Header logo is


2008


Thumb xl learningflow
Learning Optical Flow

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

In European Conf. on Computer Vision, ECCV, 5304, pages: 83-97, LNCS, (Editors: Forsyth, D. and Torr, P. and Zisserman, A.), Springer-Verlag, October 2008 (inproceedings)

Abstract
Assumptions of brightness constancy and spatial smoothness underlie most optical flow estimation methods. In contrast to standard heuristic formulations, we learn a statistical model of both brightness constancy error and the spatial properties of optical flow using image sequences with associated ground truth flow fields. The result is a complete probabilistic model of optical flow. Specifically, the ground truth enables us to model how the assumption of brightness constancy is violated in naturalistic sequences, resulting in a probabilistic model of "brightness inconstancy". We also generalize previous high-order constancy assumptions, such as gradient constancy, by modeling the constancy of responses to various linear filters in a high-order random field framework. These filters are free variables that can be learned from training data. Additionally we study the spatial structure of the optical flow and how motion boundaries are related to image intensity boundaries. Spatial smoothness is modeled using a Steerable Random Field, where spatial derivatives of the optical flow are steered by the image brightness structure. These models provide a statistical motivation for previous methods and enable the learning of all parameters from training data. All proposed models are quantitatively compared on the Middlebury flow dataset.

ps

pdf Springerlink version [BibTex]

2008


pdf Springerlink version [BibTex]


Thumb xl octave
GNU Octave Manual Version 3

John W. Eaton, David Bateman, Soren Hauberg

Network Theory Ltd., October 2008 (book)

ps

Publishers site GNU Octave [BibTex]

Publishers site GNU Octave [BibTex]


no image
Probabilistic Roadmap Method and Real Time Gait Changing Technique Implementation for Travel Time Optimization on a Designed Six-legged Robot

Ahmad, A., Dhang, N.

In pages: 1-5, 39th International Symposium on Robotics (ISR), October 2008 (inproceedings)

Abstract
This paper presents design and development of a six legged robot with a total of 12 degrees of freedom, two in each limb and then an implementation of 'obstacle and undulated terrain-based' probabilistic roadmap method for motion planning of this hexaped which is able to negotiate large undulations as obstacles. The novelty in this implementation is that, it doesnt require the complete view of the robot's configuration space at any given time during the traversal. It generates a map of the area that is in visibility range and finds the best suitable point in that field of view to make it as the next node of the algorithm. A particular category of undulations which are small enough are automatically 'run-over' as a part of the terrain and not considered as obstacles. The traversal between the nodes is optimized by taking the shortest path and the most optimum gait at that instance which the hexaped can assume. This is again a novel approach to have a real time gait changing technique to optimize the travel time. The hexaped limb can swing in the robot's X-Y plane and the lower link of the limb can move in robot's Z plane by an implementation of a four-bar mechanism. A GUI based server 'Yellow Ladybird' eventually which is the name of the hexaped, is made for real time monitoring and communicating to it the final destination co-ordinates.

ps

link (url) [BibTex]


Thumb xl eccv08
The naked truth: Estimating body shape under clothing,

Balan, A., Black, M. J.

In European Conf. on Computer Vision, ECCV, 5304, pages: 15-29, LNCS, (Editors: D. Forsyth and P. Torr and A. Zisserman), Springer-Verlag, Marseilles, France, October 2008 (inproceedings)

Abstract
We propose a method to estimate the detailed 3D shape of a person from images of that person wearing clothing. The approach exploits a model of human body shapes that is learned from a database of over 2000 range scans. We show that the parameters of this shape model can be recovered independently of body pose. We further propose a generalization of the visual hull to account for the fact that observed silhouettes of clothed people do not provide a tight bound on the true 3D shape. With clothed subjects, different poses provide different constraints on the possible underlying 3D body shape. We consequently combine constraints across pose to more accurately estimate 3D body shape in the presence of occluding clothing. Finally we use the recovered 3D shape to estimate the gender of subjects and then employ gender-specific body models to refine our shape estimates. Results on a novel database of thousands of images of clothed and "naked" subjects, as well as sequences from the HumanEva dataset, suggest the method may be accurate enough for biometric shape analysis in video.

ps

pdf pdf with higher quality images Springerlink version YouTube video on applications data slides [BibTex]

pdf pdf with higher quality images Springerlink version YouTube video on applications data slides [BibTex]


Thumb xl screen shot 2012 06 06 at 11.28.04 am
Infinite Kernel Learning

Gehler, P., Nowozin, S.

(178), Max Planck Institute, octomber 2008 (techreport)

ps

project page pdf [BibTex]

project page pdf [BibTex]


Thumb xl jnm
A non-parametric Bayesian alternative to spike sorting

Wood, F., Black, M. J.

J. Neuroscience Methods, 173(1):1–12, August 2008 (article)

Abstract
The analysis of extra-cellular neural recordings typically begins with careful spike sorting and all analysis of the data then rests on the correctness of the resulting spike trains. In many situations this is unproblematic as experimental and spike sorting procedures often focus on well isolated units. There is evidence in the literature, however, that errors in spike sorting can occur even with carefully collected and selected data. Additionally, chronically implanted electrodes and arrays with fixed electrodes cannot be easily adjusted to provide well isolated units. In these situations, multiple units may be recorded and the assignment of waveforms to units may be ambiguous. At the same time, analysis of such data may be both scientifically important and clinically relevant. In this paper we address this issue using a novel probabilistic model that accounts for several important sources of uncertainty and error in spike sorting. In lieu of sorting neural data to produce a single best spike train, we estimate a probabilistic model of spike trains given the observed data. We show how such a distribution over spike sortings can support standard neuroscientific questions while providing a representation of uncertainty in the analysis. As a representative illustration of the approach, we analyzed primary motor cortical tuning with respect to hand movement in data recorded with a chronic multi-electrode array in non-human primates.We found that the probabilistic analysis generally agrees with human sorters but suggests the presence of tuned units not detected by humans.

ps

pdf preprint pdf from publisher PubMed [BibTex]

pdf preprint pdf from publisher PubMed [BibTex]


Thumb xl thumb screen shot 2012 10 06 at 12.23.39 pm
Dynamic time warping for binocular hand tracking and reconstruction

Romero, J., Kragic, D., Kyrki, V., Argyros, A.

In IEEE International Conference on Robotics and Automation,ICRA, pages: 2289 -2294, May 2008 (inproceedings)

ps

Pdf [BibTex]

Pdf [BibTex]


no image
Learning to control in operational space

Peters, J., Schaal, S.

International Journal of Robotics Research, 27, pages: 197-212, 2008, clmc (article)

Abstract
One of the most general frameworks for phrasing control problems for complex, redundant robots is operational space control. However, while this framework is of essential importance for robotics and well-understood from an analytical point of view, it can be prohibitively hard to achieve accurate control in face of modeling errors, which are inevitable in com- plex robots, e.g., humanoid robots. In this paper, we suggest a learning approach for opertional space control as a direct inverse model learning problem. A first important insight for this paper is that a physically cor- rect solution to the inverse problem with redundant degrees-of-freedom does exist when learning of the inverse map is performed in a suitable piecewise linear way. The second crucial component for our work is based on the insight that many operational space controllers can be understood in terms of a constrained optimal control problem. The cost function as- sociated with this optimal control problem allows us to formulate a learn- ing algorithm that automatically synthesizes a globally consistent desired resolution of redundancy while learning the operational space controller. From the machine learning point of view, this learning problem corre- sponds to a reinforcement learning problem that maximizes an immediate reward. We employ an expectation-maximization policy search algorithm in order to solve this problem. Evaluations on a three degrees of freedom robot arm are used to illustrate the suggested approach. The applica- tion to a physically realistic simulator of the anthropomorphic SARCOS Master arm demonstrates feasibility for complex high degree-of-freedom robots. We also show that the proposed method works in the setting of learning resolved motion rate control on real, physical Mitsubishi PA-10 medical robotics arm.

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl pointclickimagesmall2
Neural control of computer cursor velocity by decoding motor cortical spiking activity in humans with tetraplegia

(J. Neural Engineering Highlights of 2008 Collection)

Kim, S., Simeral, J., Hochberg, L., Donoghue, J. P., Black, M. J.

J. Neural Engineering, 5, pages: 455–476, 2008 (article)

Abstract
Computer-mediated connections between human motor cortical neurons and assistive devices promise to improve or restore lost function in people with paralysis. Recently, a pilot clinical study of an intracortical neural interface system demonstrated that a tetraplegic human was able to obtain continuous two-dimensional control of a computer cursor using neural activity recorded from his motor cortex. This control, however, was not sufficiently accurate for reliable use in many common computer control tasks. Here, we studied several central design choices for such a system including the kinematic representation for cursor movement, the decoding method that translates neuronal ensemble spiking activity into a control signal and the cursor control task used during training for optimizing the parameters of the decoding method. In two tetraplegic participants, we found that controlling a cursor’s velocity resulted in more accurate closed-loop control than controlling its position directly and that cursor velocity control was achieved more rapidly than position control. Control quality was further improved over conventional linear filters by using a probabilistic method, the Kalman filter, to decode human motor cortical activity. Performance assessment based on standard metrics used for the evaluation of a wide range of pointing devices demonstrated significantly improved cursor control with velocity rather than position decoding.

ps

pdf preprint pdf from publisher [BibTex]

pdf preprint pdf from publisher [BibTex]


no image
Adaptation to a sub-optimal desired trajectory

M. Mistry, E. A. G. L. T. Y. S. S. M. K.

Advances in Computational Motor Control VII, Symposium at the Society for Neuroscience Meeting, Washington DC, 2008, 2008, clmc (article)

am

PDF [BibTex]

PDF [BibTex]


no image
Human movement generation based on convergent flow fields: A computational model and a behavioral experiment

Hoffmann, H., Schaal, S.

In Advances in Computational Motor Control VII, Symposium at the Society for Neuroscience Meeting, Washington DC, 2008, 2008, clmc (inproceedings)

am

link (url) [BibTex]

link (url) [BibTex]


Thumb xl woodtr
Incremental nonparametric Bayesian regression

Wood, F., Grollman, D. H., Heller, K. A., Jenkins, O. C., Black, M. J.

(CS-08-07), Brown University, Department of Computer Science, 2008 (techreport)

ps

pdf [BibTex]

pdf [BibTex]


Thumb xl jmiv08brownian
Brownian Warps for Non-Rigid Registration

Mads Nielsen, Peter Johansen, Andrew Jackson, Benny Lautrup, Soren Hauberg

Journal of Mathematical Imaging and Vision, 31, pages: 221-231, Springer Netherlands, 2008 (article)

ps

Publishers site PDF [BibTex]

Publishers site PDF [BibTex]


Thumb xl thumb screen shot 2012 10 06 at 12.28.24 pm
Simultaneous Visual Recognition of Manipulation Actions and Manipulated Objects

Kjellström, H., Romero, J., Martinez, D., Kragic, D.

In European Conference on Computer Vision, ECCV, pages: 336-349, 2008 (inproceedings)

ps

Pdf [BibTex]

Pdf [BibTex]


no image
Tuning analysis of motor cortical neurons in a person with paralysis during performance of visually instructed cursor control tasks

Kim, S., Simeral, J. D., Hochberg, L. R., Truccolo, W., Donoghue, J., Friehs, G. M., Black, M. J.

2008 Abstract Viewer and Itinerary Planner, Society for Neuroscience, Washington, DC, 2008, Online (conference)

ps

[BibTex]

[BibTex]


no image
Operational space control: A theoretical and emprical comparison

Nakanishi, J., Cory, R., Mistry, M., Peters, J., Schaal, S.

International Journal of Robotics Research, 27(6):737-757, 2008, clmc (article)

Abstract
Dexterous manipulation with a highly redundant movement system is one of the hallmarks of hu- man motor skills. From numerous behavioral studies, there is strong evidence that humans employ compliant task space control, i.e., they focus control only on task variables while keeping redundant degrees-of-freedom as compliant as possible. This strategy is robust towards unknown disturbances and simultaneously safe for the operator and the environment. The theory of operational space con- trol in robotics aims to achieve similar performance properties. However, despite various compelling theoretical lines of research, advanced operational space control is hardly found in actual robotics imple- mentations, in particular new kinds of robots like humanoids and service robots, which would strongly profit from compliant dexterous manipulation. To analyze the pros and cons of different approaches to operational space control, this paper focuses on a theoretical and empirical evaluation of different methods that have been suggested in the literature, but also some new variants of operational space controllers. We address formulations at the velocity, acceleration and force levels. First, we formulate all controllers in a common notational framework, including quaternion-based orientation control, and discuss some of their theoretical properties. Second, we present experimental comparisons of these approaches on a seven-degree-of-freedom anthropomorphic robot arm with several benchmark tasks. As an aside, we also introduce a novel parameter estimation algorithm for rigid body dynamics, which ensures physical consistency, as this issue was crucial for our successful robot implementations. Our extensive empirical results demonstrate that one of the simplified acceleration-based approaches can be advantageous in terms of task performance, ease of parameter tuning, and general robustness and compliance in face of inevitable modeling errors.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields

Park, D., Hoffmann, H., Pastor, P., Schaal, S.

In IEEE International Conference on Humanoid Robots, 2008., 2008, clmc (inproceedings)

am

PDF [BibTex]

PDF [BibTex]


Thumb xl screen shot 2012 06 06 at 11.28.04 am
Infinite Kernel Learning

Gehler, P., Nowozin, S.

In Proceedings of NIPS 2008 Workshop on "Kernel Learning: Automatic Selection of Optimal Kernels", 2008 (inproceedings)

ps

project page pdf [BibTex]

project page pdf [BibTex]


Thumb xl jmiv08theater
An Efficient Algorithm for Modelling Duration in Hidden Markov Models, with a Dramatic Application

Soren Hauberg, Jakob Sloth

Journal of Mathematical Imaging and Vision, 31, pages: 165-170, Springer Netherlands, 2008 (article)

ps

Publishers site Paper site PDF [BibTex]

Publishers site Paper site PDF [BibTex]


Thumb xl thumb screen shot 2012 10 06 at 12.29.08 pm
Visual Recognition of Grasps for Human-to-Robot Mapping

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

In IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS, pages: 3192-3199, 2008 (inproceedings)

ps

Pdf [BibTex]

Pdf [BibTex]


no image
More than two years of intracortically-based cursor control via a neural interface system

Hochberg, L. R., Simeral, J. D., Kim, S., Stein, J., Friehs, G. M., Black, M. J., Donoghue, J. P.

2008 Abstract Viewer and Itinerary Planner, Society for Neuroscience, Washington, DC, 2008, Online (conference)

ps

[BibTex]

[BibTex]


no image
The dual role of uncertainty in force field learning

Mistry, M., Theodorou, E., Hoffmann, H., Schaal, S.

In Abstracts of the Eighteenth Annual Meeting of Neural Control of Movement (NCM), Naples, Florida, April 29-May 4, 2008, clmc (inproceedings)

Abstract
Force field experiments have been a successful paradigm for studying the principles of planning, execution, and learning in human arm movements. Subjects have been shown to cope with the disturbances generated by force fields by learning internal models of the underlying dynamics to predict disturbance effects or by increasing arm impedance (via co-contraction) if a predictive approach becomes infeasible. Several studies have addressed the issue uncertainty in force field learning. Scheidt et al. demonstrated that subjects exposed to a viscous force field of fixed structure but varying strength (randomly changing from trial to trial), learn to adapt to the mean disturbance, regardless of the statistical distribution. Takahashi et al. additionally show a decrease in strength of after-effects after learning in the randomly varying environment. Thus they suggest that the nervous system adopts a dual strategy: learning an internal model of the mean of the random environment, while simultaneously increasing arm impedance to minimize the consequence of errors. In this study, we examine what role variance plays in the learning of uncertain force fields. We use a 7 degree-of-freedom exoskeleton robot as a manipulandum (Sarcos Master Arm, Sarcos, Inc.), and apply a 3D viscous force field of fixed structure and strength randomly selected from trial to trial. Additionally, in separate blocks of trials, we alter the variance of the randomly selected strength multiplier (while keeping a constant mean). In each block, after sufficient learning has occurred, we apply catch trials with no force field and measure the strength of after-effects. As expected in higher variance cases, results show increasingly smaller levels of after-effects as the variance is increased, thus implying subjects choose the robust strategy of increasing arm impedance to cope with higher levels of uncertainty. Interestingly, however, subjects show an increase in after-effect strength with a small amount of variance as compared to the deterministic (zero variance) case. This result implies that a small amount of variability aides in internal model formation, presumably a consequence of the additional amount of exploration conducted in the workspace of the task.

am

[BibTex]

[BibTex]


no image
Dynamic movement primitives for movement generation motivated by convergent force fields in frog

Hoffmann, H., Pastor, P., Schaal, S.

In Adaptive Motion of Animals and Machines (AMAM), 2008, clmc (inproceedings)

am

PDF [BibTex]

PDF [BibTex]


no image
Decoding of reach and grasp from MI population spiking activity using a low-dimensional model of hand and arm posture

Yadollahpour, P., Shakhnarovich, G., Vargas-Irwin, C., Donoghue, J. P., Black, M. J.

2008 Abstract Viewer and Itinerary Planner, Society for Neuroscience, Washington, DC, 2008, Online (conference)

ps

[BibTex]

[BibTex]


no image
Efficient inverse kinematics algorithms for highdimensional movement systems

Tevatia, G., Schaal, S.

CLMC Technical Report: TR-CLMC-2008-1, 2008, clmc (techreport)

Abstract
Real-time control of the endeffector of a humanoid robot in external coordinates requires computationally efficient solutions of the inverse kinematics problem. In this context, this paper investigates methods of resolved motion rate control (RMRC) that employ optimization criteria to resolve kinematic redundancies. In particular we focus on two established techniques, the pseudo inverse with explicit optimization and the extended Jacobian method. We prove that the extended Jacobian method includes pseudo-inverse methods as a special solution. In terms of computational complexity, however, pseudo-inverse and extended Jacobian differ significantly in favor of pseudo-inverse methods. Employing numerical estimation techniques, we introduce a computationally efficient version of the extended Jacobian with performance comparable to the original version. Our results are illustrated in simulation studies with a multiple degree-offreedom robot, and were evaluated on an actual 30 degree-of-freedom full-body humanoid robot.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Behavioral experiments on reinforcement learning in human motor control

Hoffmann, H., Theodorou, E., Schaal, S.

In Abstracts of the Eighteenth Annual Meeting of Neural Control of Movement (NCM), Naples, Florida, April 29-May 4, 2008, clmc (inproceedings)

Abstract
Reinforcement learning (RL) - learning solely based on reward or cost feedback - is widespread in robotics control and has been also suggested as computational model for human motor control. In human motor control, however, hardly any experiment studied reinforcement learning. Here, we study learning based on visual cost feedback in a reaching task and did three experiments: (1) to establish a simple enough experiment for RL, (2) to study spatial localization of RL, and (3) to study the dependence of RL on the cost function. In experiment (1), subjects sit in front of a drawing tablet and look at a screen onto which the drawing pen's position is projected. Beginning from a start point, their task is to move with the pen through a target point presented on screen. Visual feedback about the pen's position is given only before movement onset. At the end of a movement, subjects get visual feedback only about the cost of this trial. We choose as cost the squared distance between target and virtual pen position at the target line. Above a threshold value, the cost was fixed at this value. In the mapping of the pen's position onto the screen, we added a bias (unknown to subject) and Gaussian noise. As result, subjects could learn the bias, and thus, showed reinforcement learning. In experiment (2), we randomly altered the target position between three different locations (three different directions from start point: -45, 0, 45). For each direction, we chose a different bias. As result, subjects learned all three bias values simultaneously. Thus, RL can be spatially localized. In experiment (3), we varied the sensitivity of the cost function by multiplying the squared distance with a constant value C, while keeping the same cut-off threshold. As in experiment (2), we had three target locations. We assigned to each location a different C value (this assignment was randomized between subjects). Since subjects learned the three locations simultaneously, we could directly compare the effect of the different cost functions. As result, we found an optimal C value; if C was too small (insensitive cost), learning was slow; if C was too large (narrow cost valley), the exploration time was longer and learning delayed. Thus, reinforcement learning in human motor control appears to be sen

am

[BibTex]

[BibTex]


no image
Movement generation by learning from demonstration and generalization to new targets

Pastor, P., Hoffmann, H., Schaal, S.

In Adaptive Motion of Animals and Machines (AMAM), 2008, clmc (inproceedings)

am

PDF [BibTex]

PDF [BibTex]


no image
Combining dynamic movement primitives and potential fields for online obstacle avoidance

Park, D., Hoffmann, H., Schaal, S.

In Adaptive Motion of Animals and Machines (AMAM), Cleveland, Ohio, 2008, 2008, clmc (inproceedings)

am

link (url) [BibTex]

link (url) [BibTex]


no image
A library for locally weighted projection regression

Klanke, S., Vijayakumar, S., Schaal, S.

Journal of Machine Learning Research, 9, pages: 623-626, 2008, clmc (article)

Abstract
In this paper we introduce an improved implementation of locally weighted projection regression (LWPR), a supervised learning algorithm that is capable of handling high-dimensional input data. As the key features, our code supports multi-threading, is available for multiple platforms, and provides wrappers for several programming languages.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Neural activity in the motor cortex of humans with tetraplegia

Donoghue, J., Simeral, J., Black, M., Kim, S., Truccolo, W., Hochberg, L.

AREADNE Research in Encoding And Decoding of Neural Ensembles, June, Santorini, Greece, 2008 (conference)

ps

[BibTex]

[BibTex]


no image
Computational model for movement learning under uncertain cost

Theodorou, E., Hoffmann, H., Mistry, M., Schaal, S.

In Abstracts of the Society of Neuroscience Meeting (SFN 2008), Washington, DC 2008, 2008, clmc (inproceedings)

Abstract
Stochastic optimal control is a framework for computing control commands that lead to an optimal behavior under a given cost. Despite the long history of optimal control in engineering, it has been only recently applied to describe human motion. So far, stochastic optimal control has been mainly used in tasks that are already learned, such as reaching to a target. For learning, however, there are only few cases where optimal control has been applied. The main assumptions of stochastic optimal control that restrict its application to tasks after learning are the a priori knowledge of (1) a quadratic cost function (2) a state space model that captures the kinematics and/or dynamics of musculoskeletal system and (3) a measurement equation that models the proprioceptive and/or exteroceptive feedback. Under these assumptions, a sequence of control gains is computed that is optimal with respect to the prespecified cost function. In our work, we relax the assumption of the a priori known cost function and provide a computational framework for modeling tasks that involve learning. Typically, a cost function consists of two parts: one part that models the task constraints, like squared distance to goal at movement endpoint, and one part that integrates over the squared control commands. In learning a task, the first part of this cost function will be adapted. We use an expectation-maximization scheme for learning: the expectation step optimizes the task constraints through gradient descent of a reward function and the maximizing step optimizes the control commands. Our computational model is tested and compared with data given from a behavioral experiment. In this experiment, subjects sit in front of a drawing tablet and look at a screen onto which the drawing-pen's position is projected. Beginning from a start point, their task is to move with the pen through a target point presented on screen. Visual feedback about the pen's position is given only before movement onset. At the end of a movement, subjects get visual feedback only about the cost of this trial. In the mapping of the pen's position onto the screen, we added a bias (unknown to subject) and Gaussian noise. Therefore the cost is a function of this bias. The subjects were asked to reach to the target and minimize this cost over trials. In this behavioral experiment, subjects could learn the bias and thus showed reinforcement learning. With our computational model, we could model the learning process over trials. Particularly, the dependence on parameters of the reward function (Gaussian width) and the modulation of movement variance over time were similar in experiment and model.

am

[BibTex]

[BibTex]


no image
Optimization strategies in human reinforcement learning

Hoffmann, H., Theodorou, E., Schaal, S.

Advances in Computational Motor Control VII, Symposium at the Society for Neuroscience Meeting, Washington DC, 2008, 2008, clmc (article)

am

PDF [BibTex]

PDF [BibTex]


no image
A Bayesian approach to empirical local linearizations for robotics

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

In International Conference on Robotics and Automation (ICRA2008), Pasadena, CA, USA, May 19-23, 2008, 2008, clmc (inproceedings)

Abstract
Local linearizations are ubiquitous in the control of robotic systems. Analytical methods, if available, can be used to obtain the linearization, but in complex robotics systems where the the dynamics and kinematics are often not faithfully obtainable, empirical linearization may be preferable. In this case, it is important to only use data for the local linearization that lies within a ``reasonable'' linear regime of the system, which can be defined from the Hessian at the point of the linearization -- a quantity that is not available without an analytical model. We introduce a Bayesian approach to solve statistically what constitutes a ``reasonable'' local regime. We approach this problem in the context local linear regression. In contrast to previous locally linear methods, we avoid cross-validation or complex statistical hypothesis testing techniques to find the appropriate local regime. Instead, we treat the parameters of the local regime probabilistically and use approximate Bayesian inference for their estimation. This approach results in an analytical set of iterative update equations that are easily implemented on real robotics systems for real-time applications. As in other locally weighted regressions, our algorithm also lends itself to complete nonlinear function approximation for learning empirical internal models. We sketch the derivation of our Bayesian method and provide evaluations on synthetic data and actual robot data where the analytical linearization was known.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Do humans plan continuous trajectories in kinematic coordinates?

Hoffmann, H., Schaal, S.

In Abstracts of the Society of Neuroscience Meeting (SFN 2008), Washington, DC 2008, 2008, clmc (inproceedings)

Abstract
The planning and execution of human arm movements is still unresolved. An ongoing controversy is whether we plan a movement in kinematic coordinates and convert these coordinates with an inverse internal model into motor commands (like muscle activation) or whether we combine a few muscle synergies or equilibrium points to move a hand, e.g., between two targets. The first hypothesis implies that a planner produces a desired end-effector position for all time points; the second relies on the dynamics of the muscular-skeletal system for a given control command to produce a continuous end-effector trajectory. To distinguish between these two possibilities, we use a visuomotor adaptation experiment. Subjects moved a pen on a graphics tablet and observed the pen's mapped position onto a screen (subjects quickly adapted to this mapping). The task was to move a cursor between two points in a given time window. In the adaptation test, we manipulated the velocity profile of the cursor feedback such that the shape of the trajectories remained unchanged (for straight paths). If humans would use a kinematic plan and map at each time the desired end-effector position onto control commands, subjects should adapt to the above manipulation. In a similar experiment, Wolpert et al (1995) showed adaptation to changes in the curvature of trajectories. This result, however, cannot rule out a shift of an equilibrium point or an additional synergy activation between start and end point of a movement. In our experiment, subjects did two sessions, one control without and one with velocity-profile manipulation. To skew the velocity profile of the cursor trajectory, we added to the current velocity, v, the function 0.8*v*cos(pi + pi*x), where x is the projection of the cursor position onto the start-goal line divided by the distance start to goal (x=0 at the start point). As result, subjects did not adapt to this manipulation: for all subjects, the true hand motion was not significantly modified in a direction consistent with adaptation, despite that the visually presented motion differed significantly from the control motion. One may still argue that this difference in motion was insufficient to be processed visually. Thus, as a control experiment, we replayed control and modified motions to the subjects and asked which of the two motions appeared 'more natural'. Subjects chose the unperturbed motion as more natural significantly better than chance. In summary, for a visuomotor transformation task, the hypothesis of a planned continuous end-effector trajectory predicts adaptation to a modified velocity profile. The current experiment found no adaptation under such transformation.

am

[BibTex]

[BibTex]


Thumb xl trajectory nips
Nonrigid Structure from Motion in Trajectory Space

Akhter, I., Sheikh, Y., Khan, S., Kanade, T.

In Neural Information Processing Systems, 1(2):41-48, 2008 (inproceedings)

Abstract
Existing approaches to nonrigid structure from motion assume that the instantaneous 3D shape of a deforming object is a linear combination of basis shapes, which have to be estimated anew for each video sequence. In contrast, we propose that the evolving 3D structure be described by a linear combination of basis trajectories. The principal advantage of this approach is that we do not need to estimate any basis vectors during computation. We show that generic bases over trajectories, such as the Discrete Cosine Transform (DCT) basis, can be used to compactly describe most real motions. This results in a significant reduction in unknowns, and corresponding stability in estimation. We report empirical performance, quantitatively using motion capture data, and qualitatively on several video sequences exhibiting nonrigid motions including piece-wise rigid motion, partially nonrigid motion (such as a facial expression), and highly nonrigid motion (such as a person dancing).

ps

pdf project page [BibTex]

pdf project page [BibTex]


Thumb xl sigalnips
Combined discriminative and generative articulated pose and non-rigid shape estimation

Sigal, L., Balan, A., Black, M. J.

In Advances in Neural Information Processing Systems 20, NIPS-2007, pages: 1337–1344, MIT Press, 2008 (inproceedings)

ps

pdf [BibTex]

pdf [BibTex]


no image
Reconstructing reach and grasp actions using neural population activity from Primary Motor Cortex

Vargas-Irwin, C. E., Yadollahpour, P., Shakhnarovich, G., Black, M. J., Donoghue, J. P.

2008 Abstract Viewer and Itinerary Planner, Society for Neuroscience, Washington, DC, 2008, Online (conference)

ps

[BibTex]

[BibTex]

2007


Thumb xl floweval
A Database and Evaluation Methodology for Optical Flow

Baker, S., Scharstein, D., Lewis, J.P., Roth, S., Black, M.J., Szeliski, R.

In Int. Conf. on Computer Vision, ICCV, pages: 1-8, Rio de Janeiro, Brazil, October 2007 (inproceedings)

ps

pdf [BibTex]

2007


pdf [BibTex]


Thumb xl iccv07b
Shining a light on human pose: On shadows, shading and the estimation of pose and shape,

Balan, A., Black, M. J., Haussecker, H., Sigal, L.

In Int. Conf. on Computer Vision, ICCV, pages: 1-8, Rio de Janeiro, Brazil, October 2007 (inproceedings)

ps

pdf YouTube [BibTex]

pdf YouTube [BibTex]


no image
Ensemble spiking activity as a source of cortical control signals in individuals with tetraplegia

Simeral, J. D., Kim, S. P., Black, M. J., Donoghue, J. P., Hochberg, L. R.

Biomedical Engineering Society, BMES, september 2007 (conference)

ps

[BibTex]

[BibTex]


Thumb xl cvpr07scape
Detailed human shape and pose from images

Balan, A., Sigal, L., Black, M. J., Davis, J., Haussecker, H.

In IEEE Conf. on Computer Vision and Pattern Recognition, CVPR, pages: 1-8, Minneapolis, June 2007 (inproceedings)

ps

pdf YouTube [BibTex]

pdf YouTube [BibTex]


no image
Learning static Gestalt laws through dynamic experience

Ostrovsky, Y., Wulff, J., Sinha, P.

Journal of Vision, 7(9):315-315, ARVO, June 2007 (article)

Abstract
The Gestalt laws (Wertheimer 1923) are widely regarded as the rules that help us parse the world into objects. However, it is unclear as to how these laws are acquired by an infant's visual system. Classically, these “laws” have been presumed to be innate (Kellman and Spelke 1983). But, more recent work in infant development, showing the protracted time-course over which these grouping principles emerge (e.g., Johnson and Aslin 1995; Craton 1996), suggests that visual experience might play a role in their genesis. Specifically, our studies of patients with late-onset vision (Project Prakash; VSS 2006) and evidence from infant development both point to an early role of common motion cues for object grouping. Here we explore the possibility that the privileged status of motion in the developmental timeline is not happenstance, but rather serves to bootstrap the learning of static Gestalt cues. Our approach involves computational analyses of real-world motion sequences to investigate whether primitive optic flow information is correlated with static figural cues that could eventually come to serve as proxies for grouping in the form of Gestalt principles. We calculated local optic flow maps and then examined how similarity of motion across image patches co-varied with similarity of certain figural properties in static frames. Results indicate that patches with similar motion are much more likely to have similar luminance, color, and orientation as compared to patches with dissimilar motion vectors. This regularity suggests that, in principle, common motion extracted from dynamic visual experience can provide enough information to bootstrap region grouping based on luminance and color and contour continuation mechanisms in static scenes. These observations, coupled with the cited experimental studies, lend credence to the hypothesis that static Gestalt laws might be learned through a bootstrapping process based on early dynamic experience.

ps

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl aperture
Decoding grasp aperture from motor-cortical population activity

Artemiadis, P., Shakhnarovich, G., Vargas-Irwin, C., Donoghue, J. P., Black, M. J.

In The 3rd International IEEE EMBS Conference on Neural Engineering, pages: 518-521, May 2007 (inproceedings)

ps

pdf [BibTex]

pdf [BibTex]


Thumb xl ner07
Multi-state decoding of point-and-click control signals from motor cortical activity in a human with tetraplegia

Kim, S., Simeral, J., Hochberg, L., Donoghue, J. P., Friehs, G., Black, M. J.

In The 3rd International IEEE EMBS Conference on Neural Engineering, pages: 486-489, May 2007 (inproceedings)

Abstract
Basic neural-prosthetic control of a computer cursor has been recently demonstrated by Hochberg et al. [1] using the BrainGate system (Cyberkinetics Neurotechnology Systems, Inc.). While these results demonstrate the feasibility of intracortically-driven prostheses for humans with paralysis, a practical cursor-based computer interface requires more precise cursor control and the ability to “click” on areas of interest. Here we present a practical point and click device that decodes both continuous states (e.g. cursor kinematics) and discrete states (e.g. click state) from single neural population in human motor cortex. We describe a probabilistic multi-state decoder and the necessary training paradigms that enable point and click cursor control by a human with tetraplegia using an implanted microelectrode array. We present results from multiple recording sessions and quantify the point and click performance.

ps

pdf [BibTex]

pdf [BibTex]


Thumb xl pedestal
Neuromotor prosthesis development

Donoghue, J., Hochberg, L., Nurmikko, A., Black, M., Simeral, J., Friehs, G.

Medicine & Health Rhode Island, 90(1):12-15, January 2007 (article)

Abstract
Article describes a neuromotor prosthesis (NMP), in development at Brown University, that records human brain signals, decodes them, and transforms them into movement commands. An NMP is described as a system consisting of a neural interface, a decoding system, and a user interface, also called an effector; a closed-loop system would be completed by a feedback signal from the effector to the brain. The interface is based on neural spiking, a source of information-rich, rapid, complex control signals from the nervous system. The NMP described, named BrainGate, consists of a match-head sized platform with 100 thread-thin electrodes implanted just into the surface of the motor cortex where commands to move the hand emanate. Neural signals are decoded by a rack of computers that displays the resultant output as the motion of a cursor on a computer monitor. While computer cursor motion represents a form of virtual device control, this same command signal could be routed to a device to command motion of paralyzed muscles or the actions of prosthetic limbs. The researchers’ overall goal is the development of a fully implantable, wireless multi-neuron sensor for broad research, neural prosthetic, and human neurodiagnostic applications.

ps

pdf [BibTex]

pdf [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
Machine Learning of Motor Skills for Robotics

Peters, J.

University of Southern California, Los Angeles, CA, USA, University of Southern California, Los Angeles, CA, USA, 2007, clmc (phdthesis)

Abstract
Autonomous robots that can assist humans in situations of daily life have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. A first step towards this goal is to create robots that can accomplish a multitude of different tasks, triggered by environmental context or higher level instruction. 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 and 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 thesis, 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 major 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. As a theoretical foundation, we first study a general framework to generate control laws for real robots with a particular focus on skills represented as dynamical systems in differential constraint form. We present a point-wise optimal control framework resulting from a generalization of Gauss' principle and show how various well-known robot control laws can be derived by modifying the metric of the employed cost function. The framework has been successfully applied to task space tracking control for holonomic systems for several different metrics on the anthropomorphic SARCOS Master Arm. In order to overcome the limiting requirement of accurate robot models, we first employ learning methods to find learning controllers for task space control. However, when learning to execute a redundant control problem, we face the general problem of the non-convexity of the solution space which can force the robot to steer into physically impossible configurations if supervised learning methods are employed without further consideration. This problem can be resolved using two major insights, i.e., the learning problem can be treated as locally convex and the cost function of the analytical framework can be used to ensure global consistency. Thus, we derive an immediate reinforcement learning algorithm from the expectation-maximization point of view which leads to a reward-weighted regression technique. This method can be used both for operational space control as well as general immediate reward reinforcement learning problems. We demonstrate the feasibility of the resulting framework on the problem of redundant end-effector tracking for both a simulated 3 degrees of freedom robot arm as well as for a simulated anthropomorphic SARCOS Master Arm. While learning to execute tasks in task space is an essential component to a general framework to motor skill learning, learning the actual task is of even higher importance, particularly as this issue is more frequently beyond the abilities of analytical approaches than execution. We focus on the learning of elemental tasks which can serve as the "building blocks of movement generation", called motor primitives. Motor primitives are parameterized task representations based on splines or nonlinear differential equations with desired attractor properties. While imitation learning of parameterized motor primitives is a relatively well-understood problem, the self-improvement by interaction of the system with the environment remains a challenging problem, tackled in the fourth chapter of this thesis. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and outline both established and novel algorithms for the gradient-based improvement of parameterized policies. We compare these algorithms in the context of motor primitive learning, and show that our most modern algorithm, the Episodic Natural Actor-Critic outperforms previous algorithms by at least an order of magnitude. We demonstrate the efficiency of this reinforcement learning method in the application of learning to hit a baseball with an anthropomorphic robot arm. In conclusion, in this thesis, we have contributed a general framework for analytically computing robot control laws which can be used for deriving various previous control approaches and serves as foundation as well as inspiration for our learning algorithms. We have introduced two classes of novel reinforcement learning methods, i.e., the Natural Actor-Critic and the Reward-Weighted Regression algorithm. These algorithms have been used in order to replace the analytical components of the theoretical framework by learned representations. Evaluations have been performed on both simulated and real robot arms.

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]