Header logo is


2020


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

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

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

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

ps

link (url) DOI [BibTex]

2020


link (url) DOI [BibTex]


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

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

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

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

dlg ics

link (url) DOI [BibTex]

link (url) DOI [BibTex]


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

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

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

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

dlg

Youtube link (url) DOI [BibTex]

Youtube link (url) DOI [BibTex]


3D Morphable Face Models - Past, Present and Future
3D Morphable Face Models - Past, Present and Future

Egger, B., Smith, W. A. P., Tewari, A., Wuhrer, S., Zollhoefer, M., Beeler, T., Bernard, F., Bolkart, T., Kortylewski, A., Romdhani, S., Theobalt, C., Blanz, V., Vetter, T.

ACM Transactions on Graphics, 39(5), August 2020 (article)

Abstract
In this paper, we provide a detailed survey of 3D Morphable Face Models over the 20 years since they were first proposed. The challenges in building and applying these models, namely capture, modeling, image formation, and image analysis, are still active research topics, and we review the state-of-the-art in each of these areas. We also look ahead, identifying unsolved challenges, proposing directions for future research and highlighting the broad range of current and future applications.

ps

project page pdf preprint DOI [BibTex]

project page pdf preprint DOI [BibTex]


Learning Variable Impedance Control for Contact Sensitive Tasks
Learning Variable Impedance Control for Contact Sensitive Tasks

Bogdanovic, M., Khadiv, M., Righetti, L.

IEEE Robotics and Automation Letters ( Early Access ), IEEE, July 2020 (article)

Abstract
Reinforcement learning algorithms have shown great success in solving different problems ranging from playing video games to robotics. However, they struggle to solve delicate robotic problems, especially those involving contact interactions. Though in principle a policy outputting joint torques should be able to learn these tasks, in practice we see that they have difficulty to robustly solve the problem without any structure in the action space. In this paper, we investigate how the choice of action space can give robust performance in presence of contact uncertainties. We propose to learn a policy that outputs impedance and desired position in joint space as a function of system states without imposing any other structure to the problem. We compare the performance of this approach to torque and position control policies under different contact uncertainties. Extensive simulation results on two different systems, a hopper (floating-base) with intermittent contacts and a manipulator (fixed-base) wiping a table, show that our proposed approach outperforms policies outputting torque or position in terms of both learning rate and robustness to environment uncertainty.

mg

DOI [BibTex]

DOI [BibTex]


Walking Control Based on Step Timing Adaptation
Walking Control Based on Step Timing Adaptation

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

IEEE Transactions on Robotics, 36, pages: 629 - 643, IEEE, June 2020 (article)

Abstract
Step adjustment can improve the gait robustness of biped robots; however, the adaptation of step timing is often neglected as it gives rise to nonconvex problems when optimized over several footsteps. In this article, we argue that it is not necessary to optimize walking over several steps to ensure gait viability and show that it is sufficient to merely select the next step timing and location. Using this insight, we propose a novel walking pattern generator that optimally selects step location and timing at every control cycle. Our approach is computationally simple compared to standard approaches in the literature, yet guarantees that any viable state will remain viable in the future. We propose a swing foot adaptation strategy and integrate the pattern generator with an inverse dynamics controller that does not explicitly control the center of mass nor the foot center of pressure. This is particularly useful for biped robots with limited control authority over their foot center of pressure, such as robots with point feet or passive ankles. Extensive simulations on a humanoid robot with passive ankles demonstrate the capabilities of the approach in various walking situations, including external pushes and foot slippage, and emphasize the importance of step timing adaptation to stabilize walking.

mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Phenomenal Causality and Sensory Realism

Meding, K., Bruijns, S. A., Schölkopf, B., Berens, P., Wichmann, F. A.

i-Perception, 11(3):1-16, June 2020 (article)

ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Learning and Tracking the {3D} Body Shape of Freely Moving Infants from {RGB-D} sequences
Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences

Hesse, N., Pujades, S., Black, M., Arens, M., Hofmann, U., Schroeder, S.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 42(10):2540-2551, 2020 (article)

Abstract
Statistical models of the human body surface are generally learned from thousands of high-quality 3D scans in predefined poses to cover the wide variety of human body shapes and articulations. Acquisition of such data requires expensive equipment, calibration procedures, and is limited to cooperative subjects who can understand and follow instructions, such as adults. We present a method for learning a statistical 3D Skinned Multi-Infant Linear body model (SMIL) from incomplete, low-quality RGB-D sequences of freely moving infants. Quantitative experiments show that SMIL faithfully represents the RGB-D data and properly factorizes the shape and pose of the infants. To demonstrate the applicability of SMIL, we fit the model to RGB-D sequences of freely moving infants and show, with a case study, that our method captures enough motion detail for General Movements Assessment (GMA), a method used in clinical practice for early detection of neurodevelopmental disorders in infants. SMIL provides a new tool for analyzing infant shape and movement and is a step towards an automated system for GMA.

ps

pdf Journal DOI [BibTex]

pdf Journal DOI [BibTex]


General Movement Assessment from videos of computed {3D} infant body models is equally effective compared to conventional {RGB} Video rating
General Movement Assessment from videos of computed 3D infant body models is equally effective compared to conventional RGB Video rating

Schroeder, S., Hesse, N., Weinberger, R., Tacke, U., Gerstl, L., Hilgendorff, A., Heinen, F., Arens, M., Bodensteiner, C., Dijkstra, L. J., Pujades, S., Black, M., Hadders-Algra, M.

Early Human Development, 144, May 2020 (article)

Abstract
Background: General Movement Assessment (GMA) is a powerful tool to predict Cerebral Palsy (CP). Yet, GMA requires substantial training hampering its implementation in clinical routine. This inspired a world-wide quest for automated GMA. Aim: To test whether a low-cost, marker-less system for three-dimensional motion capture from RGB depth sequences using a whole body infant model may serve as the basis for automated GMA. Study design: Clinical case study at an academic neurodevelopmental outpatient clinic. Subjects: Twenty-nine high-risk infants were recruited and assessed at their clinical follow-up at 2-4 month corrected age (CA). Their neurodevelopmental outcome was assessed regularly up to 12-31 months CA. Outcome measures: GMA according to Hadders-Algra by a masked GMA-expert of conventional and computed 3D body model (“SMIL motion”) videos of the same GMs. Agreement between both GMAs was assessed, and sensitivity and specificity of both methods to predict CP at ≥12 months CA. Results: The agreement of the two GMA ratings was substantial, with κ=0.66 for the classification of definitely abnormal (DA) GMs and an ICC of 0.887 (95% CI 0.762;0.947) for a more detailed GM-scoring. Five children were diagnosed with CP (four bilateral, one unilateral CP). The GMs of the child with unilateral CP were twice rated as mildly abnormal. DA-ratings of both videos predicted bilateral CP well: sensitivity 75% and 100%, specificity 88% and 92% for conventional and SMIL motion videos, respectively. Conclusions: Our computed infant 3D full body model is an attractive starting point for automated GMA in infants at risk of CP.

ps

DOI [BibTex]

DOI [BibTex]


no image
Automatic Discovery of Interpretable Planning Strategies

Skirzyński, J., Becker, F., Lieder, F.

May 2020 (article) Submitted

Abstract
When making decisions, people often overlook critical information or are overly swayed by irrelevant information. A common approach to mitigate these biases is to provide decisionmakers, especially professionals such as medical doctors, with decision aids, such as decision trees and flowcharts. Designing effective decision aids is a difficult problem. We propose that recently developed reinforcement learning methods for discovering clever heuristics for good decision-making can be partially leveraged to assist human experts in this design process. One of the biggest remaining obstacles to leveraging the aforementioned methods for improving human decision-making is that the policies they learn are opaque to people. To solve this problem, we introduce AI-Interpret: a general method for transforming idiosyncratic policies into simple and interpretable descriptions. Our algorithm combines recent advances in imitation learning and program induction with a new clustering method for identifying a large subset of demonstrations that can be accurately described by a simple, high-performing decision rule. We evaluate our new AI-Interpret algorithm and employ it to translate information-acquisition policies discovered through metalevel reinforcement learning. The results of three large behavioral experiments showed that the provision of decision rules as flowcharts significantly improved people’s planning strategies and decisions across three different classes of sequential decision problems. Furthermore, a series of ablation studies confirmed that our AI-Interpret algorithm was critical to the discovery of interpretable decision rules and that it is ready to be applied to other reinforcement learning problems. We conclude that the methods and findings presented in this article are an important step towards leveraging automatic strategy discovery to improve human decision-making.

re

Automatic Discovery of Interpretable Planning Strategies The code for our algorithm and the experiments is available [BibTex]


no image
Variational Bayes In Private Settings (VIPS)

Park, M., Foulds, J., Chaudhuri, K., Welling, M.

Journal of Artificial Intelligence Research, 68, pages: 109-157, May 2020 (article)

ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Learning Multi-Human Optical Flow
Learning Multi-Human Optical Flow

Ranjan, A., Hoffmann, D. T., Tzionas, D., Tang, S., Romero, J., Black, M. J.

International Journal of Computer Vision (IJCV), (128):873-890, April 2020 (article)

Abstract
The optical flow of humans is well known to be useful for the analysis of human action. Recent optical flow methods focus on training deep networks to approach the problem. However, the training data used by them does not cover the domain of human motion. Therefore, we develop a dataset of multi-human optical flow and train optical flow networks on this dataset. We use a 3D model of the human body and motion capture data to synthesize realistic flow fields in both single-and multi-person images. We then train optical flow networks to estimate human flow fields from pairs of images. We demonstrate that our trained networks are more accurate than a wide range of top methods on held-out test data and that they can generalize well to real image sequences. The code, trained models and the dataset are available for research.

ps

pdf DOI poster link (url) DOI [BibTex]

pdf DOI poster link (url) DOI [BibTex]


no image
Adaptation and Robust Learning of Probabilistic Movement Primitives

Gomez-Gonzalez, S., Neumann, G., Schölkopf, B., Peters, J.

IEEE Transactions on Robotics, 36(2):366-379, IEEE, March 2020 (article)

ei

arXiv DOI Project Page [BibTex]

arXiv DOI Project Page [BibTex]


no image
Advancing Rational Analysis to the Algorithmic Level

Lieder, F., Griffiths, T. L.

Behavioral and Brain Sciences, 43, E27, March 2020 (article)

Abstract
The commentaries raised questions about normativity, human rationality, cognitive architectures, cognitive constraints, and the scope or resource rational analysis (RRA). We respond to these questions and clarify that RRA is a methodological advance that extends the scope of rational modeling to understanding cognitive processes, why they differ between people, why they change over time, and how they could be improved.

re

Advancing rational analysis to the algorithmic level DOI [BibTex]

Advancing rational analysis to the algorithmic level DOI [BibTex]


Trunk pitch oscillations for energy trade-offs in bipedal running birds and robots
Trunk pitch oscillations for energy trade-offs in bipedal running birds and robots

Drama, Ö., Badri-Spröwitz, A.

Bioinspiration & Biomimetics, 15(3), March 2020 (article)

Abstract
Bipedal animals have diverse morphologies and advanced locomotion abilities. Terrestrial birds, in particular, display agile, efficient, and robust running motion, in which they exploit the interplay between the body segment masses and moment of inertias. On the other hand, most legged robots are not able to generate such versatile and energy-efficient motion and often disregard trunk movements as a means to enhance their locomotion capabilities. Recent research investigated how trunk motions affect the gait characteristics of humans, but there is a lack of analysis across different bipedal morphologies. To address this issue, we analyze avian running based on a spring-loaded inverted pendulum model with a pronograde (horizontal) trunk. We use a virtual point based control scheme and modify the alignment of the ground reaction forces to assess how our control strategy influences the trunk pitch oscillations and energetics of the locomotion. We derive three potential key strategies to leverage trunk pitch motions that minimize either the energy fluctuations of the center of mass or the work performed by the hip and leg. We suggest how these strategies could be used in legged robotics.

dlg

Youtube Video link (url) DOI [BibTex]

Youtube Video link (url) DOI [BibTex]


no image
Learning to Overexert Cognitive Control in a Stroop Task

Bustamante, L., Lieder, F., Musslick, S., Shenhav, A., Cohen, J.

Febuary 2020, Laura Bustamante and Falk Lieder contributed equally to this publication. (article) In revision

Abstract
How do people learn when to allocate how much cognitive control to which task? According to the Learned Value of Control (LVOC) model, people learn to predict the value of alternative control allocations from features of a given situation. This suggests that people may generalize the value of control learned in one situation to other situations with shared features, even when the demands for cognitive control are different. This makes the intriguing prediction that what a person learned in one setting could, under some circumstances, cause them to misestimate the need for, and potentially over-exert control in another setting, even if this harms their performance. To test this prediction, we had participants perform a novel variant of the Stroop task in which, on each trial, they could choose to either name the color (more control-demanding) or read the word (more automatic). However only one of these tasks was rewarded, it changed from trial to trial, and could be predicted by one or more of the stimulus features (the color and/or the word). Participants first learned colors that predicted the rewarded task. Then they learned words that predicted the rewarded task. In the third part of the experiment, we tested how these learned feature associations transferred to novel stimuli with some overlapping features. The stimulus-task-reward associations were designed so that for certain combinations of stimuli the transfer of learned feature associations would incorrectly predict that more highly rewarded task would be color naming, which would require the exertion of control, even though the actually rewarded task was word reading and therefore did not require the engagement of control. Our results demonstrated that participants over-exerted control for these stimuli, providing support for the feature-based learning mechanism described by the LVOC model.

re

Learning to Overexert Cognitive Control in a Stroop Task DOI [BibTex]

Learning to Overexert Cognitive Control in a Stroop Task DOI [BibTex]


no image
DeepMAsED: evaluating the quality of metagenomic assemblies

Mineeva*, O., Rojas-Carulla*, M., Ley, R. E., Schölkopf, B. Y. N. D.

Bioinformatics, 36(10):3011-3017, Febuary 2020, *equal contribution (article)

ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Real Time Trajectory Prediction Using Deep Conditional Generative Models

Gomez-Gonzalez, S., Prokudin, S., Schölkopf, B., Peters, J.

IEEE Robotics and Automation Letters, 5(2):970-976, IEEE, January 2020 (article)

ei ps

arXiv DOI [BibTex]

arXiv DOI [BibTex]


Toward a Formal Theory of Proactivity
Toward a Formal Theory of Proactivity

Lieder, F., Iwama, G.

January 2020 (article) Submitted

Abstract
Beyond merely reacting to their environment and impulses, people have the remarkable capacity to proactively set and pursue their own goals. But the extent to which they leverage this capacity varies widely across people and situations. The goal of this article is to make the mechanisms and variability of proactivity more amenable to rigorous experiments and computational modeling. We proceed in three steps. First, we develop and validate a mathematically precise behavioral measure of proactivity and reactivity that can be applied across a wide range of experimental paradigms. Second, we propose a formal definition of proactivity and reactivity, and develop a computational model of proactivity in the AX Continuous Performance Task (AX-CPT). Third, we develop and test a computational-level theory of meta-control over proactivity in the AX-CPT that identifies three distinct meta-decision-making problems: intention setting, resolving response conflict between intentions and automaticity, and deciding whether to recall context and intentions into working memory. People's response frequencies in the AX-CPT were remarkably well captured by a mixture between the predictions of our models of proactive and reactive control. Empirical data from an experiment varying the incentives and contextual load of an AX-CPT confirmed the predictions of our meta-control model of individual differences in proactivity. Our results suggest that proactivity can be understood in terms of computational models of meta-control. Our model makes additional empirically testable predictions. Future work will extend our models from proactive control in the AX-CPT to proactive goal creation and goal pursuit in the real world.

re

Toward a formal theory of proactivity DOI Project Page [BibTex]


no image
An Adaptive Optimizer for Measurement-Frugal Variational Algorithms

Kübler, J. M., Arrasmith, A., Cincio, L., Coles, P. J.

Quantum, 4, pages: 263, 2020 (article)

ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Counterfactual Mean Embedding

Muandet, K., Kanagawa, M., Saengkyongam, S., Marukatat, S.

Journal of Machine Learning Research, 2020 (article) Accepted

ei

[BibTex]

[BibTex]


Postural Stability in Human Running with Step-down Perturbations: An Experimental and Numerical Study
Postural Stability in Human Running with Step-down Perturbations: An Experimental and Numerical Study

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

2020 (article) In revision

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

dlg

link (url) [BibTex]

link (url) [BibTex]


no image
Causal Discovery from Heterogeneous/Nonstationary Data

Huang, B., Zhang, K., J., Z., Ramsey, J., Sanchez-Romero, R., Glymour, C., Schölkopf, B.

Journal of Machine Learning Research, 21(89):1-53, 2020 (article)

ei

link (url) [BibTex]

link (url) [BibTex]

2009


no image
Efficient Subwindow Search: A Branch and Bound Framework for Object Localization

Lampert, C., Blaschko, M., Hofmann, T.

IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(12):2129-2142, December 2009 (article)

Abstract
Most successful object recognition systems rely on binary classification, deciding only if an object is present or not, but not providing information on the actual object location. To estimate the object‘s location, one can take a sliding window approach, but this strongly increases the computational cost because the classifier or similarity function has to be evaluated over a large set of candidate subwindows. In this paper, we propose a simple yet powerful branch and bound scheme that allows efficient maximization of a large class of quality functions over all possible subimages. It converges to a globally optimal solution typically in linear or even sublinear time, in contrast to the quadratic scaling of exhaustive or sliding window search. We show how our method is applicable to different object detection and image retrieval scenarios. The achieved speedup allows the use of classifiers for localization that formerly were considered too slow for this task, such as SVMs with a spatial pyramid kernel or nearest-neighbor classifiers based on the chi^2 distance. We demonstrate state-of-the-art localization performance of the resulting systems on the UIUC Cars data set, the PASCAL VOC 2006 data set, and in the PASCAL VOC 2007 competition.

ei

PDF Web DOI [BibTex]

2009


PDF Web DOI [BibTex]


no image
Generation of three-dimensional random rotations in fitting and matching problems

Habeck, M.

Computational Statistics, 24(4):719-731, December 2009 (article)

Abstract
An algorithm is developed to generate random rotations in three-dimensional space that follow a probability distribution arising in fitting and matching problems. The rotation matrices are orthogonally transformed into an optimal basis and then parameterized using Euler angles. The conditional distributions of the three Euler angles have a very simple form: the two azimuthal angles can be decoupled by sampling their sum and difference from a von Mises distribution; the cosine of the polar angle is exponentially distributed and thus straighforward to generate. Simulation results are shown and demonstrate the effectiveness of the method. The algorithm is compared to other methods for generating random rotations such as a random walk Metropolis scheme and a Gibbs sampling algorithm recently introduced by Green and Mardia. Finally, the algorithm is applied to a probabilistic version of the Procrustes problem of fitting two point sets and applied in the context of protein structure superposition.

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Adaptive Importance Sampling for Value Function Approximation in Off-policy Reinforcement Learning

Hachiya, H., Akiyama, T., Sugiyama, M., Peters, J.

Neural Networks, 22(10):1399-1410, December 2009 (article)

Abstract
Off-policy reinforcement learning is aimed at efficiently using data samples gathered from a policy that is different from the currently optimized policy. A common approach is to use importance sampling techniques for compensating for the bias of value function estimators caused by the difference between the data-sampling policy and the target policy. However, existing off-policy methods often do not take the variance of the value function estimators explicitly into account and therefore their performance tends to be unstable. To cope with this problem, we propose using an adaptive importance sampling technique which allows us to actively control the trade-off between bias and variance. We further provide a method for optimally determining the trade-off parameter based on a variant of cross-validation. We demonstrate the usefulness of the proposed approach through simulations.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Structured prediction by joint kernel support estimation

Lampert, CH., Blaschko, MB.

Machine Learning, 77(2-3):249-269, December 2009 (article)

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Guest editorial: special issue on structured prediction

Parker, C., Altun, Y., Tadepalli, P.

Machine Learning, 77(2-3):161-164, December 2009 (article)

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
A note on ethical aspects of BCI

Haselager, P., Vlek, R., Hill, J., Nijboer, F.

Neural Networks, 22(9):1352-1357, November 2009 (article)

Abstract
This paper focuses on ethical aspects of BCI, as a research and a clinical tool, that are challenging for practitioners currently working in the field. Specifically, the difficulties involved in acquiring informed consent from locked-in patients are investigated, in combination with an analysis of the shared moral responsibility in BCI teams, and the complications encountered in establishing effective communication with media.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Model Learning with Local Gaussian Process Regression

Nguyen-Tuong, D., Seeger, M., Peters, J.

Advanced Robotics, 23(15):2015-2034, November 2009 (article)

Abstract
Precise models of robot inverse dynamics allow the design of significantly more accurate, energy-efficient and compliant robot control. However, in some cases the accuracy of rigid-body models does not suffice for sound control performance due to unmodeled nonlinearities arising from hydraulic cable dynamics, complex friction or actuator dynamics. In such cases, estimating the inverse dynamics model from measured data poses an interesting alternative. Nonparametric regression methods, such as Gaussian process regression (GPR) or locally weighted projection regression (LWPR), are not as restrictive as parametric models and, thus, offer a more flexible framework for approximating unknown nonlinearities. In this paper, we propose a local approximation to the standard GPR, called local GPR (LGP), for real-time model online learning by combining the strengths of both regression methods, i.e., the high accuracy of GPR and the fast speed of LWPR. The approach is shown to have competitive learning performance for hig h-dimensional data while being sufficiently fast for real-time learning. The effectiveness of LGP is exhibited by a comparison with the state-of-the-art regression techniques, such as GPR, LWPR and ν-support vector regression. The applicability of the proposed LGP method is demonstrated by real-time online learning of the inverse dynamics model for robot model-based control on a Barrett WAM robot arm.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Inferring textual entailment with a probabilistically sound calculus

Harmeling, S.

Natural Language Engineering, 15(4):459-477, October 2009 (article)

Abstract
We introduce a system for textual entailment that is based on a probabilistic model of entailment. The model is defined using a calculus of transformations on dependency trees, which is characterized by the fact that derivations in that calculus preserve the truth only with a certain probability. The calculus is successfully evaluated on the datasets of the PASCAL Challenge on Recognizing Textual Entailment.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Modeling and Visualizing Uncertainty in Gene Expression Clusters using Dirichlet Process Mixtures

Rasmussen, CE., de la Cruz, BJ., Ghahramani, Z., Wild, DL.

IEEE/ACM Transactions on Computational Biology and Bioinformatics, 6(4):615-628, October 2009 (article)

Abstract
Although the use of clustering methods has rapidly become one of the standard computational approaches in the literature of microarray gene expression data, little attention has been paid to uncertainty in the results obtained. Dirichlet process mixture models provide a non-parametric Bayesian alternative to the bootstrap approach to modeling uncertainty in gene expression clustering. Most previously published applications of Bayesian model based clustering methods have been to short time series data. In this paper we present a case study of the application of non-parametric Bayesian clustering methods to the clustering of high-dimensional non-time series gene expression data using full Gaussian covariances. We use the probability that two genes belong to the same cluster in a Dirichlet process mixture model as a measure of the similarity of these gene expression profiles. Conversely, this probability can be used to define a dissimilarity measure, which, for the purposes of visualization, can be input to one of the standard linkage algorithms used for hierarchical clustering. Biologically plausible results are obtained from the Rosetta compendium of expression profiles which extend previously published cluster analyses of this data.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Thermodynamic efficiency of information and heat flow

Allahverdyan, A., Janzing, D., Mahler, G.

Journal of Statistical Mechanics: Theory and Experiment, 2009(09):P09011, September 2009 (article)

Abstract
A basic task of information processing is information transfer (flow). P0 Here we study a pair of Brownian particles each coupled to a thermal bath at temperatures T1 and T2 . The information flow in such a system is defined via the time-shifted mutual information. The information flow nullifies at equilibrium, and its efficiency is defined as the ratio of the flow to the total entropy production in the system. For a stationary state the information flows from higher to lower temperatures, and its efficiency is bounded from above by (max[T1 , T2 ])/(|T1 − T2 |). This upper bound is imposed by the second law and it quantifies the thermodynamic cost for information flow in the present class of systems. It can be reached in the adiabatic situation, where the particles have widely different characteristic times. The efficiency of heat flow—defined as the heat flow over the total amount of dissipated heat—is limited from above by the same factor. There is a complementarity between heat and information flow: the set-up which is most efficient for the former is the least efficient for the latter and vice versa. The above bound for the efficiency can be (transiently) overcome in certain non-stationary situations, but the efficiency is still limited from above. We study yet another measure of information processing (transfer entropy) proposed in the literature. Though this measure does not require any thermodynamic cost, the information flow and transfer entropy are shown to be intimately related for stationary states.

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Does Cognitive Science Need Kernels?

Jäkel, F., Schölkopf, B., Wichmann, F.

Trends in Cognitive Sciences, 13(9):381-388, September 2009 (article)

Abstract
Kernel methods are among the most successful tools in machine learning and are used in challenging data analysis problems in many disciplines. Here we provide examples where kernel methods have proven to be powerful tools for analyzing behavioral data, especially for identifying features in categorization experiments. We also demonstrate that kernel methods relate to perceptrons and exemplar models of categorization. Hence, we argue that kernel methods have neural and psychological plausibility, and theoretical results concerning their behavior are therefore potentially relevant for human category learning. In particular, we believe kernel methods have the potential to provide explanations ranging from the implementational via the algorithmic to the computational level.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Robot Learning

Peters, J., Morimoto, J., Tedrake, R., Roy, N.

IEEE Robotics and Automation Magazine, 16(3):19-20, September 2009 (article)

Abstract
Creating autonomous robots that can learn to act in unpredictable environments has been a long-standing goal of robotics, artificial intelligence, and the cognitive sciences. In contrast, current commercially available industrial and service robots mostly execute fixed tasks and exhibit little adaptability. To bridge this gap, machine learning offers a myriad set of methods, some of which have already been applied with great success to robotics problems. As a result, there is an increasing interest in machine learning and statistics within the robotics community. At the same time, there has been a growth in the learning community in using robots as motivating applications for new algorithms and formalisms. Considerable evidence of this exists in the use of learning in high-profile competitions such as RoboCup and the Defense Advanced Research Projects Agency (DARPA) challenges, and the growing number of research programs funded by governments around the world.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Kernel Methods in Computer Vision

Lampert, CH.

Foundations and Trends in Computer Graphics and Vision, 4(3):193-285, September 2009 (article)

Abstract
Over the last years, kernel methods have established themselves as powerful tools for computer vision researchers as well as for practitioners. In this tutorial, we give an introduction to kernel methods in computer vision from a geometric perspective, introducing not only the ubiquitous support vector machines, but also less known techniques for regression, dimensionality reduction, outlier detection and clustering. Additionally, we give an outlook on very recent, non-classical techniques for the prediction of structure data, for the estimation of statistical dependency and for learning the kernel function itself. All methods are illustrated with examples of successful application from the recent computer vision research literature.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Fast Kernel-Based Independent Component Analysis

Shen, H., Jegelka, S., Gretton, A.

IEEE Transactions on Signal Processing, 57(9):3498-3511, September 2009 (article)

Abstract
Recent approaches to independent component analysis (ICA) have used kernel independence measures to obtain highly accurate solutions, particularly where classical methods experience difficulty (for instance, sources with near-zero kurtosis). FastKICA (fast HSIC-based kernel ICA) is a new optimization method for one such kernel independence measure, the Hilbert-Schmidt Independence Criterion (HSIC). The high computational efficiency of this approach is achieved by combining geometric optimization techniques, specifically an approximate Newton-like method on the orthogonal group, with accurate estimates of the gradient and Hessian based on an incomplete Cholesky decomposition. In contrast to other efficient kernel-based ICA algorithms, FastKICA is applicable to any twice differentiable kernel function. Experimental results for problems with large numbers of sources and observations indicate that FastKICA provides more accurate solutions at a given cost than gradient descent on HSIC. Comparing with other recently published ICA methods, FastKICA is competitive in terms of accuracy, relatively insensitive to local minima when initialized far from independence, and more robust towards outliers. An analysis of the local convergence properties of FastKICA is provided.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Guest editorial: Special issue on robot learning, Part B

Peters, J., Ng, A.

Autonomous Robots, 27(2):91-92, August 2009 (article)

ei

PDF PDF DOI [BibTex]

PDF PDF DOI [BibTex]


no image
Policy Search for Motor Primitives

Peters, J., Kober, J.

KI - Zeitschrift K{\"u}nstliche Intelligenz, 23(3):38-40, August 2009 (article)

Abstract
Many motor skills in humanoid robotics can be learned using parametrized motor primitives from demonstrations. However, most interesting motor learning problems require self-improvement often beyond the reach of current reinforcement learning methods due to the high dimensionality of the state-space. We develop an EM-inspired algorithm applicable to complex motor learning tasks. We compare this algorithm to several well-known parametrized policy search methods and show that it outperforms them. We apply it to motor learning problems and show that it can learn the complex Ball-in-a-Cup task using a real Barrett WAM robot arm.

ei

Web [BibTex]

Web [BibTex]


no image
A neurophysiologically plausible population code model for human contrast discrimination

Goris, R., Wichmann, F., Henning, G.

Journal of Vision, 9(7):1-22, July 2009 (article)

Abstract
The pedestal effect is the improvement in the detectability of a sinusoidal grating in the presence of another grating of the same orientation, spatial frequency, and phase—usually called the pedestal. Recent evidence has demonstrated that the pedestal effect is differently modified by spectrally flat and notch-filtered noise: The pedestal effect is reduced in flat noise but virtually disappears in the presence of notched noise (G. B. Henning & F. A. Wichmann, 2007). Here we consider a network consisting of units whose contrast response functions resemble those of the cortical cells believed to underlie human pattern vision and demonstrate that, when the outputs of multiple units are combined by simple weighted summation—a heuristic decision rule that resembles optimal information combination and produces a contrast-dependent weighting profile—the network produces contrast-discrimination data consistent with psychophysical observations: The pedestal effect is present without noise, reduced in broadband noise, but almost disappears in notched noise. These findings follow naturally from the normalization model of simple cells in primary visual cortex, followed by response-based pooling, and suggest that in processing even low-contrast sinusoidal gratings, the visual system may combine information across neurons tuned to different spatial frequencies and orientations.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Falsificationism and Statistical Learning Theory: Comparing the Popper and Vapnik-Chervonenkis Dimensions

Corfield, D., Schölkopf, B., Vapnik, V.

Journal for General Philosophy of Science, 40(1):51-58, July 2009 (article)

Abstract
We compare Karl Popper’s ideas concerning the falsifiability of a theory with similar notions from the part of statistical learning theory known as VC-theory. Popper’s notion of the dimension of a theory is contrasted with the apparently very similar VC-dimension. Having located some divergences, we discuss how best to view Popper’s work from the perspective of statistical learning theory, either as a precursor or as aiming to capture a different learning activity.

ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Guest editorial: Special issue on robot learning, Part A

Peters, J., Ng, A.

Autonomous Robots, 27(1):1-2, July 2009 (article)

ei

PDF PDF DOI [BibTex]

PDF PDF DOI [BibTex]


no image
A Geometric Approach to Confidence Sets for Ratios: Fieller’s Theorem, Generalizations, and Bootstrap

von Luxburg, U., Franz, V.

Statistica Sinica, 19(3):1095-1117, July 2009 (article)

Abstract
We present a geometric method to determine confidence sets for the ratio E(Y)/E(X) of the means of random variables X and Y. This method reduces the problem of constructing confidence sets for the ratio of two random variables to the problem of constructing confidence sets for the means of one-dimensional random variables. It is valid in a large variety of circumstances. In the case of normally distributed random variables, the so constructed confidence sets coincide with the standard Fieller confidence sets. Generalizations of our construction lead to definitions of exact and conservative confidence sets for very general classes of distributions, provided the joint expectation of (X,Y) exists and the linear combinations of the form aX + bY are well-behaved. Finally, our geometric method allows to derive a very simple bootstrap approach for constructing conservative confidence sets for ratios which perform favorably in certain situations, in particular in the asymmetric heavy-tailed regime.

ei

PDF PDF Web [BibTex]


no image
Center-surround patterns emerge as optimal predictors for human saccade targets

Kienzle, W., Franz, M., Schölkopf, B., Wichmann, F.

Journal of Vision, 9(5:7):1-15, May 2009 (article)

Abstract
The human visual system is foveated, that is, outside the central visual field resolution and acuity drop rapidly. Nonetheless much of a visual scene is perceived after only a few saccadic eye movements, suggesting an effective strategy for selecting saccade targets. It has been known for some time that local image structure at saccade targets influences the selection process. However, the question of what the most relevant visual features are is still under debate. Here we show that center-surround patterns emerge as the optimal solution for predicting saccade targets from their local image structure. The resulting model, a one-layer feed-forward network, is surprisingly simple compared to previously suggested models which assume much more complex computations such as multi-scale processing and multiple feature channels. Nevertheless, our model is equally predictive. Furthermore, our findings are consistent with neurophysiological hardware in the superior colliculus. Bottom-up visual saliency may thus not be computed cortically as has been thought previously.

ei

PDF DOI [BibTex]


no image
Influence of Different Assignment Conditions on the Determination of Symmetric Homo-dimeric Structures with ARIA

Bardiaux, B., Bernard, A., Rieping, W., Habeck, M., Malliavin, TE., Nilges, M.

Proteins, 75(3):569-585, May 2009 (article)

Abstract
The ambiguous restraint for iterative assignment (ARIA) approach for NMR structure calculation is evaluated for symmetric homodimeric proteins by assessing the effect of several data analysis and assignment methods on the structure quality. In particular, we study the effects of network anchoring and spin-diffusion correction. The spin-diffusion correction improves the protein structure quality systematically, whereas network anchoring enhances the assignment efficiency by speeding up the convergence and coping with highly ambiguous data. For some homodimeric folds, network anchoring has been proved essential for unraveling both chain and proton assignment ambiguities.

ei

Web DOI [BibTex]

Web DOI [BibTex]


no image
Beamforming in Noninvasive Brain-Computer Interfaces

Grosse-Wentrup, M., Liefhold, C., Gramann, K., Buss, M.

IEEE Transactions on Biomedical Engineering, 56(4):1209-1219, April 2009 (article)

Abstract
Spatial filtering (SF) constitutes an integral part of building EEG-based brain–computer interfaces (BCIs). Algorithms frequently used for SF, such as common spatial patterns (CSPs) and independent component analysis, require labeled training data for identifying filters that provide information on a subject‘s intention, which renders these algorithms susceptible to overfitting on artifactual EEG components. In this study, beamforming is employed to construct spatial filters that extract EEG sources originating within predefined regions of interest within the brain. In this way, neurophysiological knowledge on which brain regions are relevant for a certain experimental paradigm can be utilized to construct unsupervised spatial filters that are robust against artifactual EEG components. Beamforming is experimentally compared with CSP and Laplacian spatial filtering (LP) in a two-class motor-imagery paradigm. It is demonstrated that beamforming outperforms CSP and LP on noisy datasets, while CSP and beamforming perform almost equally well on datasets with few artifactual trials. It is concluded that beamforming constitutes an alternative method for SF that might be particularly useful for BCIs used in clinical settings, i.e., in an environment where artifact-free datasets are difficult to obtain.

ei

PDF Web DOI [BibTex]

PDF Web DOI [BibTex]


no image
Constructing Sparse Kernel Machines Using Attractors

Lee, D., Jung, K., Lee, J.

IEEE Transactions on Neural Networks, 20(4):721-729, April 2009 (article)

Abstract
In this brief, a novel method that constructs a sparse kernel machine is proposed. The proposed method generates attractors as sparse solutions from a built-in kernel machine via a dynamical system framework. By readjusting the corresponding coefficients and bias terms, a sparse kernel machine that approximates a conventional kernel machine is constructed. The simulation results show that the constructed sparse kernel machine improves the efficiency of testing phase while maintaining comparable test error.

ei

Web DOI [BibTex]

Web DOI [BibTex]