Header logo is


2007


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]

2007


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]


no image
Reinforcement learning for operational space control

Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Conference on Robotics and Automation, pages: 2111-2116, IEEE Computer Society, ICRA, 2007, clmc (inproceedings)

Abstract
While operational space control 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 complex robots, e.g., humanoid robots. In such cases, learning control methods can offer an interesting alternative to analytical control algorithms. However, the resulting supervised learning problem is ill-defined as it requires to learn an inverse mapping of a usually redundant system, which is well known to suffer from the property of non-convexity of the solution space, i.e., the learning system could generate motor commands that try to steer the robot into physically impossible configurations. The important insight that many operational space control algorithms can be reformulated as optimal control problems, however, allows addressing this inverse learning problem in the framework of reinforcement learning. 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-based 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
Relative Entropy Policy Search

Peters, J.

CLMC Technical Report: TR-CLMC-2007-2, Computational Learning and Motor Control Lab, Los Angeles, CA, 2007, clmc (techreport)

Abstract
This technical report describes a cute idea of how to create new policy search approaches. It directly relates to the Natural Actor-Critic methods but allows the derivation of one shot solutions. Future work may include the application to interesting problems.

am ei

PDF link (url) [BibTex]

PDF link (url) [BibTex]


no image
Using reward-weighted regression for reinforcement learning of task space control

Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pages: 262-267, Honolulu, Hawaii, April 1-5, 2007, 2007, clmc (inproceedings)

Abstract
In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, `vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Evaluation of Policy Gradient Methods and Variants on the Cart-Pole Benchmark

Riedmiller, M., Peters, J., Schaal, S.

In Proceedings of the 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pages: 254-261, ADPRL, 2007, clmc (inproceedings)

Abstract
In this paper, we evaluate different versions from the three main kinds of model-free policy gradient methods, i.e., finite difference gradients, `vanilla' policy gradients and natural policy gradients. Each of these methods is first presented in its simple form and subsequently refined and optimized. By carrying out numerous experiments on the cart pole regulator benchmark we aim to provide a useful baseline for future research on parameterized policy search algorithms. Portable C++ code is provided for both plant and algorithms; thus, the results in this paper can be reevaluated, reused and new algorithms can be inserted with ease.

am ei

PDF [BibTex]

PDF [BibTex]


no image
Uncertain 3D Force Fields in Reaching Movements: Do Humans Favor Robust or Average Performance?

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

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

am

PDF [BibTex]

PDF [BibTex]


no image
Applying the episodic natural actor-critic architecture to motor primitive learning

Peters, J., Schaal, S.

In Proceedings of the 2007 European Symposium on Artificial Neural Networks (ESANN), Bruges, Belgium, April 25-27, 2007, clmc (inproceedings)

Abstract
In this paper, we investigate motor primitive learning with the Natural Actor-Critic approach. The Natural Actor-Critic consists out of actor updates which are achieved using natural stochastic policy gradients while the critic obtains the natural policy gradient by linear regression. We show that this architecture can be used to learn the Òbuilding blocks of movement generationÓ, called motor primitives. Motor primitives are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. We 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.

am

link (url) [BibTex]

link (url) [BibTex]


no image
The new robotics - towards human-centered machines

Schaal, S.

HFSP Journal Frontiers of Interdisciplinary Research in the Life Sciences, 1(2):115-126, 2007, clmc (article)

Abstract
Research in robotics has moved away from its primary focus on industrial applications. The New Robotics is a vision that has been developed in past years by our own university and many other national and international research instiutions and addresses how increasingly more human-like robots can live among us and take over tasks where our current society has shortcomings. Elder care, physical therapy, child education, search and rescue, and general assistance in daily life situations are some of the examples that will benefit from the New Robotics in the near future. With these goals in mind, research for the New Robotics has to embrace a broad interdisciplinary approach, ranging from traditional mathematical issues of robotics to novel issues in psychology, neuroscience, and ethics. This paper outlines some of the important research problems that will need to be resolved to make the New Robotics a reality.

am

link (url) [BibTex]

link (url) [BibTex]


no image
A computational model of human trajectory planning based on convergent flow fields

Hoffman, H., Schaal, S.

In Abstracts of the 37st Meeting of the Society of Neuroscience, San Diego, CA, Nov. 3-7, 2007, clmc (inproceedings)

Abstract
A popular computational model suggests that smooth reaching movements are generated in humans by minimizing a difference vector between hand and target in visual coordinates (Shadmehr and Wise, 2005). To achieve such a task, the optimal joint accelerations may be pre-computed. However, this pre-planning is inflexible towards perturbations of the limb, and there is strong evidence that reaching movements can be modified on-line at any moment during the movement. Thus, next-state planning models (Bullock and Grossberg, 1988) have been suggested that compute the current control command from a function of the goal state such that the overall movement smoothly converges to the goal (see Shadmehr and Wise (2005) for an overview). So far, these models have been restricted to simple point-to-point reaching movements with (approximately) straight trajectories. Here, we present a computational model for learning and executing arbitrary trajectories that combines ideas from pattern generation with dynamic systems and the observation of convergent force fields, which control a frog leg after spinal stimulation (Giszter et al., 1993). In our model, we incorporate the following two observations: first, the orientation of vectors in a force field is invariant over time, but their amplitude is modulated by a time-varying function, and second, two force fields add up when stimulated simultaneously (Giszter et al., 1993). This addition of convergent force fields varying over time results in a virtual trajectory (a moving equilibrium point) that correlates with the actual leg movement (Giszter et al., 1993). Our next-state planner is a set of differential equations that provide the desired end-effector or joint accelerations using feedback of the current state of the limb. These accelerations can be interpreted as resulting from a damped spring that links the current limb position with a virtual trajectory. This virtual trajectory can be learned to realize any desired limb trajectory and velocity profile, and learning is efficient since the time-modulated sum of convergent force fields equals a sum of weighted basis functions (Gaussian time pulses). Thus, linear algebra is sufficient to compute these weights, which correspond to points on the virtual trajectory. During movement execution, the differential equation corrects automatically for perturbations and brings back smoothly the limb towards the goal. Virtual trajectories can be rescaled and added allowing to build a set of movement primitives to describe movements more complex than previously learned. We demonstrate the potential of the suggested model by learning and generating a wide variety of movements.

am

[BibTex]

[BibTex]


no image
A Computational Model of Arm Trajectory Modification Using Dynamic Movement Primitives

Mohajerian, P., Hoffmann, H., Mistry, M., Schaal, S.

In Abstracts of the 37st Meeting of the Society of Neuroscience, San Diego, CA, Nov 3-7, 2007, clmc (inproceedings)

Abstract
Several scientists used a double-step target-displacement protocol to investigate how an unexpected upcoming new target modifies ongoing discrete movements. Interesting observations are the initial direction of the movement, the spatial path of the movement to the second target, and the amplification of the speed in the second movement. Experimental data show that the above properties are influenced by the movement reaction time and the interstimulus interval between the onset of the first and second target. Hypotheses in the literature concerning the interpretation of the observed data include a) the second movement is superimposed on the first movement (Henis and Flash, 1995), b) the first movement is aborted and the second movement is planned to smoothly connect the current state of the arm with the new target (Hoff and Arbib, 1992), c) the second movement is initiated by a new control signal that replaces the first movement's control signal, but does not take the state of the system into account (Flanagan et al., 1993), and (d) the second movement is initiated by a new goal command, but the control structure stays unchanged, and feed-back from the current state is taken into account (Hoff and Arbib, 1993). We investigate target switching from the viewpoint of Dynamic Movement Primitives (DMPs). DMPs are trajectory planning units that are formalized as stable nonlinear attractor systems (Ijspeert et al., 2002). They are a useful framework for biological motor control as they are highly flexible in creating complex rhythmic and discrete behaviors that can quickly adapt to the inevitable perturbations of dynamically changing, stochastic environments. In this model, target switching is accomplished simply by updating the target input to the discrete movement primitive for reaching. The reaching trajectory in this model can be straight or take any other route; in contrast, the Hoff and Arbib (1993) model is restricted to straight reaching movement plans. In the present study, we use DMPs to reproduce in simulation a large number of target-switching experimental data from the literature and to show that online correction and the observed target switching phenomena can be accomplished by changing the goal state of an on-going DMP, without the need to switch to different movement primitives or to re-plan the movement. :

am

PDF [BibTex]

PDF [BibTex]


no image
Inverse dynamics control with floating base and constraints

Nakanishi, J., Mistry, M., Schaal, S.

In International Conference on Robotics and Automation (ICRA2007), pages: 1942-1947, Rome, Italy, April 10-14, 2007, clmc (inproceedings)

Abstract
In this paper, we address the issues of compliant control of a robot under contact constraints with a goal of using joint space based pattern generators as movement primitives, as often considered in the studies of legged locomotion and biological motor control. For this purpose, we explore inverse dynamics control of constrained dynamical systems. When the system is overconstrained, it is not straightforward to formulate an inverse dynamics control law since the problem becomes an ill-posed one, where infinitely many combinations of joint torques are possible to achieve the desired joint accelerations. The goal of this paper is to develop a general and computationally efficient inverse dynamics algorithm for a robot with a free floating base and constraints. We suggest an approximate way of computing inverse dynamics algorithm by treating constraint forces computed with a Lagrange multiplier method as simply external forces based on FeatherstoneÕs floating base formulation of inverse dynamics. We present how all the necessary quantities to compute our controller can be efficiently extracted from FeatherstoneÕs spatial notation of robot dynamics. We evaluate the effectiveness of the suggested approach on a simulated biped robot model.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Dynamics systems vs. optimal control ? a unifying view

Schaal, S, Mohajerian, P., Ijspeert, A.

In Progress in Brain Research, (165):425-445, 2007, clmc (inbook)

Abstract
In the past, computational motor control has been approached from at least two major frameworks: the dynamic systems approach and the viewpoint of optimal control. The dynamic system approach emphasizes motor control as a process of self-organization between an animal and its environment. Nonlinear differential equations that can model entrainment and synchronization behavior are among the most favorable tools of dynamic systems modelers. In contrast, optimal control approaches view motor control as the evolutionary or development result of a nervous system that tries to optimize rather general organizational principles, e.g., energy consumption or accurate task achievement. Optimal control theory is usually employed to develop appropriate theories. Interestingly, there is rather little interaction between dynamic systems and optimal control modelers as the two approaches follow rather different philosophies and are often viewed as diametrically opposing. In this paper, we develop a computational approach to motor control that offers a unifying modeling framework for both dynamic systems and optimal control approaches. In discussions of several behavioral experiments and some theoretical and robotics studies, we demonstrate how our computational ideas allow both the representation of self-organizing processes and the optimization of movement based on reward criteria. Our modeling framework is rather simple and general, and opens opportunities to revisit many previous modeling results from this novel unifying view.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Kernel carpentry for onlne regression using randomly varying coefficient model

Edakunni, N. U., Schaal, S., Vijayakumar, S.

In Proceedings of the 20th International Joint Conference on Artificial Intelligence, Hyderabad, India: Jan. 6-12, 2007, clmc (inproceedings)

Abstract
We present a Bayesian formulation of locally weighted learning (LWL) using the novel concept of a randomly varying coefficient model. Based on this, we propose a mechanism for multivariate non-linear regression using spatially localised linear models that learns completely independent of each other, uses only local information and adapts the local model complexity in a data driven fashion. We derive online updates for the model parameters based on variational Bayesian EM. The evaluation of the proposed algorithm against other state-of-the-art methods reveal the excellent, robust generalization performance beside surprisingly efficient time and space complexity properties. This paper, for the first time, brings together the computational efficiency and the adaptability of Õnon-competitiveÕ locally weighted learning schemes and the modeling guarantees of the Bayesian formulation.

am

link (url) [BibTex]

link (url) [BibTex]


no image
A robust quadruped walking gait for traversing rough terrain

Pongas, D., Mistry, M., Schaal, S.

In International Conference on Robotics and Automation (ICRA2007), pages: 1474-1479, Rome, April 10-14, 2007, 2007, clmc (inproceedings)

Abstract
Legged locomotion excels when terrains become too rough for wheeled systems or open-loop walking pattern generators to succeed, i.e., when accurate foot placement is of primary importance in successfully reaching the task goal. In this paper we address the scenario where the rough terrain is traversed with a static walking gait, and where for every foot placement of a leg, the location of the foot placement was selected irregularly by a planning algorithm. Our goal is to adjust a smooth walking pattern generator with the selection of every foot placement such that the COG of the robot follows a stable trajectory characterized by a stability margin relative to the current support triangle. We propose a novel parameterization of the COG trajectory based on the current position, velocity, and acceleration of the four legs of the robot. This COG trajectory has guaranteed continuous velocity and acceleration profiles, which leads to continuous velocity and acceleration profiles of the leg movement, which is ideally suited for advanced model-based controllers. Pitch, yaw, and ground clearance of the robot are easily adjusted automatically under any terrain situation. We evaluate our gait generation technique on the Little-Dog quadruped robot when traversing complex rocky and sloped terrains.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Bayesian Nonparametric Regression with Local Models

Ting, J., Schaal, S.

In Workshop on Robotic Challenges for Machine Learning, NIPS 2007, 2007, clmc (inproceedings)

am

[BibTex]

[BibTex]


no image
Learning an Outlier-Robust Kalman Filter

Ting, J., Theodorou, E., Schaal, S.

CLMC Technical Report: TR-CLMC-2007-1, Los Angeles, CA, 2007, clmc (techreport)

Abstract
We introduce a modified Kalman filter that performs robust, real-time outlier detection, without the need for manual parameter tuning by the user. Systems that rely on high quality sensory data (for instance, robotic systems) can be sensitive to data containing outliers. The standard Kalman filter is not robust to outliers, and other variations of the Kalman filter have been proposed to overcome this issue. However, these methods may require manual parameter tuning, use of heuristics or complicated parameter estimation procedures. Our Kalman filter uses a weighted least squares-like approach by introducing weights for each data sample. A data sample with a smaller weight has a weaker contribution when estimating the current time step?s state. Using an incremental variational Expectation-Maximization framework, we learn the weights and system dynamics. We evaluate our Kalman filter algorithm on data from a robotic dog.

am

PDF [BibTex]

PDF [BibTex]


no image
Task space control with prioritization for balance and locomotion

Mistry, M., Nakanishi, J., Schaal, S.

In IEEE International Conference on Intelligent Robotics Systems (IROS 2007), San Diego, CA: Oct. 29 Ð Nov. 2, 2007, clmc (inproceedings)

Abstract
This paper addresses locomotion with active balancing, via task space control with prioritization. The center of gravity (COG) and foot of the swing leg are treated as task space control points. Floating base inverse kinematics with constraints is employed, thereby allowing for a mobile platform suitable for locomotion. Different techniques of task prioritization are discussed and we clarify differences and similarities of previous suggested work. Varying levels of prioritization for control are examined with emphasis on singularity robustness and the negative effects of constraint switching. A novel controller for task space control of balance and locomotion is developed which attempts to address singularity robustness, while minimizing discontinuities created by constraint switching. Controllers are evaluated using a quadruped robot simulator engaging in a locomotion task.

am

link (url) [BibTex]

link (url) [BibTex]

2006


no image
Learning operational space control

Peters, J., Schaal, S.

In Robotics: Science and Systems II (RSS 2006), pages: 255-262, (Editors: Gaurav S. Sukhatme and Stefan Schaal and Wolfram Burgard and Dieter Fox), Cambridge, MA: MIT Press, RSS , 2006, clmc (inproceedings)

Abstract
While operational space control 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 complex robots, e.g., humanoid robots. In such cases, learning control methods can offer an interesting alternative to analytical control algorithms. However, the resulting learning problem is ill-defined as it requires to learn an inverse mapping of a usually redundant system, which is well known to suffer from the property of non-covexity of the solution space, i.e., the learning system could generate motor commands that try to steer the robot into physically impossible configurations. A first important insight for this paper is that, nevertheless, a physically correct solution to the inverse problem does exits when learning of the inverse map is performed in a suitable piecewise linear way. The second crucial component for our work is based on a recent insight that many operational space controllers can be understood in terms of a constraint optimal control problem. The cost function associated with this optimal control problem allows us to formulate a learning algorithm that automatically synthesizes a globally consistent desired resolution of redundancy while learning the operational space controller. From the view of machine learning, the learning problem corresponds to a reinforcement learning problem that maximizes an immediate reward and that employs an expectation-maximization policy search algorithm. Evaluations on a three degrees of freedom robot arm illustrate the feasability of our suggested approach.

am ei

link (url) [BibTex]

2006


link (url) [BibTex]


no image
Reinforcement Learning for Parameterized Motor Primitives

Peters, J., Schaal, S.

In Proceedings of the 2006 International Joint Conference on Neural Networks, pages: 73-80, IJCNN, 2006, clmc (inproceedings)

Abstract
One of the major challenges in both action generation for robotics and in the understanding of human motor control is to learn the "building blocks of movement generation", called motor primitives. Motor primitives, as used in this paper, are parameterized control policies such as splines or nonlinear differential equations with desired attractor properties. While a lot of progress has been made in teaching parameterized motor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this paper, we evaluate different reinforcement learning approaches for improving the performance of parameterized motor primitives. 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.

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Statistical Learning of LQG controllers

Theodorou, E.

Technical Report-2006-1, Computational Action and Vision Lab University of Minnesota, 2006, clmc (techreport)

am

PDF [BibTex]

PDF [BibTex]


no image
Approximate nearest neighbor regression in very high dimensions

Vijayakumar, S., DSouza, A., Schaal, S.

In Nearest-Neighbor Methods in Learning and Vision, pages: 103-142, (Editors: Shakhnarovich, G.;Darrell, T.;Indyk, P.), Cambridge, MA: MIT Press, 2006, clmc (inbook)

am

link (url) [BibTex]

link (url) [BibTex]

2004


no image
Discovering optimal imitation strategies

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

Robotics and Autonomous Systems, 47(2-3):68-77, 2004, clmc (article)

Abstract
This paper develops a general policy for learning relevant features of an imitation task. We restrict our study to imitation of manipulative tasks or of gestures. The imitation process is modeled as a hierarchical optimization system, which minimizes the discrepancy between two multi-dimensional datasets. To classify across manipulation strategies, we apply a probabilistic analysis to data in Cartesian and joint spaces. We determine a general metric that optimizes the policy of task reproduction, following strategy determination. The model successfully discovers strategies in six different imitative tasks and controls task reproduction by a full body humanoid robot.

am

[BibTex]

2004


[BibTex]


no image
Learning Composite Adaptive Control for a Class of Nonlinear Systems

Nakanishi, J., Farrell, J. A., Schaal, S.

In IEEE International Conference on Robotics and Automation, pages: 2647-2652, New Orleans, LA, USA, April 2004, 2004, clmc (inproceedings)

am

link (url) [BibTex]

link (url) [BibTex]


no image
Rhythmic movement is not discrete

Schaal, S., Sternad, D., Osu, R., Kawato, M.

Nature Neuroscience, 7(10):1137-1144, 2004, clmc (article)

Abstract
Rhythmic movements, like walking, chewing, or scratching, are phylogenetically old mo-tor behaviors found in many organisms, ranging from insects to primates. In contrast, discrete movements, like reaching, grasping, or kicking, are behaviors that have reached sophistication primarily in younger species, particularly in primates. Neurophysiological and computational research on arm motor control has focused almost exclusively on dis-crete movements, essentially assuming similar neural circuitry for rhythmic tasks. In con-trast, many behavioral studies focused on rhythmic models, subsuming discrete move-ment as a special case. Here, using a human functional neuroimaging experiment, we show that in addition to areas activated in rhythmic movement, discrete movement in-volves several higher cortical planning areas, despite both movement conditions were confined to the same single wrist joint. These results provide the first neuroscientific evi-dence that rhythmic arm movement cannot be part of a more general discrete movement system, and may require separate neurophysiological and theoretical treatment.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning from demonstration and adaptation of biped locomotion

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

Robotics and Autonomous Systems, 47(2-3):79-91, 2004, clmc (article)

Abstract
In this paper, we introduce a framework for learning biped locomotion using dynamical movement primitives based on non-linear oscillators. Our ultimate goal is to establish a design principle of a controller in order to achieve natural human-like locomotion. We suggest dynamical movement primitives as a central pattern generator (CPG) of a biped robot, an approach we have previously proposed for learning and encoding complex human movements. Demonstrated trajectories are learned through movement primitives by locally weighted regression, and the frequency of the learned trajectories is adjusted automatically by a novel frequency adaptation algorithmbased on phase resetting and entrainment of coupled oscillators. Numerical simulations and experimental implementation on a physical robot demonstrate the effectiveness of the proposed locomotioncontroller.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Towards Tractable Parameter-Free Statistical Learning (Phd Thesis)

D’Souza, A

Department of Computer Science, University of Southern California, Los Angeles, 2004, clmc (phdthesis)

am

link (url) [BibTex]

link (url) [BibTex]


no image
A framework for learning biped locomotion with dynamic movement primitives

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

In IEEE-RAS/RSJ International Conference on Humanoid Robots (Humanoids 2004), IEEE, Los Angeles, CA: Nov.10-12, Santa Monica, CA, 2004, clmc (inproceedings)

Abstract
This article summarizes our framework for learning biped locomotion using dynamical movement primitives based on nonlinear oscillators. Our ultimate goal is to establish a design principle of a controller in order to achieve natural human-like locomotion. We suggest dynamical movement primitives as a central pattern generator (CPG) of a biped robot, an approach we have previously proposed for learning and encoding complex human movements. Demonstrated trajectories are learned through movement primitives by locally weighted regression, and the frequency of the learned trajectories is adjusted automatically by a frequency adaptation algorithm based on phase resetting and entrainment of coupled oscillators. Numerical simulations and experimental implementation on a physical robot demonstrate the effectiveness of the proposed locomotion controller. Furthermore, we demonstrate that phase resetting contributes to robustness against external perturbations and environmental changes by numerical simulations and experiments.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning Motor Primitives with Reinforcement Learning

Peters, J., Schaal, S.

In Proceedings of the 11th Joint Symposium on Neural Computation, http://resolver.caltech.edu/CaltechJSNC:2004.poster020, 2004, clmc (inproceedings)

Abstract
One of the major challenges in action generation for robotics and in the understanding of human motor control is to learn the "building blocks of move- ment generation," or more precisely, motor primitives. Recently, Ijspeert et al. [1, 2] suggested a novel framework how to use nonlinear dynamical systems as motor primitives. While a lot of progress has been made in teaching these mo- tor primitives using supervised or imitation learning, the self-improvement by interaction of the system with the environment remains a challenging problem. In this poster, we evaluate different reinforcement learning approaches can be used in order to improve the performance of motor primitives. For pursuing this goal, we highlight the difficulties with current reinforcement learning methods, and line out how these lead to a novel algorithm which is based on natural policy gradients [3]. We compare this algorithm to previous reinforcement learning algorithms in the context of dynamic motor primitive learning, and show that it outperforms these by at least an order of magnitude. We demonstrate the efficiency of the resulting reinforcement learning method for creating complex behaviors for automous robotics. The studied behaviors will include both discrete, finite tasks such as baseball swings, as well as complex rhythmic patterns as they occur in biped locomotion

am

[BibTex]

[BibTex]


no image
Feedback error learning and nonlinear adaptive control

Nakanishi, J., Schaal, S.

Neural Networks, 17(10):1453-1465, 2004, clmc (article)

Abstract
In this paper, we present our theoretical investigations of the technique of feedback error learning (FEL) from the viewpoint of adaptive control. We first discuss the relationship between FEL and nonlinear adaptive control with adaptive feedback linearization, and show that FEL can be interpreted as a form of nonlinear adaptive control. Second, we present a Lyapunov analysis suggesting that the condition of strictly positive realness (SPR) associated with the tracking error dynamics is a sufficient condition for asymptotic stability of the closed-loop dynamics. Specifically, for a class of second order SISO systems, we show that this condition reduces to KD^2 > KP; where KP and KD are positive position and velocity feedback gains, respectively. Moreover, we provide a ÔpassivityÕ-based stability analysis which suggests that SPR of the tracking error dynamics is a necessary and sufficient condition for asymptotic hyperstability. Thus, the condition KD^2>KP mentioned above is not only a sufficient but also necessary condition to guarantee asymptotic hyperstability of FEL, i.e. the tracking error is bounded and asymptotically converges to zero. As a further point, we explore the adaptive control and FEL framework for feedforward control formulations, and derive an additional sufficient condition for asymptotic stability in the sense of Lyapunov. Finally, we present numerical simulations to illustrate the stability properties of FEL obtained from our mathematical analysis.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Computational approaches to motor learning by imitation

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

In The Neuroscience of Social Interaction, (1431):199-218, (Editors: Frith, C. D.;Wolpert, D.), Oxford University Press, Oxford, 2004, clmc (inbook)

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

am

link (url) [BibTex]

link (url) [BibTex]

1998


no image
Programmable pattern generators

Schaal, S., Sternad, D.

In 3rd International Conference on Computational Intelligence in Neuroscience, pages: 48-51, Research Triangle Park, NC, Oct. 24-28, October 1998, clmc (inproceedings)

Abstract
This paper explores the idea to create complex human-like arm movements from movement primitives based on nonlinear attractor dynamics. Each degree-of-freedom of an arm is assumed to have two independent abilities to create movement, one through a discrete dynamic system, and one through a rhythmic system. The discrete system creates point-to-point movements based on internal or external target specifications. The rhythmic system can add an additional oscillatory movement relative to the current position of the discrete system. In the present study, we develop appropriate dynamic systems that can realize the above model, motivate the particular choice of the systems from a biological and engineering point of view, and present simulation results of the performance of such movement primitives. Implementation results on a Sarcos Dexterous Arm are discussed.

am

link (url) [BibTex]

1998


link (url) [BibTex]


no image
Robust local learning in high dimensional spaces

Vijayakumar, S., Schaal, S.

In 5th Joint Symposium on Neural Computation, pages: 186-193, Institute for Neural Computation, University of California, San Diego, San Diego, CA, 1998, clmc (inproceedings)

Abstract
Incremental learning of sensorimotor transformations in high dimensional spaces is one of the basic prerequisites for the success of autonomous robot devices as well as biological movement systems. So far, due to sparsity of data in high dimensional spaces, learning in such settings requires a significant amount of prior knowledge about the learning task, usually provided by a human expert. In this paper, we suggest a partial revision of this view. Based on empirical studies, we observed that, despite being globally high dimensional and sparse, data distributions from physical movement systems are locally low dimensional and dense. Under this assumption, we derive a learning algorithm, Locally Adaptive Subspace Regression, that exploits this property by combining a dynamically growing local dimensionality reduction technique as a preprocessing step with a nonparametric learning technique, locally weighted regression, that also learns the region of validity of the regression. The usefulness of the algorithm and the validity of its assumptions are illustrated for a synthetic data set, and for data of the inverse dynamics of human arm movements and an actual 7 degree-of-freedom anthropomorphic robot arm.

am

[BibTex]

[BibTex]


no image
Local dimensionality reduction

Schaal, S., Vijayakumar, S., Atkeson, C. G.

In Advances in Neural Information Processing Systems 10, pages: 633-639, (Editors: Jordan, M. I.;Kearns, M. J.;Solla, S. A.), MIT Press, Cambridge, MA, 1998, clmc (inproceedings)

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

am

link (url) [BibTex]

link (url) [BibTex]


no image
Constructive incremental learning from only local information

Schaal, S., Atkeson, C. G.

Neural Computation, 10(8):2047-2084, 1998, clmc (article)

Abstract
We introduce a constructive, incremental learning system for regression problems that models data by means of spatially localized linear models. In contrast to other approaches, the size and shape of the receptive field of each locally linear model as well as the parameters of the locally linear model itself are learned independently, i.e., without the need for competition or any other kind of communication. Independent learning is accomplished by incrementally minimizing a weighted local cross validation error. As a result, we obtain a learning system that can allocate resources as needed while dealing with the bias-variance dilemma in a principled way. The spatial localization of the linear models increases robustness towards negative interference. Our learning system can be interpreted as a nonparametric adaptive bandwidth smoother, as a mixture of experts where the experts are trained in isolation, and as a learning system which profits from combining independent expert knowledge on the same problem. This paper illustrates the potential learning capabilities of purely local learning and offers an interesting and powerful approach to learning with receptive fields. 

am

link (url) [BibTex]

link (url) [BibTex]


no image
Biomimetic gaze stabilization based on a study of the vestibulocerebellum

Shibata, T., Schaal, S.

In European Workshop on Learning Robots, pages: 84-94, Edinburgh, UK, 1998, clmc (inproceedings)

Abstract
Accurate oculomotor control is one of the essential pre-requisites for successful visuomotor coordination. In this paper, we suggest a biologically inspired control system for learning gaze stabilization with a biomimetic robotic oculomotor system. In a stepwise fashion, we develop a control circuit for the vestibulo-ocular reflex (VOR) and the opto-kinetic response (OKR), and add a nonlinear learning network to allow adaptivity. We discuss the parallels and differences of our system with biological oculomotor control and suggest solutions how to deal with nonlinearities and time delays in the control system. In simulation and actual robot studies, we demonstrate that our system can learn gaze stabilization in real time in only a few seconds with high final accuracy.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Towards biomimetic vision

Shibata, T., Schaal, S.

In International Conference on Intelligence Robots and Systems, pages: 872-879, Victoria, Canada, 1998, clmc (inproceedings)

Abstract
Oculomotor control is the foundation of most biological visual systems, as well as an important component in the entire perceptual-motor system. We review some of the most basic principles of biological oculomotor systems, and explore their usefulness from both the biological and computational point of view. As an example of biomimetic oculomotor control, we present the state of our implementations and experimental results using the vestibulo-ocular-reflex and opto-kinetic-reflex paradigm

am

link (url) [BibTex]

link (url) [BibTex]


no image
Local adaptive subspace regression

Vijayakumar, S., Schaal, S.

Neural Processing Letters, 7(3):139-149, 1998, clmc (article)

Abstract
Incremental learning of sensorimotor transformations in high dimensional spaces is one of the basic prerequisites for the success of autonomous robot devices as well as biological movement systems. So far, due to sparsity of data in high dimensional spaces, learning in such settings requires a significant amount of prior knowledge about the learning task, usually provided by a human expert. In this paper we suggest a partial revision of the view. Based on empirical studies, we observed that, despite being globally high dimensional and sparse, data distributions from physical movement systems are locally low dimensional and dense. Under this assumption, we derive a learning algorithm, Locally Adaptive Subspace Regression, that exploits this property by combining a dynamically growing local dimensionality reduction technique  as a preprocessing step with a nonparametric learning technique, locally weighted regression, that also learns the region of validity of the regression. The usefulness of the algorithm and the validity of its assumptions are illustrated for a synthetic data set, and for data of the inverse dynamics of human arm movements and an actual 7 degree-of-freedom anthropomorphic robot arm. 

am

link (url) [BibTex]

link (url) [BibTex]

1997


no image
Locally weighted learning

Atkeson, C. G., Moore, A. W., Schaal, S.

Artificial Intelligence Review, 11(1-5):11-73, 1997, clmc (article)

Abstract
This paper surveys locally weighted learning, a form of lazy learning and memory-based learning, and focuses on locally weighted linear regression. The survey discusses distance functions, smoothing parameters, weighting functions, local model structures, regularization of the estimates and bias, assessing predictions, handling noisy data and outliers, improving the quality of predictions by tuning fit parameters, interference between old and new data, implementing locally weighted learning efficiently, and applications of locally weighted learning. A companion paper surveys how locally weighted learning can be used in robot learning and control. Keywords: locally weighted regression, LOESS, LWR, lazy learning, memory-based learning, least commitment learning, distance functions, smoothing parameters, weighting functions, global tuning, local tuning, interference.

am

link (url) [BibTex]

1997


link (url) [BibTex]


no image
Locally weighted learning for control

Atkeson, C. G., Moore, A. W., Schaal, S.

Artificial Intelligence Review, 11(1-5):75-113, 1997, clmc (article)

Abstract
Lazy learning methods provide useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of complex systems. This paper surveys ways in which locally weighted learning, a type of lazy learning, has been applied by us to control tasks. We explain various forms that control tasks can take, and how this affects the choice of learning paradigm. The discussion section explores the interesting impact that explicitly remembering all previous experiences has on the problem of learning to control. Keywords: locally weighted regression, LOESS, LWR, lazy learning, memory-based learning, least commitment learning, forward models, inverse models, linear quadratic regulation (LQR), shifting setpoint algorithm, dynamic programming.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning from demonstration

Schaal, S.

In Advances in Neural Information Processing Systems 9, pages: 1040-1046, (Editors: Mozer, M. C.;Jordan, M.;Petsche, T.), MIT Press, Cambridge, MA, 1997, clmc (inproceedings)

Abstract
By now it is widely accepted that learning a task from scratch, i.e., without any prior knowledge, is a daunting undertaking. Humans, however, rarely attempt to learn from scratch. They extract initial biases as well as strategies how to approach a learning problem from instructions and/or demonstrations of other humans. For learning control, this paper investigates how learning from demonstration can be applied in the context of reinforcement learning. We consider priming the Q-function, the value function, the policy, and the model of the task dynamics as possible areas where demonstrations can speed up learning. In general nonlinear learning problems, only model-based reinforcement learning shows significant speed-up after a demonstration, while in the special case of linear quadratic regulator (LQR) problems, all methods profit from the demonstration. In an implementation of pole balancing on a complex anthropomorphic robot arm, we demonstrate that, when facing the complexities of real signal processing, model-based reinforcement learning offers the most robustness for LQR problems. Using the suggested methods, the robot learns pole balancing in just a single trial after a 30 second long demonstration of the human instructor. 

am

link (url) [BibTex]

link (url) [BibTex]


no image
Robot learning from demonstration

Atkeson, C. G., Schaal, S.

In Machine Learning: Proceedings of the Fourteenth International Conference (ICML ’97), pages: 12-20, (Editors: Fisher Jr., D. H.), Morgan Kaufmann, Nashville, TN, July 8-12, 1997, 1997, clmc (inproceedings)

Abstract
The goal of robot learning from demonstration is to have a robot learn from watching a demonstration of the task to be performed. In our approach to learning from demonstration the robot learns a reward function from the demonstration and a task model from repeated attempts to perform the task. A policy is computed based on the learned reward function and task model. Lessons learned from an implementation on an anthropomorphic robot arm using a pendulum swing up task include 1) simply mimicking demonstrated motions is not adequate to perform this task, 2) a task planner can use a learned model and reward function to compute an appropriate policy, 3) this model-based planning process supports rapid learning, 4) both parametric and nonparametric models can be learned and used, and 5) incorporating a task level direct learning component, which is non-model-based, in addition to the model-based planner, is useful in compensating for structural modeling errors and slow model learning. 

am

link (url) [BibTex]

link (url) [BibTex]


no image
Local dimensionality reduction for locally weighted learning

Vijayakumar, S., Schaal, S.

In International Conference on Computational Intelligence in Robotics and Automation, pages: 220-225, Monteray, CA, July10-11, 1997, 1997, clmc (inproceedings)

Abstract
Incremental learning of sensorimotor transformations in high dimensional spaces is one of the basic prerequisites for the success of autonomous robot devices as well as biological movement systems. So far, due to sparsity of data in high dimensional spaces, learning in such settings requires a significant amount of prior knowledge about the learning task, usually provided by a human expert. In this paper we suggest a partial revision of the view. Based on empirical studies, it can been observed that, despite being globally high dimensional and sparse, data distributions from physical movement systems are locally low dimensional and dense. Under this assumption, we derive a learning algorithm, Locally Adaptive Subspace Regression, that exploits this property by combining a local dimensionality reduction as a preprocessing step with a nonparametric learning technique, locally weighted regression. The usefulness of the algorithm and the validity of its assumptions are illustrated for a synthetic data set and data of the inverse dynamics of an actual 7 degree-of-freedom anthropomorphic robot arm.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning tasks from a single demonstration

Atkeson, C. G., Schaal, S.

In IEEE International Conference on Robotics and Automation (ICRA97), 2, pages: 1706-1712, Piscataway, NJ: IEEE, Albuquerque, NM, 20-25 April, 1997, clmc (inproceedings)

Abstract
Learning a complex dynamic robot manoeuvre from a single human demonstration is difficult. This paper explores an approach to learning from demonstration based on learning an optimization criterion from the demonstration and a task model from repeated attempts to perform the task, and using the learned criterion and model to compute an appropriate robot movement. A preliminary version of the approach has been implemented on an anthropomorphic robot arm using a pendulum swing up task as an example

am

link (url) [BibTex]

link (url) [BibTex]