Header logo is


2013


Thumb xl thumb
Branch&Rank for Efficient Object Detection

Lehmann, A., Gehler, P., VanGool, L.

International Journal of Computer Vision, Springer, December 2013 (article)

Abstract
Ranking hypothesis sets is a powerful concept for efficient object detection. In this work, we propose a branch&rank scheme that detects objects with often less than 100 ranking operations. This efficiency enables the use of strong and also costly classifiers like non-linear SVMs with RBF-TeX kernels. We thereby relieve an inherent limitation of branch&bound methods as bounds are often not tight enough to be effective in practice. Our approach features three key components: a ranking function that operates on sets of hypotheses and a grouping of these into different tasks. Detection efficiency results from adaptively sub-dividing the object search space into decreasingly smaller sets. This is inherited from branch&bound, while the ranking function supersedes a tight bound which is often unavailable (except for rather limited function classes). The grouping makes the system effective: it separates image classification from object recognition, yet combines them in a single formulation, phrased as a structured SVM problem. A novel aspect of branch&rank is that a better ranking function is expected to decrease the number of classifier calls during detection. We use the VOC’07 dataset to demonstrate the algorithmic properties of branch&rank.

ps

pdf link (url) [BibTex]

2013


pdf link (url) [BibTex]


Thumb xl thumb
Strong Appearance and Expressive Spatial Models for Human Pose Estimation

Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.

In International Conference on Computer Vision (ICCV), pages: 3487 - 3494 , IEEE, Computer Vision (ICCV), IEEE International Conference on , December 2013 (inproceedings)

Abstract
Typical approaches to articulated pose estimation combine spatial modelling of the human body with appearance modelling of body parts. This paper aims to push the state-of-the-art in articulated pose estimation in two ways. First we explore various types of appearance representations aiming to substantially improve the body part hypotheses. And second, we draw on and combine several recently proposed powerful ideas such as more flexible spatial models as well as image-conditioned spatial models. In a series of experiments we draw several important conclusions: (1) we show that the proposed appearance representations are complementary; (2) we demonstrate that even a basic tree-structure spatial human body model achieves state-of-the-art performance when augmented with the proper appearance representation; and (3) we show that the combination of the best performing appearance model with a flexible image-conditioned spatial model achieves the best result, significantly improving over the state of the art, on the "Leeds Sports Poses'' and "Parse'' benchmarks.

ps

pdf DOI Project Page [BibTex]

pdf DOI Project Page [BibTex]


Thumb xl tro
Extracting Postural Synergies for Robotic Grasping

Romero, J., Feix, T., Ek, C., Kjellstrom, H., Kragic, D.

Robotics, IEEE Transactions on, 29(6):1342-1352, December 2013 (article)

ps

[BibTex]

[BibTex]


Thumb xl zhang
Understanding High-Level Semantics by Modeling Traffic Patterns

Zhang, H., Geiger, A., Urtasun, R.

In International Conference on Computer Vision, pages: 3056-3063, Sydney, Australia, December 2013 (inproceedings)

Abstract
In this paper, we are interested in understanding the semantics of outdoor scenes in the context of autonomous driving. Towards this goal, we propose a generative model of 3D urban scenes which is able to reason not only about the geometry and objects present in the scene, but also about the high-level semantics in the form of traffic patterns. We found that a small number of patterns is sufficient to model the vast majority of traffic scenes and show how these patterns can be learned. As evidenced by our experiments, this high-level reasoning significantly improves the overall scene estimation as well as the vehicle-to-lane association when compared to state-of-the-art approaches. All data and code will be made available upon publication.

avg ps

pdf [BibTex]

pdf [BibTex]


Thumb xl thumb
A Non-parametric Bayesian Network Prior of Human Pose

Lehrmann, A. M., Gehler, P., Nowozin, S.

In Proceedings IEEE Conf. on Computer Vision (ICCV), pages: 1281-1288, IEEE International Conference on Computer Vision, December 2013 (inproceedings)

Abstract
Having a sensible prior of human pose is a vital ingredient for many computer vision applications, including tracking and pose estimation. While the application of global non-parametric approaches and parametric models has led to some success, finding the right balance in terms of flexibility and tractability, as well as estimating model parameters from data has turned out to be challenging. In this work, we introduce a sparse Bayesian network model of human pose that is non-parametric with respect to the estimation of both its graph structure and its local distributions. We describe an efficient sampling scheme for our model and show its tractability for the computation of exact log-likelihoods. We empirically validate our approach on the Human 3.6M dataset and demonstrate superior performance to global models and parametric networks. We further illustrate our model's ability to represent and compose poses not present in the training set (compositionality) and describe a speed-accuracy trade-off that allows realtime scoring of poses.

ps

Project page pdf DOI Project Page [BibTex]

Project page pdf DOI Project Page [BibTex]


Thumb xl jhuang
Towards understanding action recognition

Jhuang, H., Gall, J., Zuffi, S., Schmid, C., Black, M. J.

In IEEE International Conference on Computer Vision (ICCV), pages: 3192-3199, IEEE, Sydney, Australia, December 2013 (inproceedings)

Abstract
Although action recognition in videos is widely studied, current methods often fail on real-world datasets. Many recent approaches improve accuracy and robustness to cope with challenging video sequences, but it is often unclear what affects the results most. This paper attempts to provide insights based on a systematic performance evaluation using thoroughly-annotated data of human actions. We annotate human Joints for the HMDB dataset (J-HMDB). This annotation can be used to derive ground truth optical flow and segmentation. We evaluate current methods using this dataset and systematically replace the output of various algorithms with ground truth. This enables us to discover what is important – for example, should we work on improving flow algorithms, estimating human bounding boxes, or enabling pose estimation? In summary, we find that highlevel pose features greatly outperform low/mid level features; in particular, pose over time is critical, but current pose estimation algorithms are not yet reliable enough to provide this information. We also find that the accuracy of a top-performing action recognition framework can be greatly increased by refining the underlying low/mid level features; this suggests it is important to improve optical flow and human detection algorithms. Our analysis and JHMDB dataset should facilitate a deeper understanding of action recognition algorithms.

ps

Website Errata Poster Paper Slides DOI Project Page Project Page Project Page [BibTex]

Website Errata Poster Paper Slides DOI Project Page Project Page Project Page [BibTex]


Thumb xl impact battery
Probabilistic Object Tracking Using a Range Camera

Wüthrich, M., Pastor, P., Kalakrishnan, M., Bohg, J., Schaal, S.

In IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 3195-3202, IEEE, November 2013 (inproceedings)

Abstract
We address the problem of tracking the 6-DoF pose of an object while it is being manipulated by a human or a robot. We use a dynamic Bayesian network to perform inference and compute a posterior distribution over the current object pose. Depending on whether a robot or a human manipulates the object, we employ a process model with or without knowledge of control inputs. Observations are obtained from a range camera. As opposed to previous object tracking methods, we explicitly model self-occlusions and occlusions from the environment, e.g, the human or robotic hand. This leads to a strongly non-linear observation model and additional dependencies in the Bayesian network. We employ a Rao-Blackwellised particle filter to compute an estimate of the object pose at every time step. In a set of experiments, we demonstrate the ability of our method to accurately and robustly track the object pose in real-time while it is being manipulated by a human or a robot.

am

arXiv Video Code Video DOI Project Page [BibTex]

arXiv Video Code Video DOI Project Page [BibTex]


Thumb xl embs2013
Mixing Decoded Cursor Velocity and Position from an Offline Kalman Filter Improves Cursor Control in People with Tetraplegia

Homer, M., Harrison, M., Black, M. J., Perge, J., Cash, S., Friehs, G., Hochberg, L.

In 6th International IEEE EMBS Conference on Neural Engineering, pages: 715-718, San Diego, November 2013 (inproceedings)

Abstract
Kalman filtering is a common method to decode neural signals from the motor cortex. In clinical research investigating the use of intracortical brain computer interfaces (iBCIs), the technique enabled people with tetraplegia to control assistive devices such as a computer or robotic arm directly from their neural activity. For reaching movements, the Kalman filter typically estimates the instantaneous endpoint velocity of the control device. Here, we analyzed attempted arm/hand movements by people with tetraplegia to control a cursor on a computer screen to reach several circular targets. A standard velocity Kalman filter is enhanced to additionally decode for the cursor’s position. We then mix decoded velocity and position to generate cursor movement commands. We analyzed data, offline, from two participants across six sessions. Root mean squared error between the actual and estimated cursor trajectory improved by 12.2 ±10.5% (pairwise t-test, p<0.05) as compared to a standard velocity Kalman filter. The findings suggest that simultaneously decoding for intended velocity and position and using them both to generate movement commands can improve the performance of iBCIs.

ps

pdf Project Page [BibTex]

pdf Project Page [BibTex]


Thumb xl pic cviu13
Markov Random Field Modeling, Inference & Learning in Computer Vision & Image Understanding: A Survey

Wang, C., Komodakis, N., Paragios, N.

Computer Vision and Image Understanding (CVIU), 117(11):1610-1627, November 2013 (article)

Abstract
In this paper, we present a comprehensive survey of Markov Random Fields (MRFs) in computer vision and image understanding, with respect to the modeling, the inference and the learning. While MRFs were introduced into the computer vision field about two decades ago, they started to become a ubiquitous tool for solving visual perception problems around the turn of the millennium following the emergence of efficient inference methods. During the past decade, a variety of MRF models as well as inference and learning methods have been developed for addressing numerous low, mid and high-level vision problems. While most of the literature concerns pairwise MRFs, in recent years we have also witnessed significant progress in higher-order MRFs, which substantially enhances the expressiveness of graph-based models and expands the domain of solvable problems. This survey provides a compact and informative summary of the major literature in this research topic.

ps

Publishers site pdf [BibTex]

Publishers site pdf [BibTex]


Thumb xl multi modal
3-D Object Reconstruction of Symmetric Objects by Fusing Visual and Tactile Sensing

Illonen, J., Bohg, J., Kyrki, V.

The International Journal of Robotics Research, 33(2):321-341, Sage, October 2013 (article)

Abstract
In this work, we propose to reconstruct a complete 3-D model of an unknown object by fusion of visual and tactile information while the object is grasped. Assuming the object is symmetric, a first hypothesis of its complete 3-D shape is generated. A grasp is executed on the object with a robotic manipulator equipped with tactile sensors. Given the detected contacts between the fingers and the object, the initial full object model including the symmetry parameters can be refined. This refined model will then allow the planning of more complex manipulation tasks. The main contribution of this work is an optimal estimation approach for the fusion of visual and tactile data applying the constraint of object symmetry. The fusion is formulated as a state estimation problem and solved with an iterative extended Kalman filter. The approach is validated experimentally using both artificial and real data from two different robotic platforms.

am

Web DOI Project Page [BibTex]

Web DOI Project Page [BibTex]


Thumb xl implied flow whue
Puppet Flow

Zuffi, S., Black, M. J.

(7), Max Planck Institute for Intelligent Systems, October 2013 (techreport)

Abstract
We introduce Puppet Flow (PF), a layered model describing the optical flow of a person in a video sequence. We consider video frames composed by two layers: a foreground layer corresponding to a person, and background. We model the background as an affine flow field. The foreground layer, being a moving person, requires reasoning about the articulated nature of the human body. We thus represent the foreground layer with the Deformable Structures model (DS), a parametrized 2D part-based human body representation. We call the motion field defined through articulated motion and deformation of the DS model, a Puppet Flow. By exploiting the DS representation, Puppet Flow is a parametrized optical flow field, where parameters are the person's pose, gender and body shape.

ps

pdf Project Page Project Page [BibTex]

pdf Project Page Project Page [BibTex]


Thumb xl ijrr
Vision meets Robotics: The KITTI Dataset

Geiger, A., Lenz, P., Stiller, C., Urtasun, R.

International Journal of Robotics Research, 32(11):1231 - 1237 , Sage Publishing, September 2013 (article)

Abstract
We present a novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research. In total, we recorded 6 hours of traffic scenarios at 10-100 Hz using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras, a Velodyne 3D laser scanner and a high-precision GPS/IMU inertial navigation system. The scenarios are diverse, capturing real-world traffic situations and range from freeways over rural areas to inner-city scenes with many static and dynamic objects. Our data is calibrated, synchronized and timestamped, and we provide the rectified and raw image sequences. Our dataset also contains object labels in the form of 3D tracklets and we provide online benchmarks for stereo, optical flow, object detection and other tasks. This paper describes our recording platform, the data format and the utilities that we provide.

avg ps

pdf DOI [BibTex]

pdf DOI [BibTex]


Thumb xl imgf0006
Human Pose Calculation from Optical Flow Data

Black, M., Loper, M., Romero, J., Zuffi, S.

European Patent Application EP 2843621 , August 2013 (patent)

ps

Google Patents [BibTex]

Google Patents [BibTex]


Thumb xl cover3
Statistics on Manifolds with Applications to Modeling Shape Deformations

Freifeld, O.

Brown University, August 2013 (phdthesis)

Abstract
Statistical models of non-rigid deformable shape have wide application in many fi elds, including computer vision, computer graphics, and biometry. We show that shape deformations are well represented through nonlinear manifolds that are also matrix Lie groups. These pattern-theoretic representations lead to several advantages over other alternatives, including a principled measure of shape dissimilarity and a natural way to compose deformations. Moreover, they enable building models using statistics on manifolds. Consequently, such models are superior to those based on Euclidean representations. We demonstrate this by modeling 2D and 3D human body shape. Shape deformations are only one example of manifold-valued data. More generally, in many computer-vision and machine-learning problems, nonlinear manifold representations arise naturally and provide a powerful alternative to Euclidean representations. Statistics is traditionally concerned with data in a Euclidean space, relying on the linear structure and the distances associated with such a space; this renders it inappropriate for nonlinear spaces. Statistics can, however, be generalized to nonlinear manifolds. Moreover, by respecting the underlying geometry, the statistical models result in not only more e ffective analysis but also consistent synthesis. We go beyond previous work on statistics on manifolds by showing how, even on these curved spaces, problems related to modeling a class from scarce data can be dealt with by leveraging information from related classes residing in di fferent regions of the space. We show the usefulness of our approach with 3D shape deformations. To summarize our main contributions: 1) We de fine a new 2D articulated model -- more expressive than traditional ones -- of deformable human shape that factors body-shape, pose, and camera variations. Its high realism is obtained from training data generated from a detailed 3D model. 2) We defi ne a new manifold-based representation of 3D shape deformations that yields statistical deformable-template models that are better than the current state-of-the- art. 3) We generalize a transfer learning idea from Euclidean spaces to Riemannian manifolds. This work demonstrates the value of modeling manifold-valued data and their statistics explicitly on the manifold. Specifi cally, the methods here provide new tools for shape analysis.

ps

pdf Project Page [BibTex]


Thumb xl thumb
Poselet conditioned pictorial structures

Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.

In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pages: 588 - 595, IEEE, Portland, OR, Conference on Computer Vision and Pattern Recognition (CVRP), June 2013 (inproceedings)

ps

pdf DOI Project Page [BibTex]

pdf DOI Project Page [BibTex]


Thumb xl thumb
Occlusion Patterns for Object Class Detection

Pepik, B., Stark, M., Gehler, P., Schiele, B.

In IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Portland, OR, June 2013 (inproceedings)

Abstract
Despite the success of recent object class recognition systems, the long-standing problem of partial occlusion re- mains a major challenge, and a principled solution is yet to be found. In this paper we leave the beaten path of meth- ods that treat occlusion as just another source of noise – instead, we include the occluder itself into the modelling, by mining distinctive, reoccurring occlusion patterns from annotated training data. These patterns are then used as training data for dedicated detectors of varying sophistica- tion. In particular, we evaluate and compare models that range from standard object class detectors to hierarchical, part-based representations of occluder/occludee pairs. In an extensive evaluation we derive insights that can aid fur- ther developments in tackling the occlusion challenge.

ps

pdf Project Page [BibTex]

pdf Project Page [BibTex]


Thumb xl lost
Lost! Leveraging the Crowd for Probabilistic Visual Self-Localization

(CVPR13 Best Paper Runner-Up)

Brubaker, M. A., Geiger, A., Urtasun, R.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 2013), pages: 3057-3064, IEEE, Portland, OR, June 2013 (inproceedings)

Abstract
In this paper we propose an affordable solution to self- localization, which utilizes visual odometry and road maps as the only inputs. To this end, we present a probabilis- tic model as well as an efficient approximate inference al- gorithm, which is able to utilize distributed computation to meet the real-time requirements of autonomous systems. Because of the probabilistic nature of the model we are able to cope with uncertainty due to noisy visual odometry and inherent ambiguities in the map ( e.g ., in a Manhattan world). By exploiting freely available, community devel- oped maps and visual odometry measurements, we are able to localize a vehicle up to 3m after only a few seconds of driving on maps which contain more than 2,150km of driv- able roads.

avg ps

pdf supplementary project page [BibTex]

pdf supplementary project page [BibTex]


Thumb xl poseregression
Human Pose Estimation using Body Parts Dependent Joint Regressors

Dantone, M., Gall, J., Leistner, C., van Gool, L.

In IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pages: 3041-3048, IEEE, Portland, OR, USA, June 2013 (inproceedings)

Abstract
In this work, we address the problem of estimating 2d human pose from still images. Recent methods that rely on discriminatively trained deformable parts organized in a tree model have shown to be very successful in solving this task. Within such a pictorial structure framework, we address the problem of obtaining good part templates by proposing novel, non-linear joint regressors. In particular, we employ two-layered random forests as joint regressors. The first layer acts as a discriminative, independent body part classifier. The second layer takes the estimated class distributions of the first one into account and is thereby able to predict joint locations by modeling the interdependence and co-occurrence of the parts. This results in a pose estimation framework that takes dependencies between body parts already for joint localization into account and is thus able to circumvent typical ambiguities of tree structures, such as for legs and arms. In the experiments, we demonstrate that our body parts dependent joint regressors achieve a higher joint localization accuracy than tree-based state-of-the-art methods.

ps

pdf DOI Project Page [BibTex]

pdf DOI Project Page [BibTex]


Thumb xl deqingcvpr13b
A fully-connected layered model of foreground and background flow

Sun, D., Wulff, J., Sudderth, E., Pfister, H., Black, M.

In IEEE Conf. on Computer Vision and Pattern Recognition, (CVPR 2013), pages: 2451-2458, Portland, OR, June 2013 (inproceedings)

Abstract
Layered models allow scene segmentation and motion estimation to be formulated together and to inform one another. Traditional layered motion methods, however, employ fairly weak models of scene structure, relying on locally connected Ising/Potts models which have limited ability to capture long-range correlations in natural scenes. To address this, we formulate a fully-connected layered model that enables global reasoning about the complicated segmentations of real objects. Optimization with fully-connected graphical models is challenging, and our inference algorithm leverages recent work on efficient mean field updates for fully-connected conditional random fields. These methods can be implemented efficiently using high-dimensional Gaussian filtering. We combine these ideas with a layered flow model, and find that the long-range connections greatly improve segmentation into figure-ground layers when compared with locally connected MRF models. Experiments on several benchmark datasets show that the method can recover fine structures and large occlusion regions, with good flow accuracy and much lower computational cost than previous locally-connected layered models.

ps

pdf Supplemental Material Project Page Project Page [BibTex]

pdf Supplemental Material Project Page Project Page [BibTex]


Thumb xl submodularity nips
Learning and Optimization with Submodular Functions

Sankaran, B., Ghazvininejad, M., He, X., Kale, D., Cohen, L.

ArXiv, May 2013 (techreport)

Abstract
In many naturally occurring optimization problems one needs to ensure that the definition of the optimization problem lends itself to solutions that are tractable to compute. In cases where exact solutions cannot be computed tractably, it is beneficial to have strong guarantees on the tractable approximate solutions. In order operate under these criterion most optimization problems are cast under the umbrella of convexity or submodularity. In this report we will study design and optimization over a common class of functions called submodular functions. Set functions, and specifically submodular set functions, characterize a wide variety of naturally occurring optimization problems, and the property of submodularity of set functions has deep theoretical consequences with wide ranging applications. Informally, the property of submodularity of set functions concerns the intuitive principle of diminishing returns. This property states that adding an element to a smaller set has more value than adding it to a larger set. Common examples of submodular monotone functions are entropies, concave functions of cardinality, and matroid rank functions; non-monotone examples include graph cuts, network flows, and mutual information. In this paper we will review the formal definition of submodularity; the optimization of submodular functions, both maximization and minimization; and finally discuss some applications in relation to learning and reasoning using submodular functions.

am

arxiv link (url) [BibTex]

arxiv link (url) [BibTex]


Thumb xl featureextraction
Hypothesis Testing Framework for Active Object Detection

Sankaran, B., Atanasov, N., Le Ny, J., Koletschka, T., Pappas, G., Daniilidis, K.

In IEEE International Conference on Robotics and Automation (ICRA), May 2013, clmc (inproceedings)

Abstract
One of the central problems in computer vision is the detection of semantically important objects and the estimation of their pose. Most of the work in object detection has been based on single image processing and its performance is limited by occlusions and ambiguity in appearance and geometry. This paper proposes an active approach to object detection by controlling the point of view of a mobile depth camera. When an initial static detection phase identifies an object of interest, several hypotheses are made about its class and orientation. The sensor then plans a sequence of view-points, which balances the amount of energy used to move with the chance of identifying the correct hypothesis. We formulate an active M-ary hypothesis testing problem, which includes sensor mobility, and solve it using a point-based approximate POMDP algorithm. The validity of our approach is verified through simulation and experiments with real scenes captured by a kinect sensor. The results suggest a significant improvement over static object detection.

am

pdf [BibTex]

pdf [BibTex]


Thumb xl jmiv2012 mut
Unscented Kalman Filtering on Riemannian Manifolds

Soren Hauberg, Francois Lauze, Kim S. Pedersen

Journal of Mathematical Imaging and Vision, 46(1):103-120, Springer Netherlands, May 2013 (article)

ps

Publishers site PDF [BibTex]

Publishers site PDF [BibTex]


Thumb xl thumb hennigk2012 2
Quasi-Newton Methods: A New Direction

Hennig, P., Kiefel, M.

Journal of Machine Learning Research, 14(1):843-865, March 2013 (article)

Abstract
Four decades after their invention, quasi-Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that fit a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newton methods can be interpreted as approximations of Bayesian linear regression under varying prior assumptions. This new notion elucidates some shortcomings of classical algorithms, and lights the way to a novel nonparametric quasi-Newton method, which is able to make more efficient use of available information at computational cost similar to its predecessors.

ei ps pn

website+code pdf link (url) [BibTex]

website+code pdf link (url) [BibTex]


no image
Action and Goal Related Decision Variables Modulate the Competition Between Multiple Potential Targets

Enachescu, V, Christopoulos, Vassilios N, Schrater, P. R., Schaal, S.

In Abstracts of Neural Control of Movement Conference (NCM 2013), February 2013 (inproceedings)

am

[BibTex]

[BibTex]


Thumb xl secretstr
A Quantitative Analysis of Current Practices in Optical Flow Estimation and the Principles Behind Them

Sun, D., Roth, S., Black, M. J.

(CS-10-03), Brown University, Department of Computer Science, January 2013 (techreport)

ps

pdf [BibTex]

pdf [BibTex]


Thumb xl toc image
Hybrid nanocolloids with programmed three-dimensional shape and material composition

Mark, A. G., Gibbs, J. G., Lee, T., Fischer, P.

NATURE MATERIALS, 12(9):802-807, 2013, Max Planck Press Release. (article)

Abstract
Tuning the optical(1,2), electromagnetic(3,4) and mechanical properties of a material requires simultaneous control over its composition and shape(5). This is particularly challenging for complex structures at the nanoscale because surface-energy minimization generally causes small structures to be highly symmetric(5). Here we combine low-temperature shadow deposition with nanoscale patterning to realize nanocolloids with anisotropic three-dimensional shapes, feature sizes down to 20 nm and a wide choice of materials. We demonstrate the versatility of the fabrication scheme by growing three-dimensional hybrid nanostructures that contain several functional materials with the lowest possible symmetry, and by fabricating hundreds of billions of plasmonic nanohelices, which we use as chiral metafluids with record circular dichroism and tunable chiroptical properties.

Max Planck Press Release.

pf

Video - Fabrication of Designer Nanostructures DOI [BibTex]


no image
Optimal control of reaching includes kinematic constraints

Mistry, M., Theodorou, E., Schaal, S., Kawato, M.

Journal of Neurophysiology, 2013, clmc (article)

Abstract
We investigate adaptation under a reaching task with an acceleration-based force field perturbation designed to alter the nominal straight hand trajectory in a potentially benign manner:pushing the hand of course in one direction before subsequently restoring towards the target. In this particular task, an explicit strategy to reduce motor effort requires a distinct deviation from the nominal rectilinear hand trajectory. Rather, our results display a clear directional preference during learning, as subjects adapted perturbed curved trajectories towards their initial baselines. We model this behavior using the framework of stochastic optimal control theory and an objective function that trades-of the discordant requirements of 1) target accuracy, 2) motor effort, and 3) desired trajectory. Our work addresses the underlying objective of a reaching movement, and we suggest that robustness, particularly against internal model uncertainly, is as essential to the reaching task as terminal accuracy and energy effciency.

am

PDF [BibTex]

PDF [BibTex]


Thumb xl thumbiccvsilvia
Estimating Human Pose with Flowing Puppets

Zuffi, S., Romero, J., Schmid, C., Black, M. J.

In IEEE International Conference on Computer Vision (ICCV), pages: 3312-3319, 2013 (inproceedings)

Abstract
We address the problem of upper-body human pose estimation in uncontrolled monocular video sequences, without manual initialization. Most current methods focus on isolated video frames and often fail to correctly localize arms and hands. Inferring pose over a video sequence is advantageous because poses of people in adjacent frames exhibit properties of smooth variation due to the nature of human and camera motion. To exploit this, previous methods have used prior knowledge about distinctive actions or generic temporal priors combined with static image likelihoods to track people in motion. Here we take a different approach based on a simple observation: Information about how a person moves from frame to frame is present in the optical flow field. We develop an approach for tracking articulated motions that "links" articulated shape models of people in adjacent frames trough the dense optical flow. Key to this approach is a 2D shape model of the body that we use to compute how the body moves over time. The resulting "flowing puppets" provide a way of integrating image evidence across frames to improve pose inference. We apply our method on a challenging dataset of TV video sequences and show state-of-the-art performance.

ps

pdf code data DOI Project Page Project Page Project Page [BibTex]

pdf code data DOI Project Page Project Page Project Page [BibTex]


Thumb xl fig1
Chiral Colloidal Molecules And Observation of The Propeller Effect

Schamel, D., Pfeifer, M., Gibbs, J. G., Miksch, B., Mark, A. G., Fischer, P.

JOURNAL OF THE AMERICAN CHEMICAL SOCIETY, 135(33):12353-12359, 2013 (article)

Abstract
Chiral molecules play an important role in biological and chemical processes, but physical effects due to their symmetry-breaking are generally weak. Several physical chiral separation schemes which could potentially be useful, including the propeller effect, have therefore not yet been demonstrated at the molecular scale. However, it has been proposed that complex nonspherical colloidal particles could act as ``colloidal molecules{''} in mesoscopic model systems to permit the visualization of molecular phenomena that are otherwise difficult to observe. Unfortunately, it is difficult to synthesize such colloids because surface minimization generally favors the growth of symmetric particles. Here we demonstrate the production of large numbers of complex colloids with glancing angle physical vapor deposition. We use chiral colloids to demonstrate the Baranova and Zel'dovich (Baranova, N. B.; Zel'dovich, B. Y. Chem. Phys. Lett. 1978, 57, 435) propeller effect: the separation of a racemic mixture by application of a rotating field that couples to the dipole moment of the enantiomers and screw propels them in opposite directions. The handedness of the colloidal suspensions is monitored with circular differential light scattering. An exact solution for the colloid's propulsion is derived, and comparisons between the colloidal system and the corresponding effect at the molecular scale are made.

pf

Video - Nanospropellers DOI [BibTex]

Video - Nanospropellers DOI [BibTex]


Thumb xl screen shot 2015 08 23 at 00.29.36
Fusing visual and tactile sensing for 3-D object reconstruction while grasping

Ilonen, J., Bohg, J., Kyrki, V.

In IEEE International Conference on Robotics and Automation (ICRA), pages: 3547-3554, 2013 (inproceedings)

Abstract
In this work, we propose to reconstruct a complete 3-D model of an unknown object by fusion of visual and tactile information while the object is grasped. Assuming the object is symmetric, a first hypothesis of its complete 3-D shape is generated from a single view. This initial model is used to plan a grasp on the object which is then executed with a robotic manipulator equipped with tactile sensors. Given the detected contacts between the fingers and the object, the full object model including the symmetry parameters can be refined. This refined model will then allow the planning of more complex manipulation tasks. The main contribution of this work is an optimal estimation approach for the fusion of visual and tactile data applying the constraint of object symmetry. The fusion is formulated as a state estimation problem and solved with an iterative extended Kalman filter. The approach is validated experimentally using both artificial and real data from two different robotic platforms.

am

DOI Project Page [BibTex]

DOI Project Page [BibTex]


Thumb xl toc image
Indirect absorption spectroscopy using quantum cascade lasers: mid-infrared refractometry and photothermal spectroscopy

Pfeifer, M., Ruf, A., Fischer, P.

OPTICS EXPRESS, 21(22):25643-25654, 2013 (article)

Abstract
We record vibrational spectra with two indirect schemes that depend on the real part of the index of refraction: mid-infrared refractometry and photothermal spectroscopy. In the former, a quantum cascade laser (QCL) spot is imaged to determine the angles of total internal reflection, which yields the absorption line via a beam profile analysis. In the photothermal measurements, a tunable QCL excites vibrational resonances of a molecular monolayer, which heats the surrounding medium and changes its refractive index. This is observed with a probe laser in the visible. Sub-monolayer sensitivities are demonstrated. (C) 2013 Optical Society of America

pf

DOI [BibTex]


Thumb xl gcpr thumbnail 200 112
A Comparison of Directional Distances for Hand Pose Estimation

Tzionas, D., Gall, J.

In German Conference on Pattern Recognition (GCPR), 8142, pages: 131-141, Lecture Notes in Computer Science, (Editors: Weickert, Joachim and Hein, Matthias and Schiele, Bernt), Springer, 2013 (inproceedings)

Abstract
Benchmarking methods for 3d hand tracking is still an open problem due to the difficulty of acquiring ground truth data. We introduce a new dataset and benchmarking protocol that is insensitive to the accumulative error of other protocols. To this end, we create testing frame pairs of increasing difficulty and measure the pose estimation error separately for each of them. This approach gives new insights and allows to accurately study the performance of each feature or method without employing a full tracking pipeline. Following this protocol, we evaluate various directional distances in the context of silhouette-based 3d hand tracking, expressed as special cases of a generalized Chamfer distance form. An appropriate parameter setup is proposed for each of them, and a comparative study reveals the best performing method in this context.

ps

pdf Supplementary Project Page link (url) DOI Project Page [BibTex]

pdf Supplementary Project Page link (url) DOI Project Page [BibTex]


no image
Dynamical Movement Primitives: Learning Attractor Models for Motor Behaviors

Ijspeert, A., Nakanishi, J., Pastor, P., Hoffmann, H., Schaal, S.

Neural Computation, (25):328-373, 2013, clmc (article)

Abstract
Nonlinear dynamical systems have been used in many disciplines to model complex behaviors, including biological motor control, robotics, perception, economics, traffic prediction, and neuroscience. While often the unexpected emergent behavior of nonlinear systems is the focus of investigations, it is of equal importance to create goal-directed behavior (e.g., stable locomotion from a system of coupled oscillators under perceptual guidance). Modeling goal-directed behavior with nonlinear systems is, however, rather difficult due to the parameter sensitivity of these systems, their complex phase transitions in response to subtle parameter changes, and the difficulty of analyzing and predicting their long-term behavior; intuition and time-consuming parameter tuning play a major role. This letter presents and reviews dynamical movement primitives, a line of research for modeling attractor behaviors of autonomous nonlinear dynamical systems with the help of statistical learning techniques. The essence of our approach is to start with a simple dynamical system, such as a set of linear differential equations, and transform those into a weakly nonlinear system with prescribed attractor dynamics by meansof a learnable autonomous forcing term. Both point attractors and limit cycle attractors of almost arbitrary complexity can be generated. We explain the design principle of our approach and evaluate its properties in several example applications in motor control and robotics.

am

link (url) [BibTex]

link (url) [BibTex]


Thumb xl applied physics cover vol 103 number 21
Plasmonic nanohelix metamaterials with tailorable giant circular dichroism

Gibbs, J. G., Mark, A. G., Eslami, S., Fischer, P.

APPLIED PHYSICS LETTERS, 103(21), 2013, Featured cover article. (article)

Abstract
Plasmonic nanohelix arrays are shown to interact with electromagnetic fields in ways not typically seen with ordinary matter. Chiral metamaterials (CMMs) with feature sizes small with respect to the wavelength of visible light are a promising route to experimentally achieve such phenomena as negative refraction without the need for simultaneously negative e and mu. Here we not only show that giant circular dichroism in the visible is achievable with hexagonally arranged plasmonic nanohelix arrays, but that we can precisely tune the optical activity via morphology and lattice spacing. The discrete dipole approximation is implemented to support experimental data. (C) 2013 AIP Publishing LLC.

Featured cover article.

pf

DOI [BibTex]

DOI [BibTex]


no image
Learning Objective Functions for Manipulation

Kalakrishnan, M., Pastor, P., Righetti, L., Schaal, S.

In 2013 IEEE International Conference on Robotics and Automation, IEEE, Karlsruhe, Germany, 2013 (inproceedings)

Abstract
We present an approach to learning objective functions for robotic manipulation based on inverse reinforcement learning. Our path integral inverse reinforcement learning algorithm can deal with high-dimensional continuous state-action spaces, and only requires local optimality of demonstrated trajectories. We use L 1 regularization in order to achieve feature selection, and propose an efficient algorithm to minimize the resulting convex objective function. We demonstrate our approach by applying it to two core problems in robotic manipulation. First, we learn a cost function for redundancy resolution in inverse kinematics. Second, we use our method to learn a cost function over trajectories, which is then used in optimization-based motion planning for grasping and manipulation tasks. Experimental results show that our method outperforms previous algorithms in high-dimensional settings.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Using Torque Redundancy to Optimize Contact Forces in Legged Robots

Righetti, L., Buchli, J., Mistry, M., Kalakrishnan, M., Schaal, S.

In Redundancy in Robot Manipulators and Multi-Robot Systems, 57, pages: 35-51, Lecture Notes in Electrical Engineering, Springer Berlin Heidelberg, 2013 (incollection)

Abstract
The development of legged robots for complex environments requires controllers that guarantee both high tracking performance and compliance with the environment. More specifically the control of contact interaction with the environment is of crucial importance to ensure stable, robust and safe motions. In the following, we present an inverse dynamics controller that exploits torque redundancy to directly and explicitly minimize any combination of linear and quadratic costs in the contact constraints and in the commands. Such a result is particularly relevant for legged robots as it allows to use torque redundancy to directly optimize contact interactions. For example, given a desired locomotion behavior, it can guarantee the minimization of contact forces to reduce slipping on difficult terrains while ensuring high tracking performance of the desired motion. The proposed controller is very simple and computationally efficient, and most importantly it can greatly improve the performance of legged locomotion on difficult terrains as can be seen in the experimental results.

am mg

link (url) [BibTex]

link (url) [BibTex]


Thumb xl pic cdc iccv13
A Generic Deformation Model for Dense Non-Rigid Surface Registration: a Higher-Order MRF-based Approach

Zeng, Y., Wang, C., Gu, X., Samaras, D., Paragios, N.

In IEEE International Conference on Computer Vision (ICCV), pages: 3360~3367, 2013 (inproceedings)

ps

pdf [BibTex]

pdf [BibTex]


Thumb xl training faces
Random Forests for Real Time 3D Face Analysis

Fanelli, G., Dantone, M., Gall, J., Fossati, A., van Gool, L.

International Journal of Computer Vision, 101(3):437-458, Springer, 2013 (article)

Abstract
We present a random forest-based framework for real time head pose estimation from depth images and extend it to localize a set of facial features in 3D. Our algorithm takes a voting approach, where each patch extracted from the depth image can directly cast a vote for the head pose or each of the facial features. Our system proves capable of handling large rotations, partial occlusions, and the noisy depth data acquired using commercial sensors. Moreover, the algorithm works on each frame independently and achieves real time performance without resorting to parallel computations on a GPU. We present extensive experiments on publicly available, challenging datasets and present a new annotated head pose database recorded using a Microsoft Kinect.

ps

data and code publisher's site pdf DOI Project Page [BibTex]

data and code publisher's site pdf DOI Project Page [BibTex]


Thumb xl humans3tracking
Markerless Motion Capture of Multiple Characters Using Multi-view Image Segmentation

Liu, Y., Gall, J., Stoll, C., Dai, Q., Seidel, H., Theobalt, C.

Transactions on Pattern Analysis and Machine Intelligence, 35(11):2720-2735, 2013 (article)

Abstract
Capturing the skeleton motion and detailed time-varying surface geometry of multiple, closely interacting peoples is a very challenging task, even in a multicamera setup, due to frequent occlusions and ambiguities in feature-to-person assignments. To address this task, we propose a framework that exploits multiview image segmentation. To this end, a probabilistic shape and appearance model is employed to segment the input images and to assign each pixel uniquely to one person. Given the articulated template models of each person and the labeled pixels, a combined optimization scheme, which splits the skeleton pose optimization problem into a local one and a lower dimensional global one, is applied one by one to each individual, followed with surface estimation to capture detailed nonrigid deformations. We show on various sequences that our approach can capture the 3D motion of humans accurately even if they move rapidly, if they wear wide apparel, and if they are engaged in challenging multiperson motions, including dancing, wrestling, and hugging.

ps

data and video pdf DOI Project Page [BibTex]

data and video pdf DOI Project Page [BibTex]


Thumb xl perception
Viewpoint and pose in body-form adaptation

Sekunova, A., Black, M., Parkinson, L., Barton, J. J. S.

Perception, 42(2):176-186, 2013 (article)

Abstract
Faces and bodies are complex structures, perception of which can play important roles in person identification and inference of emotional state. Face representations have been explored using behavioural adaptation: in particular, studies have shown that face aftereffects show relatively broad tuning for viewpoint, consistent with origin in a high-level structural descriptor far removed from the retinal image. Our goals were to determine first, if body aftereffects also showed a degree of viewpoint invariance, and second if they also showed pose invariance, given that changes in pose create even more dramatic changes in the 2-D retinal image. We used a 3-D model of the human body to generate headless body images, whose parameters could be varied to generate different body forms, viewpoints, and poses. In the first experiment, subjects adapted to varying viewpoints of either slim or heavy bodies in a neutral stance, followed by test stimuli that were all front-facing. In the second experiment, we used the same front-facing bodies in neutral stance as test stimuli, but compared adaptation from bodies in the same neutral stance to adaptation with the same bodies in different poses. We found that body aftereffects were obtained over substantial viewpoint changes, with no significant decline in aftereffect magnitude with increasing viewpoint difference between adapting and test images. Aftereffects also showed transfer across one change in pose but not across another. We conclude that body representations may have more viewpoint invariance than faces, and demonstrate at least some transfer across pose, consistent with a high-level structural description. Keywords: aftereffect, shape, face, representation

ps

pdf from publisher abstract pdf link (url) Project Page [BibTex]

pdf from publisher abstract pdf link (url) Project Page [BibTex]


no image
Optimal distribution of contact forces with inverse-dynamics control

Righetti, L., Buchli, J., Mistry, M., Kalakrishnan, M., Schaal, S.

The International Journal of Robotics Research, 32(3):280-298, March 2013 (article)

Abstract
The development of legged robots for complex environments requires controllers that guarantee both high tracking performance and compliance with the environment. More specifically the control of the contact interaction with the environment is of crucial importance to ensure stable, robust and safe motions. In this contribution we develop an inverse-dynamics controller for floating-base robots under contact constraints that can minimize any combination of linear and quadratic costs in the contact constraints and the commands. Our main result is the exact analytical derivation of the controller. Such a result is particularly relevant for legged robots as it allows us to use torque redundancy to directly optimize contact interactions. For example, given a desired locomotion behavior, we can guarantee the minimization of contact forces to reduce slipping on difficult terrains while ensuring high tracking performance of the desired motion. The main advantages of the controller are its simplicity, computational efficiency and robustness to model inaccuracies. We present detailed experimental results on simulated humanoid and quadruped robots as well as a real quadruped robot. The experiments demonstrate that the controller can greatly improve the robustness of locomotion of the robots.1

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl houghforest
Class-Specific Hough Forests for Object Detection

Gall, J., Lempitsky, V.

In Decision Forests for Computer Vision and Medical Image Analysis, pages: 143-157, 11, (Editors: Criminisi, A. and Shotton, J.), Springer, 2013 (incollection)

ps

code Project Page [BibTex]

code Project Page [BibTex]


no image
Learning Task Error Models for Manipulation

Pastor, P., Kalakrishnan, M., Binney, J., Kelly, J., Righetti, L., Sukhatme, G. S., Schaal, S.

In 2013 IEEE Conference on Robotics and Automation, IEEE, Karlsruhe, Germany, 2013 (inproceedings)

Abstract
Precise kinematic forward models are important for robots to successfully perform dexterous grasping and manipulation tasks, especially when visual servoing is rendered infeasible due to occlusions. A lot of research has been conducted to estimate geometric and non-geometric parameters of kinematic chains to minimize reconstruction errors. However, kinematic chains can include non-linearities, e.g. due to cable stretch and motor-side encoders, that result in significantly different errors for different parts of the state space. Previous work either does not consider such non-linearities or proposes to estimate non-geometric parameters of carefully engineered models that are robot specific. We propose a data-driven approach that learns task error models that account for such unmodeled non-linearities. We argue that in the context of grasping and manipulation, it is sufficient to achieve high accuracy in the task relevant state space. We identify this relevant state space using previously executed joint configurations and learn error corrections for those. Therefore, our system is developed to generate subsequent executions that are similar to previous ones. The experiments show that our method successfully captures the non-linearities in the head kinematic chain (due to a counterbalancing spring) and the arm kinematic chains (due to cable stretch) of the considered experimental platform, see Fig. 1. The feasibility of the presented error learning approach has also been evaluated in independent DARPA ARM-S testing contributing to successfully complete 67 out of 72 grasping and manipulation tasks.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl 2013 ivc rkek teaser
Non-parametric hand pose estimation with object context

Romero, J., Kjellström, H., Ek, C. H., Kragic, D.

Image and Vision Computing , 31(8):555 - 564, 2013 (article)

Abstract
In the spirit of recent work on contextual recognition and estimation, we present a method for estimating the pose of human hands, employing information about the shape of the object in the hand. Despite the fact that most applications of human hand tracking involve grasping and manipulation of objects, the majority of methods in the literature assume a free hand, isolated from the surrounding environment. Occlusion of the hand from grasped objects does in fact often pose a severe challenge to the estimation of hand pose. In the presented method, object occlusion is not only compensated for, it contributes to the pose estimation in a contextual fashion; this without an explicit model of object shape. Our hand tracking method is non-parametric, performing a nearest neighbor search in a large database (.. entries) of hand poses with and without grasped objects. The system that operates in real time, is robust to self occlusions, object occlusions and segmentation errors, and provides full hand pose reconstruction from monocular video. Temporal consistency in hand pose is taken into account, without explicitly tracking the hand in the high-dim pose space. Experiments show the non-parametric method to outperform other state of the art regression methods, while operating at a significantly lower computational cost than comparable model-based hand tracking methods.

ps

Publisher site pdf link (url) [BibTex]

Publisher site pdf link (url) [BibTex]

2007


Thumb xl toc image
Frequency-domain displacement sensing with a fiber ring-resonator containing a variable gap

Vollmer, F., Fischer, P.

SENSORS AND ACTUATORS A-PHYSICAL, 134(2):410-413, 2007 (article)

Abstract
Ring-resonators are in general not amenable to strain-free (non-contact) displacement measurements. We show that this limitation may be overcome if the ring-resonator, here a fiber-loop, is designed to contain a gap, such that the light traverses a free-space part between two aligned waveguide ends. Displacements are determined with nanometer sensitivity by measuring the associated changes in the resonance frequencies. Miniaturization should increase the sensitivity of the ring-resonator interferometer. Ring geometries that contain an optical circulator can be used to profile reflective samples. (c) 2006 Elsevier B.V. All rights reserved.

pf

DOI [BibTex]

2007


DOI [BibTex]


no image
Towards Machine Learning of Motor Skills

Peters, J., Schaal, S., Schölkopf, B.

In Proceedings of Autonome Mobile Systeme (AMS), pages: 138-144, (Editors: K Berns and T Luksch), 2007, clmc (inproceedings)

Abstract
Autonomous robots that can adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s, however, made it clear that an approach purely based on reasoning or human insights would not be able to model all the perceptuomotor tasks that a robot should fulfill. Instead, new hope was put in the growing wake of machine learning that promised fully adaptive control algorithms which learn both by observation and trial-and-error. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach to motor skill learning in order to get one step closer towards human-like performance. For doing so, we study two ma jor components for such an approach, i.e., firstly, a theoretically well-founded general approach to representing the required control structures for task representation and execution and, secondly, appropriate learning algorithms which can be applied in this setting.

am ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Reinforcement Learning for Optimal Control of Arm Movements

Theodorou, E., Peters, J., Schaal, S.

In Abstracts of the 37st Meeting of the Society of Neuroscience., Neuroscience, 2007, clmc (inproceedings)

Abstract
Every day motor behavior consists of a plethora of challenging motor skills from discrete movements such as reaching and throwing to rhythmic movements such as walking, drumming and running. How this plethora of motor skills can be learned remains an open question. In particular, is there any unifying computa-tional framework that could model the learning process of this variety of motor behaviors and at the same time be biologically plausible? In this work we aim to give an answer to these questions by providing a computational framework that unifies the learning mechanism of both rhythmic and discrete movements under optimization criteria, i.e., in a non-supervised trial-and-error fashion. Our suggested framework is based on Reinforcement Learning, which is mostly considered as too costly to be a plausible mechanism for learning com-plex limb movement. However, recent work on reinforcement learning with pol-icy gradients combined with parameterized movement primitives allows novel and more efficient algorithms. By using the representational power of such mo-tor primitives we show how rhythmic motor behaviors such as walking, squash-ing and drumming as well as discrete behaviors like reaching and grasping can be learned with biologically plausible algorithms. Using extensive simulations and by using different reward functions we provide results that support the hy-pothesis that Reinforcement Learning could be a viable candidate for motor learning of human motor behavior when other learning methods like supervised learning are not feasible.

am ei

[BibTex]

[BibTex]


no image
Reinforcement learning by reward-weighted regression for operational space control

Peters, J., Schaal, S.

In Proceedings of the 24th Annual International Conference on Machine Learning, pages: 745-750, ICML, 2007, clmc (inproceedings)

Abstract
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-base reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Policy gradient methods for machine learning

Peters, J., Theodorou, E., Schaal, S.

In Proceedings of the 14th INFORMS Conference of the Applied Probability Society, pages: 97-98, Eindhoven, Netherlands, July 9-11, 2007, 2007, clmc (inproceedings)

Abstract
We present an in-depth survey of policy gradient methods as they are used in the machine learning community for optimizing parameterized, stochastic control policies in Markovian systems with respect to the expected reward. Despite having been developed separately in the reinforcement learning literature, policy gradient methods employ likelihood ratio gradient estimators as also suggested in the stochastic simulation optimization community. It is well-known that this approach to policy gradient estimation traditionally suffers from three drawbacks, i.e., large variance, a strong dependence on baseline functions and a inefficient gradient descent. In this talk, we will present a series of recent results which tackles each of these problems. The variance of the gradient estimation can be reduced significantly through recently introduced techniques such as optimal baselines, compatible function approximations and all-action gradients. However, as even the analytically obtainable policy gradients perform unnaturally slow, it required the step from ÔvanillaÕ policy gradient methods towards natural policy gradients in order to overcome the inefficiency of the gradient descent. This development resulted into the Natural Actor-Critic architecture which can be shown to be very efficient in application to motor primitive learning for robotics.

am ei

[BibTex]

[BibTex]


no image
Policy Learning for Motor Skills

Peters, J., Schaal, S.

In Proceedings of 14th International Conference on Neural Information Processing (ICONIP), pages: 233-242, (Editors: Ishikawa, M. , K. Doya, H. Miyamoto, T. Yamakawa), 2007, clmc (inproceedings)

Abstract
Policy learning which allows autonomous robots to adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach policy learning with the goal of an application to motor skill refinement in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, we study policy learning algorithms which can be applied in the general setting of motor skill learning, and, secondly, we study a theoretically well-founded general approach to representing the required control structures for task representation and execution.

am ei

PDF DOI [BibTex]

PDF DOI [BibTex]