times. The results are in semi-quantitative agreement with numerical results of a refined Langevin model that treats translational and rotational degrees of freedom on the same footing.

pf

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl fig toyex lqr1kernel 1
On the Design of LQR Kernels for Efficient Controller Learning

Marco, A., Hennig, P., Schaal, S., Trimpe, S.

Proceedings of the 56th IEEE Annual Conference on Decision and Control (CDC), pages: 5193-5200, IEEE, IEEE Conference on Decision and Control, December 2017 (conference)

Abstract
Finding optimal feedback controllers for nonlinear dynamic systems from data is hard. Recently, Bayesian optimization (BO) has been proposed as a powerful framework for direct controller tuning from experimental trials. For selecting the next query point and finding the global optimum, BO relies on a probabilistic description of the latent objective function, typically a Gaussian process (GP). As is shown herein, GPs with a common kernel choice can, however, lead to poor learning outcomes on standard quadratic control problems. For a first-order system, we construct two kernels that specifically leverage the structure of the well-known Linear Quadratic Regulator (LQR), yet retain the flexibility of Bayesian nonparametric learning. Simulations of uncertain linear and nonlinear systems demonstrate that the LQR kernels yield superior learning performance.

am ics pn

arXiv PDF On the Design of LQR Kernels for Efficient Controller Learning - CDC presentation DOI Project Page [BibTex]

arXiv PDF On the Design of LQR Kernels for Efficient Controller Learning - CDC presentation DOI Project Page [BibTex]


Thumb xl robot legos
Interactive Perception: Leveraging Action in Perception and Perception in Action

Bohg, J., Hausman, K., Sankaran, B., Brock, O., Kragic, D., Schaal, S., Sukhatme, G.

IEEE Transactions on Robotics, 33, pages: 1273-1291, December 2017 (article)

Abstract
Recent approaches in robotics follow the insight that perception is facilitated by interactivity with the environment. These approaches are subsumed under the term of Interactive Perception (IP). We argue that IP provides the following benefits: (i) any type of forceful interaction with the environment creates a new type of informative sensory signal that would otherwise not be present and (ii) any prior knowledge about the nature of the interaction supports the interpretation of the signal. This is facilitated by knowledge of the regularity in the combined space of sensory information and action parameters. The goal of this survey is to postulate this as a principle and collect evidence in support by analyzing and categorizing existing work in this area. We also provide an overview of the most important applications of Interactive Perception. We close this survey by discussing the remaining open questions. Thereby, we hope to define a field and inspire future work.

am

arXiv DOI Project Page [BibTex]

arXiv DOI Project Page [BibTex]


Thumb xl fig1
Wireless Acoustic-Surface Actuators for Miniaturized Endoscopes

Qiu, T., Adams, F., Palagi, S., Melde, K., Mark, A. G., Wetterauer, U., Miernik, A., Fischer, P.

ACS Applied Materials & Interfaces, 9(49):42536 - 42543, November 2017 (article)

Abstract
Endoscopy enables minimally invasive procedures in many medical fields, such as urology. However, current endoscopes are normally cable-driven, which limits their dexterity and makes them hard to miniaturize. Indeed current urological endoscopes have an outer diameter of about 3 mm and still only possess one bending degree of freedom. In this paper, we report a novel wireless actuation mechanism that increases the dexterity and that permits the miniaturization of a urological endoscope. The novel actuator consists of thin active surfaces that can be readily attached to any device and are wirelessly powered by ultrasound. The surfaces consist of two-dimensional arrays of micro-bubbles, which oscillate under ultrasound excitation and thereby generate an acoustic streaming force. Bubbles of different sizes are addressed by their unique resonance frequency, thus multiple degrees of freedom can readily be incorporated. Two active miniaturized devices (with a side length of around 1 mm) are demonstrated: a miniaturized mechanical arm that realizes two degrees of freedom, and a flexible endoscope prototype equipped with a camera at the tip. With the flexible endoscope, an active endoscopic examination is successfully performed in a rabbit bladder. This results show the potential medical applicability of surface actuators wirelessly powered by ultrasound penetrating through biological tissues.

pf

link (url) DOI Project Page [BibTex]

link (url) DOI Project Page [BibTex]


Thumb xl teaser
Optimizing Long-term Predictions for Model-based Policy Search

Doerr, A., Daniel, C., Nguyen-Tuong, D., Marco, A., Schaal, S., Toussaint, M., Trimpe, S.

Proceedings of 1st Annual Conference on Robot Learning (CoRL), 78, pages: 227-238, (Editors: Sergey Levine and Vincent Vanhoucke and Ken Goldberg), 1st Annual Conference on Robot Learning, November 2017 (conference)

Abstract
We propose a novel long-term optimization criterion to improve the robustness of model-based reinforcement learning in real-world scenarios. Learning a dynamics model to derive a solution promises much greater data-efficiency and reusability compared to model-free alternatives. In practice, however, modelbased RL suffers from various imperfections such as noisy input and output data, delays and unmeasured (latent) states. To achieve higher resilience against such effects, we propose to optimize a generative long-term prediction model directly with respect to the likelihood of observed trajectories as opposed to the common approach of optimizing a dynamics model for one-step-ahead predictions. We evaluate the proposed method on several artificial and real-world benchmark problems and compare it to PILCO, a model-based RL framework, in experiments on a manipulation robot. The results show that the proposed method is competitive compared to state-of-the-art model learning methods. In contrast to these more involved models, our model can directly be employed for policy search and outperforms a baseline method in the robot experiment.

am ics

PDF Project Page [BibTex]

PDF Project Page [BibTex]


Thumb xl qg net rev
Acquiring Target Stacking Skills by Goal-Parameterized Deep Reinforcement Learning

Li, W., Bohg, J., Fritz, M.

arXiv, November 2017 (article) Submitted

Abstract
Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through interaction with the environment. We created a synthetic block stacking environment with physics simulation in which the agent can learn a policy end-to-end through trial and error. Thereby, we bypass to explicitly model physical knowledge within the policy. We are specifically interested in tasks that require the agent to reach a given goal state that may be different for every new trial. To this end, we propose a deep reinforcement learning framework that learns policies which are parametrized by a goal. We validated the model on a toy example navigating in a grid world with different target positions and in a block stacking task with different target structures of the final tower. In contrast to prior work, our policies show better generalization across different goals.

am

arXiv [BibTex]


Thumb xl admi201770108 gra 0001 m
Active Acoustic Surfaces Enable the Propulsion of a Wireless Robot

Qiu, T., Palagi, S., Mark, A. G., Melde, K., Adams, F., Fischer, P.

Advanced Materials Interfaces, 4(21):1700933, September 2017 (article)

Abstract
A major challenge that prevents the miniaturization of mechanically actuated systems is the lack of suitable methods that permit the efficient transfer of power to small scales. Acoustic energy holds great potential, as it is wireless, penetrates deep into biological tissues, and the mechanical vibrations can be directly converted into directional forces. Recently, active acoustic surfaces are developed that consist of 2D arrays of microcavities holding microbubbles that can be excited with an external acoustic field. At resonance, the surfaces give rise to acoustic streaming and thus provide a highly directional propulsive force. Here, this study advances these wireless surface actuators by studying their force output as the size of the bubble-array is increased. In particular, a general method is reported to dramatically improve the propulsive force, demonstrating that the surface actuators are actually able to propel centimeter-scale devices. To prove the flexibility of the functional surfaces as wireless ready-to-attach actuator, a mobile mini-robot capable of propulsion in water along multiple directions is presented. This work paves the way toward effectively exploiting acoustic surfaces as a novel wireless actuation scheme at small scales.

pf

link (url) DOI Project Page [BibTex]


no image
A New Data Source for Inverse Dynamics Learning

Kappler, D., Meier, F., Ratliff, N., Schaal, S.

In Proceedings IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, Piscataway, NJ, USA, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), September 2017 (inproceedings)

am

[BibTex]

[BibTex]


no image
Bayesian Regression for Artifact Correction in Electroencephalography

Fiebig, K., Jayaram, V., Hesse, T., Blank, A., Peters, J., Grosse-Wentrup, M.

Proceedings of the 7th Graz Brain-Computer Interface Conference 2017 - From Vision to Reality, pages: 131-136, (Editors: Müller-Putz G.R., Steyrl D., Wriessnegger S. C., Scherer R.), Graz University of Technology, Austria, Graz Brain-Computer Interface Conference, September 2017 (conference)

am ei

DOI [BibTex]

DOI [BibTex]


no image
Investigating Music Imagery as a Cognitive Paradigm for Low-Cost Brain-Computer Interfaces

Grossberger, L., Hohmann, M. R., Peters, J., Grosse-Wentrup, M.

Proceedings of the 7th Graz Brain-Computer Interface Conference 2017 - From Vision to Reality, pages: 160-164, (Editors: Müller-Putz G.R., Steyrl D., Wriessnegger S. C., Scherer R.), Graz University of Technology, Austria, Graz Brain-Computer Interface Conference, September 2017 (conference)

am ei

DOI [BibTex]

DOI [BibTex]


Thumb xl jeong et al 2017 advanced science
Corrosion-Protected Hybrid Nanoparticles

Jeong, H. H., Alarcon-Correa, M., Mark, A. G., Son, K., Lee, T., Fischer, P.

Advanced Science, 4(12):1700234, September 2017 (article)

Abstract
Nanoparticles composed of functional materials hold great promise for applications due to their unique electronic, optical, magnetic, and catalytic properties. However, a number of functional materials are not only difficult to fabricate at the nanoscale, but are also chemically unstable in solution. Hence, protecting nanoparticles from corrosion is a major challenge for those applications that require stability in aqueous solutions and biological fluids. Here, this study presents a generic scheme to grow hybrid 3D nanoparticles that are completely encapsulated by a nm thick protective shell. The method consists of vacuum-based growth and protection, and combines oblique physical vapor deposition with atomic layer deposition. It provides wide flexibility in the shape and composition of the nanoparticles, and the environments against which particles are protected. The work demonstrates the approach with multifunctional nanoparticles possessing ferromagnetic, plasmonic, and chiral properties. The present scheme allows nanocolloids, which immediately corrode without protection, to remain functional, at least for a week, in acidic solutions.

pf

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl screen shot 2017 08 01 at 15.41.10
On the relevance of grasp metrics for predicting grasp success

Rubert, C., Kappler, D., Morales, A., Schaal, S., Bohg, J.

In Proceedings of the IEEE/RSJ International Conference of Intelligent Robots and Systems, September 2017 (inproceedings) Accepted

Abstract
We aim to reliably predict whether a grasp on a known object is successful before it is executed in the real world. There is an entire suite of grasp metrics that has already been developed which rely on precisely known contact points between object and hand. However, it remains unclear whether and how they may be combined into a general purpose grasp stability predictor. In this paper, we analyze these questions by leveraging a large scale database of simulated grasps on a wide variety of objects. For each grasp, we compute the value of seven metrics. Each grasp is annotated by human subjects with ground truth stability labels. Given this data set, we train several classification methods to find out whether there is some underlying, non-trivial structure in the data that is difficult to model manually but can be learned. Quantitative and qualitative results show the complexity of the prediction problem. We found that a good prediction performance critically depends on using a combination of metrics as input features. Furthermore, non-parametric and non-linear classifiers best capture the structure in the data.

am

Project Page [BibTex]

Project Page [BibTex]


no image
Local Bayesian Optimization of Motor Skills

Akrour, R., Sorokin, D., Peters, J., Neumann, G.

Proceedings of the 34th International Conference on Machine Learning, 70, pages: 41-50, Proceedings of Machine Learning Research, (Editors: Doina Precup, Yee Whye Teh), PMLR, International Conference on Machine Learning (ICML), August 2017 (conference)

am ei

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]


Thumb xl pilqr cover
Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning

Chebotar, Y., Hausman, K., Zhang, M., Sukhatme, G., Schaal, S., Levine, S.

Proceedings of the 34th International Conference on Machine Learning, 70, Proceedings of Machine Learning Research, (Editors: Doina Precup, Yee Whye Teh), PMLR, International Conference on Machine Learning (ICML), August 2017 (conference)

am

pdf video [BibTex]

pdf video [BibTex]


Thumb xl fig1
Locomotion of light-driven soft microrobots through a hydrogel via local melting

Palagi, S., Mark, A. G., Melde, K., Qiu, T., Zeng, H., Parmeggiani, C., Martella, D., Wiersma, D. S., Fischer, P.

In 2017 International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS), pages: 1-5, July 2017 (inproceedings)

Abstract
Soft mobile microrobots whose deformation can be directly controlled by an external field can adapt to move in different environments. This is the case for the light-driven microrobots based on liquid-crystal elastomers (LCEs). Here we show that the soft microrobots can move through an agarose hydrogel by means of light-controlled travelling-wave motions. This is achieved by exploiting the inherent rise of the LCE temperature above the melting temperature of the agarose gel, which facilitates penetration of the microrobot through the hydrogel. The locomotion performance is investigated as a function of the travelling-wave parameters, showing that effective propulsion can be obtained by adapting the generated motion to the specific environmental conditions.

pf

DOI [BibTex]

DOI [BibTex]


no image
Event-based State Estimation: An Emulation-based Approach

Trimpe, S.

IET Control Theory & Applications, 11(11):1684-1693, July 2017 (article)

Abstract
An event-based state estimation approach for reducing communication in a networked control system is proposed. Multiple distributed sensor agents observe a dynamic process and sporadically transmit their measurements to estimator agents over a shared bus network. Local event-triggering protocols ensure that data is transmitted only when necessary to meet a desired estimation accuracy. The event-based design is shown to emulate the performance of a centralised state observer design up to guaranteed bounds, but with reduced communication. The stability results for state estimation are extended to the distributed control system that results when the local estimates are used for feedback control. Results from numerical simulations and hardware experiments illustrate the effectiveness of the proposed approach in reducing network communication.

am ics

arXiv Supplementary material PDF DOI Project Page [BibTex]

arXiv Supplementary material PDF DOI Project Page [BibTex]


Thumb xl comp 3e 00000 copy
Non-Equilibrium Assembly of Light-Activated Colloidal Mixtures

Singh, D. P., Choudhury, U., Fischer, P., Mark, A. G.

Advanced Materials, 29, pages: 1701328, June 2017, 32 (article)

Abstract
The collective phenomena exhibited by artificial active matter systems present novel routes to fabricating out-of-equilibrium microscale assemblies. Here, the crystallization of passive silica colloids into well-controlled 2D assemblies is shown, which is directed by a small number of self-propelled active colloids. The active colloids are titania–silica Janus particles that are propelled when illuminated by UV light. The strength of the attractive interaction and thus the extent of the assembled clusters can be regulated by the light intensity. A remarkably small number of the active colloids is sufficient to induce the assembly of the dynamic crystals. The approach produces rationally designed colloidal clusters and crystals with controllable sizes, shapes, and symmetries. This multicomponent active matter system offers the possibility of obtaining structures and assemblies that cannot be found in equilibrium systems.

pf

link (url) DOI [BibTex]


Thumb xl kim et al 2017 advanced materials
Nanodiamonds That Swim

Kim, J. T., Choudhury, U., Hyeon-Ho, J., Fischer, P.

Advanced Materials, 29(30):1701024, June 2017, Back Cover (article)

Abstract
Nanodiamonds are emerging as nanoscale quantum probes for bio-sensing and imaging. This necessitates the development of new methods to accurately manipulate their position and orientation in aqueous solutions. The realization of an “active” nanodiamond (ND) swimmer in fluids, composed of a ND crystal containing nitrogen vacancy centers and a light-driven self-thermophoretic micromotor, is reported. The swimmer is propelled by a local temperature gradient created by laser illumination on its metal-coated side. Its locomotion—from translational to rotational motion—is successfully controlled by shape-dependent hydrodynamic interactions. The precise engineering of the swimmer's geometry is achieved by self-assembly combined with physical vapor shadow growth. The optical addressability of the suspended ND swimmers is demonstrated by observing the electron spin resonance in the presence of magnetic fields. Active motion at the nanoscale enables new sensing capabilities combined with active transport including, potentially, in living organisms.

pf

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl apollo system2 croped
Model-Based Policy Search for Automatic Tuning of Multivariate PID Controllers

Doerr, A., Nguyen-Tuong, D., Marco, A., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 5295-5301, IEEE, Piscataway, NJ, USA, IEEE International Conference on Robotics and Automation (ICRA), May 2017 (inproceedings)

am ics

PDF arXiv DOI Project Page [BibTex]

PDF arXiv DOI Project Page [BibTex]


Thumb xl learning ct block diagram v2
Learning Feedback Terms for Reactive Planning and Control

Rai, A., Sutanto, G., Schaal, S., Meier, F.

Proceedings 2017 IEEE International Conference on Robotics and Automation (ICRA), IEEE, Piscataway, NJ, USA, IEEE International Conference on Robotics and Automation (ICRA), May 2017 (conference)

am

pdf video [BibTex]

pdf video [BibTex]


Thumb xl this one
Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization

Marco, A., Berkenkamp, F., Hennig, P., Schoellig, A. P., Krause, A., Schaal, S., Trimpe, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 1557-1563, IEEE, Piscataway, NJ, USA, IEEE International Conference on Robotics and Automation (ICRA), May 2017 (inproceedings)

am ics pn

PDF arXiv ICRA 2017 Spotlight presentation Virtual vs. Real - Video explanation DOI Project Page [BibTex]

PDF arXiv ICRA 2017 Spotlight presentation Virtual vs. Real - Video explanation DOI Project Page [BibTex]


Thumb xl fig  quali  arm
Probabilistic Articulated Real-Time Tracking for Robot Manipulation

(Best Paper of RA-L 2017, Finalist of Best Robotic Vision Paper Award of ICRA 2017)

Garcia Cifuentes, C., Issac, J., Wüthrich, M., Schaal, S., Bohg, J.

IEEE Robotics and Automation Letters (RA-L), 2(2):577-584, April 2017 (article)

Abstract
We propose a probabilistic filtering method which fuses joint measurements with depth images to yield a precise, real-time estimate of the end-effector pose in the camera frame. This avoids the need for frame transformations when using it in combination with visual object tracking methods. Precision is achieved by modeling and correcting biases in the joint measurements as well as inaccuracies in the robot model, such as poor extrinsic camera calibration. We make our method computationally efficient through a principled combination of Kalman filtering of the joint measurements and asynchronous depth-image updates based on the Coordinate Particle Filter. We quantitatively evaluate our approach on a dataset recorded from a real robotic platform, annotated with ground truth from a motion capture system. We show that our approach is robust and accurate even under challenging conditions such as fast motion, significant and long-term occlusions, and time-varying biases. We release the dataset along with open-source code of our approach to allow for quantitative comparison with alternative approaches.

am

arXiv video code and dataset video PDF DOI Project Page [BibTex]


Thumb xl toc image
Soft 3D-Printed Phantom of the Human Kidney with Collecting System

Adams, F., Qiu, T., Mark, A., Fritz, B., Kramer, L., Schlager, D., Wetterauer, U., Miernik, A., Fischer, P.

Ann. of Biomed. Eng., 45(4):963-972, April 2017 (article)

Abstract
Organ models are used for planning and simulation of operations, developing new surgical instruments, and training purposes. There is a substantial demand for in vitro organ phantoms, especially in urological surgery. Animal models and existing simulator systems poorly mimic the detailed morphology and the physical properties of human organs. In this paper, we report a novel fabrication process to make a human kidney phantom with realistic anatomical structures and physical properties. The detailed anatomical structure was directly acquired from high resolution CT data sets of human cadaveric kidneys. The soft phantoms were constructed using a novel technique that combines 3D wax printing and polymer molding. Anatomical details and material properties of the phantoms were validated in detail by CT scan, ultrasound, and endoscopy. CT reconstruction, ultrasound examination, and endoscopy showed that the designed phantom mimics a real kidney's detailed anatomy and correctly corresponds to the targeted human cadaver's upper urinary tract. Soft materials with a tensile modulus of 0.8-1.5 MPa as well as biocompatible hydrogels were used to mimic human kidney tissues. We developed a method of constructing 3D organ models from medical imaging data using a 3D wax printing and molding process. This method is cost-effective means for obtaining a reproducible and robust model suitable for surgical simulation and training purposes.

pf

DOI Project Page [BibTex]

DOI Project Page [BibTex]


Thumb xl fig1
Chapter 8 - Micro- and nanorobots in Newtonian and biological viscoelastic fluids

Palagi, S., (Walker) Schamel, D., Qiu, T., Fischer, P.

In Microbiorobotics, pages: 133 - 162, 8, Micro and Nano Technologies, Second edition, Elsevier, Boston, March 2017 (incollection)

Abstract
Swimming microorganisms are a source of inspiration for small scale robots that are intended to operate in fluidic environments including complex biomedical fluids. Nature has devised swimming strategies that are effective at small scales and at low Reynolds number. These include the rotary corkscrew motion that, for instance, propels a flagellated bacterial cell, as well as the asymmetric beat of appendages that sperm cells or ciliated protozoa use to move through fluids. These mechanisms can overcome the reciprocity that governs the hydrodynamics at small scale. The complex molecular structure of biologically important fluids presents an additional challenge for the effective propulsion of microrobots. In this chapter it is shown how physical and chemical approaches are essential in realizing engineered abiotic micro- and nanorobots that can move in biomedically important environments. Interestingly, we also describe a microswimmer that is effective in biological viscoelastic fluids that does not have a natural analogue.

pf

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl eururol2017
Wireless micro-robots for endoscopic applications in urology

Adams, F., Qiu, T., Mark, A. G., Melde, K., Palagi, S., Miernik, A., Fischer, P.

In Eur Urol Suppl, 16(3):e1914, March 2017 (inproceedings)

Abstract
Endoscopy is an essential and common method for both diagnostics and therapy in Urology. Current flexible endoscope is normally cable-driven, thus it is hard to be miniaturized and its reachability is restricted as only one bending section near the tip with one degree of freedom (DoF) is allowed. Recent progresses in micro-robotics offer a unique opportunity for medical inspections in minimally invasive surgery. Micro-robots are active devices that has a feature size smaller than one millimeter and can normally be actuated and controlled wirelessly. Magnetically actuated micro-robots have been demonstrated to propel through biological fluids.Here, we report a novel micro robotic arm, which is actuated wirelessly by ultrasound. It works as a miniaturized endoscope with a side length of ~1 mm, which fits through the 3 Fr. tool channel of a cystoscope, and successfully performs an active cystoscopy in a rabbit bladder.

pf

link (url) DOI [BibTex]


Thumb xl toc image
Pattern formation and collective effects in populations of magnetic microswimmers

Vach, P. J., (Walker) Schamel, D., Fischer, P., Fratzl, P., Faivre, D.

J. of Phys. D: Appl. Phys., 50(11):11LT03, Febuary 2017 (article)

Abstract
Self-propelled particles are one prototype of synthetic active matter used to understand complex biological processes, such as the coordination of movement in bacterial colonies or schools of fishes. Collective patterns such as clusters were observed for such systems, reproducing features of biological organization. However, one limitation of this model is that the synthetic assemblies are made of identical individuals. Here we introduce an active system based on magnetic particles at colloidal scales. We use identical but also randomly-shaped magnetic micropropellers and show that they exhibit dynamic and reversible pattern formation.

pf

DOI [BibTex]

DOI [BibTex]


Thumb xl toc image
On-chip enzymatic microbiofuel cell-powered integrated circuits

Mark, A. G., Suraniti, E., Roche, J., Richter, H., Kuhn, A., Mano, N., Fischer, P.

Lab on a Chip, 17(10):1761-1768, Febuary 2017, Recent HOT Article (article)

Abstract
A variety of diagnostic and therapeutic medical technologies rely on long term implantation of an electronic device to monitor or regulate a patient's condition. One proposed approach to powering these devices is to use a biofuel cell to convert the chemical energy from blood nutrients into electrical current to supply the electronics. We present here an enzymatic microbiofuel cell whose electrodes are directly integrated into a digital electronic circuit. Glucose oxidizing and oxygen reducing enzymes are immobilized on microelectrodes of an application specific integrated circuit (ASIC) using redox hydrogels to produce an enzymatic biofuel cell, capable of harvesting electrical power from just a single droplet of 5 mM glucose solution. Optimisation of the fuel cell voltage and power to match the requirements of the electronics allow self-powered operation of the on-board digital circuitry. This study represents a step towards implantable self-powered electronic devices that gather their energy from physiological fluids.

Recent HOT Article.

pf

DOI [BibTex]

DOI [BibTex]


Thumb xl toc image
Strong Rotational Anisotropies Affect Nonlinear Chiral Metamaterials

Hooper, D. C., Mark, A. G., Kuppe, C., Collins, J. T., Fischer, P., Valev, V. K.

Advanced Materials, 29(13):1605110, January 2017 (article)

Abstract
Masked by rotational anisotropies, the nonlinear chiroptical response of a metamaterial is initially completely inaccessible. Upon rotating the sample the chiral information emerges. These results highlight the need for a general method to extract the true chiral contributions to the nonlinear optical signal, which would be hugely valuable in the present context of increasingly complex chiral meta/nanomaterials.

pf

DOI [BibTex]

DOI [BibTex]


no image
Anticipatory Action Selection for Human-Robot Table Tennis

Wang, Z., Boularias, A., Mülling, K., Schölkopf, B., Peters, J.

Artificial Intelligence, 247, pages: 399-414, 2017, Special Issue on AI and Robotics (article)

Abstract
Abstract Anticipation can enhance the capability of a robot in its interaction with humans, where the robot predicts the humans' intention for selecting its own action. We present a novel framework of anticipatory action selection for human-robot interaction, which is capable to handle nonlinear and stochastic human behaviors such as table tennis strokes and allows the robot to choose the optimal action based on prediction of the human partner's intention with uncertainty. The presented framework is generic and can be used in many human-robot interaction scenarios, for example, in navigation and human-robot co-manipulation. In this article, we conduct a case study on human-robot table tennis. Due to the limited amount of time for executing hitting movements, a robot usually needs to initiate its hitting movement before the opponent hits the ball, which requires the robot to be anticipatory based on visual observation of the opponent's movement. Previous work on Intention-Driven Dynamics Models (IDDM) allowed the robot to predict the intended target of the opponent. In this article, we address the problem of action selection and optimal timing for initiating a chosen action by formulating the anticipatory action selection as a Partially Observable Markov Decision Process (POMDP), where the transition and observation are modeled by the \{IDDM\} framework. We present two approaches to anticipatory action selection based on the \{POMDP\} formulation, i.e., a model-free policy learning method based on Least-Squares Policy Iteration (LSPI) that employs the \{IDDM\} for belief updates, and a model-based Monte-Carlo Planning (MCP) method, which benefits from the transition and observation model by the IDDM. Experimental results using real data in a simulated environment show the importance of anticipatory action selection, and that \{POMDPs\} are suitable to formulate the anticipatory action selection problem by taking into account the uncertainties in prediction. We also show that existing algorithms for POMDPs, such as \{LSPI\} and MCP, can be applied to substantially improve the robot's performance in its interaction with humans.

am ei

DOI Project Page [BibTex]

DOI Project Page [BibTex]


no image
Robot Learning

Peters, J., Lee, D., Kober, J., Nguyen-Tuong, D., Bagnell, J., Schaal, S.

In Springer Handbook of Robotics, pages: 357-394, 15, 2nd, (Editors: Siciliano, Bruno and Khatib, Oussama), Springer International Publishing, 2017 (inbook)

am ei

Project Page [BibTex]

Project Page [BibTex]


no image
Momentum-Centered Control of Contact Interactions

Righetti, L., Herzog, A.

In Geometric and Numerical Foundations of Movements, 117, pages: 339-359, Springer Tracts in Advanced Robotics, Springer, Cham, 2017 (incollection)

mg

link (url) [BibTex]

link (url) [BibTex]


no image
Pattern Generation for Walking on Slippery Terrains

Khadiv, M., Moosavian, S. A. A., Herzog, A., Righetti, L.

In 2017 5th International Conference on Robotics and Mechatronics (ICROM), Iran, August 2017 (inproceedings)

Abstract
In this paper, we extend state of the art Model Predictive Control (MPC) approaches to generate safe bipedal walking on slippery surfaces. In this setting, we formulate walking as a trade off between realizing a desired walking velocity and preserving robust foot-ground contact. Exploiting this for- mulation inside MPC, we show that safe walking on various flat terrains can be achieved by compromising three main attributes, i. e. walking velocity tracking, the Zero Moment Point (ZMP) modulation, and the Required Coefficient of Friction (RCoF) regulation. Simulation results show that increasing the walking velocity increases the possibility of slippage, while reducing the slippage possibility conflicts with reducing the tip-over possibility of the contact and vice versa.

mg

link (url) [BibTex]

link (url) [BibTex]

2003


no image
Dynamic movement primitives - A framework for motor control in humans and humanoid robots

Schaal, S.

In The International Symposium on Adaptive Motion of Animals and Machines, Kyoto, Japan, March 4-8, 2003, March 2003, clmc (inproceedings)

Abstract
Sensory-motor integration is one of the key issues in robotics. In this paper, we propose an approach to rhythmic arm movement control that is synchronized with an external signal based on exploiting a simple neural oscillator network. Trajectory generation by the neural oscillator is a biologically inspired method that can allow us to generate a smooth and continuous trajectory. The parameter tuning of the oscillators is used to generate a synchronized movement with wide intervals. We adopted the method for the drumming task as an example task. By using this method, the robot can realize synchronized drumming with wide drumming intervals in real time. The paper also shows the experimental results of drumming by a humanoid robot.

am

link (url) [BibTex]

2003


link (url) [BibTex]


Thumb xl toc image
New electro-optic effect: Sum-frequency generation from optically active liquids in the presence of a dc electric field

Fischer, P., Buckingham, A., Beckwitt, K., Wiersma, D., Wise, F.

PHYSICAL REVIEW LETTERS, 91(17), 2003 (article)

Abstract
We report the observation of sum-frequency signals that depend linearly on an applied electrostatic field and that change sign with the handedness of an optically active solute. This recently predicted chiral electro-optic effect exists in the electric-dipole approximation. The static electric field gives rise to an electric-field-induced sum-frequency signal (an achiral third-order process) that interferes with the chirality-specific sum-frequency at second order. The cross-terms linear in the electrostatic field constitute the effect and may be used to determine the absolute sign of second- and third-order nonlinear-optical susceptibilities in isotropic media.

pf

DOI [BibTex]

DOI [BibTex]


Thumb xl toc image
Chiral and achiral contributions to sum-frequency generation from optically active solutions of binaphthol

Fischer, P., Wise, F., Albrecht, A.

JOURNAL OF PHYSICAL CHEMISTRY A, 107(40):8232-8238, 2003 (article)

Abstract
The nonlinear sum- and difference-frequency generation spectroscopies can be probes of molecular chirality in optically active systems. We present a tensorial analysis of the chirality-specific electric-dipolar sum-frequency-generation susceptibility and the achiral electric-quadrupolar and magnetic-dipolar nonlinearities at second order in isotropic media. The chiral and achiral contributions to the sum-frequency signal from the bulk of optically active solutions of 1,1'-bi-2-naphthol (2,2'-dehydroxy-1,1'-binaphthyl) can be distinguished, and the former dominates. Ab initio computations reveal the dramatic resonance enhancement that the isotropic component of the electric-dipolar three-wave mixing hyperpolarizability experiences. Away from resonance its magnitude rapidly decreases, as-unlike the vector component-it is zero in the static limit. The dispersion of the first hyperpolarizability is computed by a configuration interaction singles sum-over-states approach with explicit regard to the Franck-Condon active vibrational substructure for all resonant electronic states.

pf

DOI [BibTex]

DOI [BibTex]


no image
Bayesian backfitting

D’Souza, A., Vijayakumar, S., Schaal, S.

In Proceedings of the 10th Joint Symposium on Neural Computation (JSNC 2003), Irvine, CA, May 2003, 2003, clmc (inproceedings)

Abstract
We present an algorithm aimed at addressing both computational and analytical intractability of Bayesian regression models which operate in very high-dimensional, usually underconstrained spaces. Several domains of research frequently provide such datasets, including chemometrics [2], and human movement analysis [1]. The literature in nonparametric statistics provides interesting solutions such as Backfitting [3] and Partial Least Squares [4], which are extremely robust and efficient, yet lack a probabilistic interpretation that could place them in the context of current research in statistical learning algorithms that emphasize the estimation of confidence, posterior distributions, and model complexity. In order to achieve numerical robustness and low computational cost, we first derive a novel Bayesian interpretation of Backfitting (BB) as a computationally efficient regression algorithm. BBÕs learning complexity scales linearly with the input dimensionality by decoupling inference among individual input dimensions. We embed BB in an efficient, locally variational model selection mechanism that automatically grows the number of backfitting experts in a mixture-of-experts regression model. We demonstrate the effectiveness of the algorithm in performing principled regularization of model complexity when fitting nonlinear manifolds while avoiding the numerical hazards associated with highly underconstrained problems. We also note that this algorithm appears applicable in various areas of neural computation, e.g., in abstract models of computational neuroscience, or implementations of statistical learning on artificial systems.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Reinforcement learning for humanoid robotics

Peters, J., Vijayakumar, S., Schaal, S.

In IEEE-RAS International Conference on Humanoid Robots (Humanoids2003), Karlsruhe, Germany, Sept.29-30, 2003, clmc (inproceedings)

Abstract
Reinforcement learning offers one of the most general framework to take traditional robotics towards true autonomy and versatility. However, applying reinforcement learning to high dimensional movement systems like humanoid robots remains an unsolved problem. In this paper, we discuss different approaches of reinforcement learning in terms of their applicability in humanoid robotics. Methods can be coarsely classified into three different categories, i.e., greedy methods, `vanilla' policy gradient methods, and natural gradient methods. We discuss that greedy methods are not likely to scale into the domain humanoid robotics as they are problematic when used with function approximation. `Vanilla' policy gradient methods on the other hand have been successfully applied on real-world robots including at least one humanoid robot. We demonstrate that these methods can be significantly improved using the natural policy gradient instead of the regular policy gradient. A derivation of the natural policy gradient is provided, proving that the average policy gradient of Kakade (2002) is indeed the true natural gradient. A general algorithm for estimating the natural gradient, the Natural Actor-Critic algorithm, is introduced. This algorithm converges to the nearest local minimum of the cost function with respect to the Fisher information metric under suitable conditions. The algorithm outperforms non-natural policy gradients by far in a cart-pole balancing evaluation, and for learning nonlinear dynamic motor primitives for humanoid robot control. It offers a promising route for the development of reinforcement learning for truly high dimensionally continuous state-action systems.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Discovering imitation strategies through categorization of multi-cimensional data

Billard, A., Epars, Y., Schaal, S., Cheng, G.

In IEEE International Conference on Intelligent Robots and Systems (IROS 2003), Las Vegas, NV, Oct. 27-31, 2003, clmc (inproceedings)

Abstract
An essential problem of imitation is that of determining Ówhat to imitateÓ, i.e. to determine which of the many features of the demonstration are relevant to the task and which should be reproduced. The strategy followed by the imitator can be modeled as a hierarchical optimization system, which minimizes the discrepancy between two multidimensional datasets. We consider imitation of a manipulation task. To classify across manipulation strategies, we apply a probabilistic analysis to data in Cartesian and joint spaces. We determine a general metric that optimizes the policy of task reproduction, following strategy determination. The model successfully discovers strategies in six different manipulation tasks and controls task reproduction by a full body humanoid robot. or the complete path followed by the demonstrator. We follow a similar taxonomy and apply it to the learning and reproduction of a manipulation task by a humanoid robot. We take the perspective that the features of the movements to imitate are those that appear most frequently, i.e. the invariants in time. The model builds upon previous work [3], [4] and is composed of a hierarchical time delay neural network that extracts invariant features from a manipulation task performed by a human demonstrator. The system analyzes the Carthesian trajectories of the objects and the joint

am

link (url) [BibTex]

link (url) [BibTex]


no image
Scaling reinforcement learning paradigms for motor learning

Peters, J., Vijayakumar, S., Schaal, S.

In Proceedings of the 10th Joint Symposium on Neural Computation (JSNC 2003), Irvine, CA, May 2003, 2003, clmc (inproceedings)

Abstract
Reinforcement learning offers a general framework to explain reward related learning in artificial and biological motor control. However, current reinforcement learning methods rarely scale to high dimensional movement systems and mainly operate in discrete, low dimensional domains like game-playing, artificial toy problems, etc. This drawback makes them unsuitable for application to human or bio-mimetic motor control. In this poster, we look at promising approaches that can potentially scale and suggest a novel formulation of the actor-critic algorithm which takes steps towards alleviating the current shortcomings. We argue that methods based on greedy policies are not likely to scale into high-dimensional domains as they are problematic when used with function approximation Ð a must when dealing with continuous domains. We adopt the path of direct policy gradient based policy improvements since they avoid the problems of unstabilizing dynamics encountered in traditional value iteration based updates. While regular policy gradient methods have demonstrated promising results in the domain of humanoid notor control, we demonstrate that these methods can be significantly improved using the natural policy gradient instead of the regular policy gradient. Based on this, it is proved that KakadeÕs Ôaverage natural policy gradientÕ is indeed the true natural gradient. A general algorithm for estimating the natural gradient, the Natural Actor-Critic algorithm, is introduced. This algorithm converges with probability one to the nearest local minimum in Riemannian space of the cost function. The algorithm outperforms nonnatural policy gradients by far in a cart-pole balancing evaluation, and offers a promising route for the development of reinforcement learning for truly high-dimensionally continuous state-action systems.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning attractor landscapes for learning motor primitives

Ijspeert, A., Nakanishi, J., Schaal, S.

In Advances in Neural Information Processing Systems 15, pages: 1547-1554, (Editors: Becker, S.;Thrun, S.;Obermayer, K.), Cambridge, MA: MIT Press, 2003, clmc (inproceedings)

Abstract
If globally high dimensional data has locally only low dimensional distributions, it is advantageous to perform a local dimensionality reduction before further processing the data. In this paper we examine several techniques for local dimensionality reduction in the context of locally weighted linear regression. As possible candidates, we derive local versions of factor analysis regression, principle component regression, principle component regression on joint distributions, and partial least squares regression. After outlining the statistical bases of these methods, we perform Monte Carlo simulations to evaluate their robustness with respect to violations of their statistical assumptions. One surprising outcome is that locally weighted partial least squares regression offers the best average results, thus outperforming even factor analysis, the theoretically most appealing of our candidate techniques.Ê

am

link (url) [BibTex]

link (url) [BibTex]


no image
Evolution of Fault-tolerant Self-replicating Structures

Righetti, L., Shokur, S., Capcarre, M.

In Advances in Artificial Life, pages: 278-288, Lecture Notes in Computer Science, Springer Berlin Heidelberg, 2003 (inproceedings)

Abstract
Designed and evolved self-replicating structures in cellular automata have been extensively studied in the past as models of Artificial Life. However, CAs, unlike their biological counterpart, are very brittle: any faulty cell usually leads to the complete destruction of any emerging structures, let alone self-replicating structures. A way to design fault-tolerant structures based on error-correcting-code has been presented recently [1], but it required a cumbersome work to be put into practice. In this paper, we get back to the original inspiration for these works, nature, and propose a way to evolve self-replicating structures, faults here being only an idiosyncracy of the environment.

mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Learning from demonstration and adaptation of biped locomotion with dynamical movement primitives

Nakanishi, J., Morimoto, J., Endo, G., Schaal, S., Kawato, M.

In Workshop on Robot Learning by Demonstration, IEEE International Conference on Intelligent Robots and Systems (IROS 2003), Las Vegas, NV, Oct. 27-31, 2003, clmc (inproceedings)

Abstract
In this paper, we report on our research for learning biped locomotion from human demonstration. Our ultimate goal is to establish a design principle of a controller in order to achieve natural human-like locomotion. We suggest dynamical movement primitives as a CPG of a biped robot, an approach we have previously proposed for learning and encoding complex human movements. Demonstrated trajectories are learned through the movement primitives by locally weighted regression, and the frequency of the learned trajectories is adjusted automatically by a novel frequency adaptation algorithm based on phase resetting and entrainment of oscillators. Numerical simulations demonstrate the effectiveness of the proposed locomotion controller.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Movement planning and imitation by shaping nonlinear attractors

Schaal, S.

In Proceedings of the 12th Yale Workshop on Adaptive and Learning Systems, Yale University, New Haven, CT, 2003, clmc (inproceedings)

Abstract
Given the continuous stream of movements that biological systems exhibit in their daily activities, an account for such versatility and creativity has to assume that movement sequences consist of segments, executed either in sequence or with partial or complete overlap. Therefore, a fundamental question that has pervaded research in motor control both in artificial and biological systems revolves around identifying movement primitives (a.k.a. units of actions, basis behaviors, motor schemas, etc.). What are the fundamental building blocks that are strung together, adapted to, and created for ever new behaviors? This paper summarizes results that led to the hypothesis of Dynamic Movement Primitives (DMP). DMPs are units of action that are formalized as stable nonlinear attractor systems. They are useful for autonomous robotics as they are highly flexible in creating complex rhythmic (e.g., locomotion) and discrete (e.g., a tennis swing) behaviors that can quickly be adapted to the inevitable perturbations of a dy-namically changing, stochastic environment. Moreover, DMPs provide a formal framework that also lends itself to investigations in computational neuroscience. A recent finding that allows creating DMPs with the help of well-understood statistical learning methods has elevated DMPs from a more heuristic to a principled modeling approach, and, moreover, created a new foundation for imitation learning. Theoretical insights, evaluations on a humanoid robot, and behavioral and brain imaging data will serve to outline the framework of DMPs for a general approach to motor control and imitation in robotics and biology.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Computational approaches to motor learning by imitation

Schaal, S., Ijspeert, A., Billard, A.

Philosophical Transaction of the Royal Society of London: Series B, Biological Sciences, 358(1431):537-547, 2003, clmc (article)

Abstract
Movement imitation requires a complex set of mechanisms that map an observed movement of a teacher onto one's own movement apparatus. Relevant problems include movement recognition, pose estimation, pose tracking, body correspondence, coordinate transformation from external to egocentric space, matching of observed against previously learned movement, resolution of redundant degrees-of-freedom that are unconstrained by the observation, suitable movement representations for imitation, modularization of motor control, etc. All of these topics by themselves are active research problems in computational and neurobiological sciences, such that their combination into a complete imitation system remains a daunting undertaking - indeed, one could argue that we need to understand the complete perception-action loop. As a strategy to untangle the complexity of imitation, this paper will examine imitation purely from a computational point of view, i.e. we will review statistical and mathematical approaches that have been suggested for tackling parts of the imitation problem, and discuss their merits, disadvantages and underlying principles. Given the focus on action recognition of other contributions in this special issue, this paper will primarily emphasize the motor side of imitation, assuming that a perceptual system has already identified important features of a demonstrated movement and created their corresponding spatial information. Based on the formalization of motor control in terms of control policies and their associated performance criteria, useful taxonomies of imitation learning can be generated that clarify different approaches and future research directions.

am

link (url) [BibTex]

link (url) [BibTex]


Thumb xl teaser 1
Accurate Vision-based Manipulation through Contact Reasoning

Kloss, A., Bauza, M., Wu, J., Tenenbaum, J. B., Rodriguez, A., Bohg, J.

In International Conference on Robotics and Automation, May (inproceedings) Submitted

Abstract
Planning contact interactions is one of the core challenges of many robotic tasks. Optimizing contact locations while taking dynamics into account is computationally costly and in only partially observed environments, executing contact-based tasks often suffers from low accuracy. We present an approach that addresses these two challenges for the problem of vision-based manipulation. First, we propose to disentangle contact from motion optimization. Thereby, we improve planning efficiency by focusing computation on promising contact locations. Second, we use a hybrid approach for perception and state estimation that combines neural networks with a physically meaningful state representation. In simulation and real-world experiments on the task of planar pushing, we show that our method is more efficient and achieves a higher manipulation accuracy than previous vision-based approaches.

am

[BibTex]


[BibTex]