Header logo is am


2003


no image
Reinforcement learning for humanoid robotics

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

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

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

link (url) [BibTex]

2003

link (url) [BibTex]


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

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

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

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

link (url) [BibTex]

link (url) [BibTex]


no image
Scaling reinforcement learning paradigms for motor learning

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

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

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

link (url) [BibTex]

link (url) [BibTex]


no image
Design and Control of a Leg for the Running Machine PANTER

Berns, K., Grimminger, F., Hochholdinger, U., Kerscher, T., Albiez, J.

In Proceedings of the ICAR 2003–11th International Conference on Advanced Robotics, pages: 1737-1742, 2003 (inproceedings)

[BibTex]

[BibTex]


no image
Learning attractor landscapes for learning motor primitives

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

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

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

link (url) [BibTex]

link (url) [BibTex]


no image
PANTER-prototype for a fast-running quadruped robot with pneumatic muscles

Albiez, J., Kerscher, T., Grimminger, F., Hochholdinger, U., Dillmann, R., Berns, K.

In Proceedings of the 6th International Conference on Climbing and Walking Robots, pages: 617-624, 2003 (inproceedings)

[BibTex]

[BibTex]


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

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

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

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

link (url) [BibTex]

link (url) [BibTex]


no image
Movement planning and imitation by shaping nonlinear attractors

Schaal, S.

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

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

link (url) [BibTex]

link (url) [BibTex]

2002


no image
Learning rhythmic movements by demonstration using nonlinear oscillators

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

In IEEE International Conference on Intelligent Robots and Systems (IROS 2002), pages: 958-963, Piscataway, NJ: IEEE, Lausanne, Sept.30-Oct.4 2002, 2002, clmc (inproceedings)

Abstract
Locally weighted learning (LWL) is a class of statistical learning techniques that provides useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of robotic systems. This paper introduces several LWL algorithms that have been tested successfully in real-time learning of complex robot tasks. We discuss two major classes of LWL, memory-based LWL and purely incremental LWL that does not need to remember any data explicitly. In contrast to the traditional beliefs that LWL methods cannot work well in high-dimensional spaces, we provide new algorithms that have been tested in up to 50 dimensional learning problems. The applicability of our LWL algorithms is demonstrated in various robot learning examples, including the learning of devil-sticking, pole-balancing of a humanoid robot arm, and inverse-dynamics learning for a seven degree-of-freedom robot.

link (url) [BibTex]

2002

link (url) [BibTex]


no image
Reliable stair climbing in the simple hexapod ’RHex’

Moore, E. Z., Campbell, D., Grimminger, F., Buehler, M.

In Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292), 3, pages: 2222-2227 vol.3, May 2002 (inproceedings)

DOI [BibTex]

DOI [BibTex]


no image
Movement imitation with nonlinear dynamical systems in humanoid robots

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

In International Conference on Robotics and Automation (ICRA2002), Washinton, May 11-15 2002, 2002, clmc (inproceedings)

Abstract
Locally weighted learning (LWL) is a class of statistical learning techniques that provides useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of robotic systems. This paper introduces several LWL algorithms that have been tested successfully in real-time learning of complex robot tasks. We discuss two major classes of LWL, memory-based LWL and purely incremental LWL that does not need to remember any data explicitly. In contrast to the traditional beliefs that LWL methods cannot work well in high-dimensional spaces, we provide new algorithms that have been tested in up to 50 dimensional learning problems. The applicability of our LWL algorithms is demonstrated in various robot learning examples, including the learning of devil-sticking, pole-balancing of a humanoid robot arm, and inverse-dynamics learning for a seven degree-of-freedom robot.

link (url) [BibTex]

link (url) [BibTex]


no image
A locally weighted learning composite adaptive controller with structure adaptation

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

In IEEE International Conference on Intelligent Robots and Systems (IROS 2002), Lausanne, Sept.30-Oct.4 2002, 2002, clmc (inproceedings)

Abstract
This paper introduces a provably stable adaptive learning controller which employs nonlinear function approximation with automatic growth of the learning network according to the nonlinearities and the working domain of the control system. The unknown function in the dynamical system is approximated by piecewise linear models using a nonparametric regression technique. Local models are allocated as necessary and their parameters are optimized on-line. Inspired by composite adaptive control methods, the pro-posed learning adaptive control algorithm uses both the tracking error and the estimation error to up-date the parameters. We provide Lyapunov analyses that demonstrate the stability properties of the learning controller. Numerical simulations illustrate rapid convergence of the tracking error and the automatic structure adaptation capability of the function approximator. This paper introduces a provably stable adaptive learning controller which employs nonlinear function approximation with automatic growth of the learning network according to the nonlinearities and the working domain of the control system. The unknown function in the dynamical system is approximated by piecewise linear models using a nonparametric regression technique. Local models are allocated as necessary and their parameters are optimized on-line. Inspired by composite adaptive control methods, the pro-posed learning adaptive control algorithm uses both the tracking error and the estimation error to up-date the parameters. We provide Lyapunov analyses that demonstrate the stability properties of the learning controller. Numerical simulations illustrate rapid convergence of the tracking error and the automatic structure adaptation capability of the function approximator

link (url) [BibTex]

link (url) [BibTex]

1997


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. 

link (url) [BibTex]

1997

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. 

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.

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

link (url) [BibTex]

link (url) [BibTex]

1994


no image
Robot learning by nonparametric regression

Schaal, S., Atkeson, C. G.

In Proceedings of the International Conference on Intelligent Robots and Systems (IROS’94), pages: 478-485, Munich Germany, 1994, clmc (inproceedings)

Abstract
We present an approach to robot learning grounded on a nonparametric regression technique, locally weighted regression. The model of the task to be performed is represented by infinitely many local linear models, i.e., the (hyper-) tangent planes at every query point. Such a model, however, is only generated when a query is performed and is not retained. This is in contrast to other methods using a finite set of linear models to accomplish a piecewise linear model. Architectural parameters of our approach, such as distance metrics, are also a function of the current query point instead of being global. Statistical tests are presented for when a local model is good enough such that it can be reliably used to build a local controller. These statistical measures also direct the exploration of the robot. We explicitly deal with the case where prediction accuracy requirements exist during exploration: By gradually shifting a center of exploration and controlling the speed of the shift with local prediction accuracy, a goal-directed exploration of state space takes place along the fringes of the current data support until the task goal is achieved. We illustrate this approach by describing how it has been used to enable a robot to learn a challenging juggling task: Within 40 to 100 trials the robot accomplished the task goal starting out with no initial experiences.

[BibTex]

1994

[BibTex]


no image
Assessing the quality of learned local models

Schaal, S., Atkeson, C. G.

In Advances in Neural Information Processing Systems 6, pages: 160-167, (Editors: Cowan, J.;Tesauro, G.;Alspector, J.), Morgan Kaufmann, San Mateo, CA, 1994, clmc (inproceedings)

Abstract
An approach is presented to learning high dimensional functions in the case where the learning algorithm can affect the generation of new data. A local modeling algorithm, locally weighted regression, is used to represent the learned function. Architectural parameters of the approach, such as distance metrics, are also localized and become a function of the query point instead of being global. Statistical tests are given for when a local model is good enough and sampling should be moved to a new area. Our methods explicitly deal with the case where prediction accuracy requirements exist during exploration: By gradually shifting a "center of exploration" and controlling the speed of the shift with local prediction accuracy, a goal-directed exploration of state space takes place along the fringes of the current data support until the task goal is achieved. We illustrate this approach with simulation results and results from a real robot learning a complex juggling task.

link (url) [BibTex]

link (url) [BibTex]


no image
Memory-based robot learning

Schaal, S., Atkeson, C. G.

In IEEE International Conference on Robotics and Automation, 3, pages: 2928-2933, San Diego, CA, 1994, clmc (inproceedings)

Abstract
We present a memory-based local modeling approach to robot learning using a nonparametric regression technique, locally weighted regression. The model of the task to be performed is represented by infinitely many local linear models, the (hyper-) tangent planes at every query point. This is in contrast to other methods using a finite set of linear models to accomplish a piece-wise linear model. Architectural parameters of our approach, such as distance metrics, are a function of the current query point instead of being global. Statistical tests are presented for when a local model is good enough such that it can be reliably used to build a local controller. These statistical measures also direct the exploration of the robot. We explicitly deal with the case where prediction accuracy requirements exist during exploration: By gradually shifting a center of exploration and controlling the speed of the shift with local prediction accuracy, a goal-directed exploration of state space takes place along the fringes of the current data support until the task goal is achieved. We illustrate this approach by describing how it has been used to enable a robot to learn a challenging juggling task: within 40 to 100 trials the robot accomplished the task goal starting out with no initial experiences.

[BibTex]

[BibTex]


no image
Nonparametric regression for learning

Schaal, S.

In Conference on Adaptive Behavior and Learning, Center of Interdisciplinary Research (ZIF) Bielefeld Germany, also technical report TR-H-098 of the ATR Human Information Processing Research Laboratories, 1994, clmc (inproceedings)

Abstract
In recent years, learning theory has been increasingly influenced by the fact that many learning algorithms have at least in part a comprehensive interpretation in terms of well established statistical theories. Furthermore, with little modification, several statistical methods can be directly cast into learning algorithms. One family of such methods stems from nonparametric regression. This paper compares nonparametric learning with the more widely used parametric counterparts and investigates how these two families differ in their properties and their applicability. 

link (url) [BibTex]

link (url) [BibTex]

1992


no image
What should be learned?

Schaal, S., Atkeson, C. G., Botros, S.

In Proceedings of Seventh Yale Workshop on Adaptive and Learning Systems, pages: 199-204, New Haven, CT, May 20-22, 1992, clmc (inproceedings)

[BibTex]

1992

[BibTex]