Header logo is


2020


no image
Automatic Discovery of Interpretable Planning Strategies

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

May 2020 (article) Submitted

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

re

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


no image
Advancing Rational Analysis to the Algorithmic Level

Lieder, F., Griffiths, T. L.

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

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

re

Advancing rational analysis to the algorithmic level DOI [BibTex]

Advancing rational analysis to the algorithmic level DOI [BibTex]


no image
Learning to Overexert Cognitive Control in a Stroop Task

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

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

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

re

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

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


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

Lieder, F., Iwama, G.

January 2020 (article) Submitted

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

re

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


no image
Analytical classical density functionals from an equation learning network

Lin, S., Martius, G., Oettel, M.

The Journal of Chemical Physics, 152(2):021102, 2020, arXiv preprint \url{https://arxiv.org/abs/1910.12752} (article)

al

Preprint_PDF DOI [BibTex]

Preprint_PDF DOI [BibTex]


Wearable and Stretchable Strain Sensors: Materials, Sensing Mechanisms, and Applications
Wearable and Stretchable Strain Sensors: Materials, Sensing Mechanisms, and Applications

Souri, H., Banerjee, H., Jusufi, A., Radacsi, N., Stokes, A. A., Park, I., Sitti, M., Amjadi, M.

Advanced Intelligent Systems, 2020 (article)

bio pi

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Combining learned and analytical models for predicting action effects from sensory data
Combining learned and analytical models for predicting action effects from sensory data

Kloss, A., Schaal, S., Bohg, J.

International Journal of Robotics Research, 2020 (article) Accepted

Abstract
One of the most basic skills a robot should possess is predicting the effect of physical interactions with objects in the environment. This enables optimal action selection to reach a certain goal state. Traditionally, dynamics are approximated by physics-based analytical models. These models rely on specific state representations that may be hard to obtain from raw sensory data, especially if no knowledge of the object shape is assumed. More recently, we have seen learning approaches that can predict the effect of complex physical interactions directly from sensory input. It is however an open question how far these models generalize beyond their training data. In this work, we investigate the advantages and limitations of neural network based learning approaches for predicting the effects of actions based on sensory input and show how analytical and learned models can be combined to leverage the best of both worlds. As physical interaction task, we use planar pushing, for which there exists a well-known analytical model and a large real-world dataset. We propose to use a convolutional neural network to convert raw depth images or organized point clouds into a suitable representation for the analytical model and compare this approach to using neural networks for both, perception and prediction. A systematic evaluation of the proposed approach on a very large real-world dataset shows two main advantages of the hybrid architecture. Compared to a pure neural network, it significantly (i) reduces required training data and (ii) improves generalization to novel physical interaction.

am

arXiv pdf link (url) [BibTex]


no image
Fish-like aquatic propulsion studied using a pneumatically-actuated soft-robotic model

Wolf, Z., Jusufi, A., Vogt, D. M., Lauder, G. V.

Bioinspiration & Biomimetics, 15(4):046008, Inst. of Physics, London, 2020 (article)

bio

DOI [BibTex]

DOI [BibTex]


Safe and Fast Tracking on a Robot Manipulator: Robust MPC and Neural Network Control
Safe and Fast Tracking on a Robot Manipulator: Robust MPC and Neural Network Control

Nubert, J., Koehler, J., Berenz, V., Allgower, F., Trimpe, S.

IEEE Robotics and Automation Letters, 2020 (article) Accepted

Abstract
Fast feedback control and safety guarantees are essential in modern robotics. We present an approach that achieves both by combining novel robust model predictive control (MPC) with function approximation via (deep) neural networks (NNs). The result is a new approach for complex tasks with nonlinear, uncertain, and constrained dynamics as are common in robotics. Specifically, we leverage recent results in MPC research to propose a new robust setpoint tracking MPC algorithm, which achieves reliable and safe tracking of a dynamic setpoint while guaranteeing stability and constraint satisfaction. The presented robust MPC scheme constitutes a one-layer approach that unifies the often separated planning and control layers, by directly computing the control command based on a reference and possibly obstacle positions. As a separate contribution, we show how the computation time of the MPC can be drastically reduced by approximating the MPC law with a NN controller. The NN is trained and validated from offline samples of the MPC, yielding statistical guarantees, and used in lieu thereof at run time. Our experiments on a state-of-the-art robot manipulator are the first to show that both the proposed robust and approximate MPC schemes scale to real-world robotic systems.

am ics

arXiv PDF DOI [BibTex]

arXiv PDF DOI [BibTex]

2017


Interactive Perception: Leveraging Action in Perception and Perception in Action
Interactive Perception: Leveraging Action in Perception and Perception in Action

Bohg, J., Hausman, K., Sankaran, B., Brock, O., Kragic, D., Schaal, S., Sukhatme, G.

IEEE Transactions on Robotics, 33, pages: 1273-1291, December 2017 (article)

Abstract
Recent approaches in robotics follow the insight that perception is facilitated by interactivity with the environment. These approaches are subsumed under the term of Interactive Perception (IP). We argue that IP provides the following benefits: (i) any type of forceful interaction with the environment creates a new type of informative sensory signal that would otherwise not be present and (ii) any prior knowledge about the nature of the interaction supports the interpretation of the signal. This is facilitated by knowledge of the regularity in the combined space of sensory information and action parameters. The goal of this survey is to postulate this as a principle and collect evidence in support by analyzing and categorizing existing work in this area. We also provide an overview of the most important applications of Interactive Perception. We close this survey by discussing the remaining open questions. Thereby, we hope to define a field and inspire future work.

am

arXiv DOI Project Page [BibTex]

2017


arXiv DOI Project Page [BibTex]


Acquiring Target Stacking Skills by Goal-Parameterized Deep Reinforcement Learning
Acquiring Target Stacking Skills by Goal-Parameterized Deep Reinforcement Learning

Li, W., Bohg, J., Fritz, M.

arXiv, November 2017 (article) Submitted

Abstract
Understanding physical phenomena is a key component of human intelligence and enables physical interaction with previously unseen environments. In this paper, we study how an artificial agent can autonomously acquire this intuition through interaction with the environment. We created a synthetic block stacking environment with physics simulation in which the agent can learn a policy end-to-end through trial and error. Thereby, we bypass to explicitly model physical knowledge within the policy. We are specifically interested in tasks that require the agent to reach a given goal state that may be different for every new trial. To this end, we propose a deep reinforcement learning framework that learns policies which are parametrized by a goal. We validated the model on a toy example navigating in a grid world with different target positions and in a block stacking task with different target structures of the final tower. In contrast to prior work, our policies show better generalization across different goals.

am

arXiv [BibTex]


no image
Event-based State Estimation: An Emulation-based Approach

Trimpe, S.

IET Control Theory & Applications, 11(11):1684-1693, July 2017 (article)

Abstract
An event-based state estimation approach for reducing communication in a networked control system is proposed. Multiple distributed sensor agents observe a dynamic process and sporadically transmit their measurements to estimator agents over a shared bus network. Local event-triggering protocols ensure that data is transmitted only when necessary to meet a desired estimation accuracy. The event-based design is shown to emulate the performance of a centralised state observer design up to guaranteed bounds, but with reduced communication. The stability results for state estimation are extended to the distributed control system that results when the local estimates are used for feedback control. Results from numerical simulations and hardware experiments illustrate the effectiveness of the proposed approach in reducing network communication.

am ics

arXiv Supplementary material PDF DOI Project Page [BibTex]

arXiv Supplementary material PDF DOI Project Page [BibTex]


Probabilistic Articulated Real-Time Tracking for Robot Manipulation
Probabilistic Articulated Real-Time Tracking for Robot Manipulation

(Best Paper of RA-L 2017, Finalist of Best Robotic Vision Paper Award of ICRA 2017)

Garcia Cifuentes, C., Issac, J., Wüthrich, M., Schaal, S., Bohg, J.

IEEE Robotics and Automation Letters (RA-L), 2(2):577-584, April 2017 (article)

Abstract
We propose a probabilistic filtering method which fuses joint measurements with depth images to yield a precise, real-time estimate of the end-effector pose in the camera frame. This avoids the need for frame transformations when using it in combination with visual object tracking methods. Precision is achieved by modeling and correcting biases in the joint measurements as well as inaccuracies in the robot model, such as poor extrinsic camera calibration. We make our method computationally efficient through a principled combination of Kalman filtering of the joint measurements and asynchronous depth-image updates based on the Coordinate Particle Filter. We quantitatively evaluate our approach on a dataset recorded from a real robotic platform, annotated with ground truth from a motion capture system. We show that our approach is robust and accurate even under challenging conditions such as fast motion, significant and long-term occlusions, and time-varying biases. We release the dataset along with open-source code of our approach to allow for quantitative comparison with alternative approaches.

am

arXiv video code and dataset video PDF DOI Project Page [BibTex]


no image
Anticipatory Action Selection for Human-Robot Table Tennis

Wang, Z., Boularias, A., Mülling, K., Schölkopf, B., Peters, J.

Artificial Intelligence, 247, pages: 399-414, 2017, Special Issue on AI and Robotics (article)

Abstract
Abstract Anticipation can enhance the capability of a robot in its interaction with humans, where the robot predicts the humans' intention for selecting its own action. We present a novel framework of anticipatory action selection for human-robot interaction, which is capable to handle nonlinear and stochastic human behaviors such as table tennis strokes and allows the robot to choose the optimal action based on prediction of the human partner's intention with uncertainty. The presented framework is generic and can be used in many human-robot interaction scenarios, for example, in navigation and human-robot co-manipulation. In this article, we conduct a case study on human-robot table tennis. Due to the limited amount of time for executing hitting movements, a robot usually needs to initiate its hitting movement before the opponent hits the ball, which requires the robot to be anticipatory based on visual observation of the opponent's movement. Previous work on Intention-Driven Dynamics Models (IDDM) allowed the robot to predict the intended target of the opponent. In this article, we address the problem of action selection and optimal timing for initiating a chosen action by formulating the anticipatory action selection as a Partially Observable Markov Decision Process (POMDP), where the transition and observation are modeled by the \{IDDM\} framework. We present two approaches to anticipatory action selection based on the \{POMDP\} formulation, i.e., a model-free policy learning method based on Least-Squares Policy Iteration (LSPI) that employs the \{IDDM\} for belief updates, and a model-based Monte-Carlo Planning (MCP) method, which benefits from the transition and observation model by the IDDM. Experimental results using real data in a simulated environment show the importance of anticipatory action selection, and that \{POMDPs\} are suitable to formulate the anticipatory action selection problem by taking into account the uncertainties in prediction. We also show that existing algorithms for POMDPs, such as \{LSPI\} and MCP, can be applied to substantially improve the robot's performance in its interaction with humans.

am ei

DOI Project Page [BibTex]

DOI Project Page [BibTex]


no image
Self-Organized Behavior Generation for Musculoskeletal Robots

Der, R., Martius, G.

Frontiers in Neurorobotics, 11, pages: 8, 2017 (article)

al

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2016


A New Perspective and Extension of the Gaussian Filter
A New Perspective and Extension of the Gaussian Filter

Wüthrich, M., Trimpe, S., Garcia Cifuentes, C., Kappler, D., Schaal, S.

The International Journal of Robotics Research, 35(14):1731-1749, December 2016 (article)

Abstract
The Gaussian Filter (GF) is one of the most widely used filtering algorithms; instances are the Extended Kalman Filter, the Unscented Kalman Filter and the Divided Difference Filter. The GF represents the belief of the current state by a Gaussian distribution, whose mean is an affine function of the measurement. We show that this representation can be too restrictive to accurately capture the dependences in systems with nonlinear observation models, and we investigate how the GF can be generalized to alleviate this problem. To this end, we view the GF as the solution to a constrained optimization problem. From this new perspective, the GF is seen as a special case of a much broader class of filters, obtained by relaxing the constraint on the form of the approximate posterior. On this basis, we outline some conditions which potential generalizations have to satisfy in order to maintain the computational efficiency of the GF. We propose one concrete generalization which corresponds to the standard GF using a pseudo measurement instead of the actual measurement. Extending an existing GF implementation in this manner is trivial. Nevertheless, we show that this small change can have a major impact on the estimation accuracy.

am ics

PDF DOI Project Page [BibTex]

2016


PDF DOI Project Page [BibTex]


no image
Probabilistic Inference for Determining Options in Reinforcement Learning

Daniel, C., van Hoof, H., Peters, J., Neumann, G.

Machine Learning, Special Issue, 104(2):337-357, (Editors: Gärtner, T., Nanni, M., Passerini, A. and Robardet, C.), European Conference on Machine Learning im Machine Learning, Journal Track, 2016, Best Student Paper Award of ECML-PKDD 2016 (article)

am ei

DOI Project Page [BibTex]

DOI Project Page [BibTex]


no image
Event-based Sampling for Reducing Communication Load in Realtime Human Motion Analysis by Wireless Inertial Sensor Networks

Laidig, D., Trimpe, S., Seel, T.

Current Directions in Biomedical Engineering, 2(1):711-714, De Gruyter, 2016 (article)

am ics

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Momentum Control with Hierarchical Inverse Dynamics on a Torque-Controlled Humanoid

Herzog, A., Rotella, N., Mason, S., Grimminger, F., Schaal, S., Righetti, L.

Autonomous Robots, 40(3):473-491, 2016 (article)

Abstract
Hierarchical inverse dynamics based on cascades of quadratic programs have been proposed for the control of legged robots. They have important benefits but to the best of our knowledge have never been implemented on a torque controlled humanoid where model inaccuracies, sensor noise and real-time computation requirements can be problematic. Using a reformulation of existing algorithms, we propose a simplification of the problem that allows to achieve real-time control. Momentum-based control is integrated in the task hierarchy and a LQR design approach is used to compute the desired associated closed-loop behavior and improve performance. Extensive experiments on various balancing and tracking tasks show very robust performance in the face of unknown disturbances, even when the humanoid is standing on one foot. Our results demonstrate that hierarchical inverse dynamics together with momentum control can be efficiently used for feedback control under real robot conditions.

am mg

link (url) DOI [BibTex]


no image
Bioinspired Motor Control for Articulated Robots [From the Guest Editors]

Vitiello, Nicola, Ijspeert, Auke J, Schaal, S.

IEEE Robotics {\&} Automation Magazine, 23(1):20-21, 2016 (article)

am

[BibTex]

[BibTex]

2012


no image
From Dynamic Movement Primitives to Associative Skill Memories

Pastor, P., Kalakrishnan, M., Meier, F., Stulp, F., Buchli, J., Theodorou, E., Schaal, S.

Robotics and Autonomous Systems, 2012 (article)

am

Project Page [BibTex]

2012


Project Page [BibTex]


no image
Tail-assisted pitch control in lizards, robots and dinosaurs

Libby, T., Moore, T., Chang, E., Li, D., Cohen, D., Jusufi, A., Full, R.

Nature, 2012 (article)

bio

link (url) [BibTex]

link (url) [BibTex]


no image
Rapid Inversion: Running Animals and Robots Swing like a Pendulum under Ledges

Mongeau, J., McRae, B., Jusufi, A., Birkmeyer, P., Hoover, A., Fearing, R.

PLoS One, 2012 (article)

bio

link (url) [BibTex]

link (url) [BibTex]


no image
Variants of guided self-organization for robot control

Martius, G., Herrmann, J.

Theory in Biosci., 131(3):129-137, Springer Berlin / Heidelberg, 2012 (article)

al

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Model-free reinforcement learning of impedance control in stochastic environments

Stulp, Freek, Buchli, Jonas, Ellmer, Alice, Mistry, Michael, Theodorou, Evangelos A., Schaal, S.

Autonomous Mental Development, IEEE Transactions on, 4(4):330-341, 2012 (article)

am

[BibTex]

[BibTex]


no image
Reinforcement Learning with Sequences of Motion Primitives for Robust Manipulation

Stulp, F., Theodorou, E., Schaal, S.

IEEE Transactions on Robotics, 2012 (article)

am

[BibTex]

[BibTex]

2011


no image
Learning, planning, and control for quadruped locomotion over challenging terrain

Kalakrishnan, Mrinal, Buchli, Jonas, Pastor, Peter, Mistry, Michael, Schaal, S.

International Journal of Robotics Research, 30(2):236-258, February 2011 (article)

am

[BibTex]

2011


[BibTex]


no image
Aerial righting reflexes in flightless animals

Jusufi, A., Zeng, Y., Full, R., Dudley, R.

Integ. Comp. Biol. , 2011 (article)

bio

[BibTex]

[BibTex]


no image
Bayesian robot system identification with input and output noise

Ting, J., D’Souza, A., Schaal, S.

Neural Networks, 24(1):99-108, 2011, clmc (article)

Abstract
For complex robots such as humanoids, model-based control is highly beneficial for accurate tracking while keeping negative feedback gains low for compliance. However, in such multi degree-of-freedom lightweight systems, conventional identification of rigid body dynamics models using CAD data and actuator models is inaccurate due to unknown nonlinear robot dynamic effects. An alternative method is data-driven parameter estimation, but significant noise in measured and inferred variables affects it adversely. Moreover, standard estimation procedures may give physically inconsistent results due to unmodeled nonlinearities or insufficiently rich data. This paper addresses these problems, proposing a Bayesian system identification technique for linear or piecewise linear systems. Inspired by Factor Analysis regression, we develop a computationally efficient variational Bayesian regression algorithm that is robust to ill-conditioned data, automatically detects relevant features, and identifies input and output noise. We evaluate our approach on rigid body parameter estimation for various robotic systems, achieving an error of up to three times lower than other state-of-the-art machine learning methods

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning variable impedance control

Buchli, J., Stulp, F., Theodorou, E., Schaal, S.

International Journal of Robotics Research, 2011, clmc (article)

Abstract
One of the hallmarks of the performance, versatility, and robustness of biological motor control is the ability to adapt the impedance of the overall biomechanical system to different task requirements and stochastic disturbances. A transfer of this principle to robotics is desirable, for instance to enable robots to work robustly and safely in everyday human environments. It is, however, not trivial to derive variable impedance controllers for practical high degree-of-freedom (DOF) robotic tasks. In this contribution, we accomplish such variable impedance control with the reinforcement learning (RL) algorithm PISq ({f P}olicy {f I}mprovement with {f P}ath {f I}ntegrals). PISq is a model-free, sampling based learning method derived from first principles of stochastic optimal control. The PISq algorithm requires no tuning of algorithmic parameters besides the exploration noise. The designer can thus fully focus on cost function design to specify the task. From the viewpoint of robotics, a particular useful property of PISq is that it can scale to problems of many DOFs, so that reinforcement learning on real robotic systems becomes feasible. We sketch the PISq algorithm and its theoretical properties, and how it is applied to gain scheduling for variable impedance control. We evaluate our approach by presenting results on several simulated and real robots. We consider tasks involving accurate tracking through via-points, and manipulation tasks requiring physical contact with the environment. In these tasks, the optimal strategy requires both tuning of a reference trajectory emph{and} the impedance of the end-effector. The results show that we can use path integral based reinforcement learning not only for planning but also to derive variable gain feedback controllers in realistic scenarios. Thus, the power of variable impedance control is made available to a wide variety of robotic systems and practical applications.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Understanding haptics by evolving mechatronic systems

Loeb, G. E., Tsianos, G.A., Fishel, J.A., Wettels, N., Schaal, S.

Progress in Brain Research, 192, pages: 129, 2011 (article)

am

[BibTex]

[BibTex]


no image
Intelligent Mobility—Autonomous Outdoor Robotics at the DFKI

Joyeux, S., Schwendner, J., Kirchner, F., Babu, A., Grimminger, F., Machowinski, J., Paranhos, P., Gaudig, C.

KI, 25(2):133-139, May 2011 (article)

am

DOI [BibTex]

DOI [BibTex]

2010


no image
Policy learning algorithmis for motor learning (Algorithmen zum automatischen Erlernen von Motorfähigkigkeiten)

Peters, J., Kober, J., Schaal, S.

Automatisierungstechnik, 58(12):688-694, 2010, clmc (article)

Abstract
Robot learning methods which allow au- tonomous robots to adapt to novel situations have been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, to date, learning techniques have yet to ful- fill 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. If possible, scaling was usually only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general ap- proach 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 algo- rithms 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 structu- res for task representation and execution.

am

link (url) [BibTex]


no image
A Bayesian approach to nonlinear parameter identification for rigid-body dynamics

Ting, J., DSouza, A., Schaal, S.

Neural Networks, 2010, clmc (article)

Abstract
For complex robots such as humanoids, model-based control is highly beneficial for accurate tracking while keeping negative feedback gains low for compliance. However, in such multi degree-of-freedom lightweight systems, conventional identification of rigid body dynamics models using CAD data and actuator models is inaccurate due to unknown nonlinear robot dynamic effects. An alternative method is data-driven parameter estimation, but significant noise in measured and inferred variables affects it adversely. Moreover, standard estimation procedures may give physically inconsistent results due to unmodeled nonlinearities or insufficiently rich data. This paper addresses these problems, proposing a Bayesian system identification technique for linear or piecewise linear systems. Inspired by Factor Analysis regression, we develop a computationally efficient variational Bayesian regression algorithm that is robust to ill-conditioned data, automatically detects relevant features, and identifies input and output noise. We evaluate our approach on rigid body parameter estimation for various robotic systems, achieving an error of up to three times lower than other state-of-the-art machine learning methods.

am

link (url) [BibTex]


no image
A first optimal control solution for a complex, nonlinear, tendon driven neuromuscular finger model

Theodorou, E. A., Todorov, E., Valero-Cuevas, F.

Proceedings of the ASME 2010 Summer Bioengineering Conference August 30-September 2, 2010, Naples, Florida, USA, 2010, clmc (article)

Abstract
In this work we present the first constrained stochastic op- timal feedback controller applied to a fully nonlinear, tendon driven index finger model. Our model also takes into account an extensor mechanism, and muscle force-length and force-velocity properties. We show this feedback controller is robust to noise and perturbations to the dynamics, while successfully handling the nonlinearities and high dimensionality of the system. By ex- tending prior methods, we are able to approximate physiological realism by ensuring positivity of neural commands and tendon tensions at all timesthus can, for the first time, use the optimal control framework to predict biologically plausible tendon tensions for a nonlinear neuromuscular finger model. METHODS 1 Muscle Model The rigid-body triple pendulum finger model with slightly viscous joints is actuated by Hill-type muscle models. Joint torques are generated by the seven muscles of the index fin-

am

PDF [BibTex]

PDF [BibTex]


no image
Efficient learning and feature detection in high dimensional regression

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

Neural Computation, 22, pages: 831-886, 2010, clmc (article)

Abstract
We present a novel algorithm for efficient learning and feature selection in high- dimensional regression problems. We arrive at this model through a modification of the standard regression model, enabling us to derive a probabilistic version of the well-known statistical regression technique of backfitting. Using the Expectation- Maximization algorithm, along with variational approximation methods to overcome intractability, we extend our algorithm to include automatic relevance detection of the input features. This Variational Bayesian Least Squares (VBLS) approach retains its simplicity as a linear model, but offers a novel statistically robust â??black- boxâ? approach to generalized linear regression with high-dimensional inputs. It can be easily extended to nonlinear regression and classification problems. In particular, we derive the framework of sparse Bayesian learning, e.g., the Relevance Vector Machine, with VBLS at its core, offering significant computational and robustness advantages for this class of methods. We evaluate our algorithm on synthetic and neurophysiological data sets, as well as on standard regression and classification benchmark data sets, comparing it with other competitive statistical approaches and demonstrating its suitability as a drop-in replacement for other generalized linear regression techniques.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Stochastic Differential Dynamic Programming

Theodorou, E., Tassa, Y., Todorov, E.

In the proceedings of American Control Conference (ACC 2010) , 2010, clmc (article)

Abstract
We present a generalization of the classic Differential Dynamic Programming algorithm. We assume the existence of state- and control-dependent process noise, and proceed to derive the second-order expansion of the cost-to-go. Despite having quartic and cubic terms in the initial expression, we show that these vanish, leaving us with the same quadratic structure as standard DDP.

am

PDF [BibTex]

PDF [BibTex]


no image
Learning control in robotics – trajectory-based opitimal control techniques

Schaal, S., Atkeson, C. G.

Robotics and Automation Magazine, 17(2):20-29, 2010, clmc (article)

Abstract
In a not too distant future, robots will be a natural part of daily life in human society, providing assistance in many areas ranging from clinical applications, education and care giving, to normal household environments [1]. It is hard to imagine that all possible tasks can be preprogrammed in such robots. Robots need to be able to learn, either by themselves or with the help of human supervision. Additionally, wear and tear on robots in daily use needs to be automatically compensated for, which requires a form of continuous self-calibration, another form of learning. Finally, robots need to react to stochastic and dynamic environments, i.e., they need to learn how to optimally adapt to uncertainty and unforeseen changes. Robot learning is going to be a key ingredient for the future of autonomous robots. While robot learning covers a rather large field, from learning to perceive, to plan, to make decisions, etc., we will focus this review on topics of learning control, in particular, as it is concerned with learning control in simulated or actual physical robots. In general, learning control refers to the process of acquiring a control strategy for a particular control system and a particular task by trial and error. Learning control is usually distinguished from adaptive control [2] in that the learning system can have rather general optimization objectivesâ??not just, e.g., minimal tracking errorâ??and is permitted to fail during the process of learning, while adaptive control emphasizes fast convergence without failure. Thus, learning control resembles the way that humans and animals acquire new movement strategies, while adaptive control is a special case of learning control that fulfills stringent performance constraints, e.g., as needed in life-critical systems like airplanes. Learning control has been an active topic of research for at least three decades. However, given the lack of working robots that actually use learning components, more work needs to be done before robot learning will make it beyond the laboratory environment. This article will survey some ongoing and past activities in robot learning to assess where the field stands and where it is going. We will largely focus on nonwheeled robots and less on topics of state estimation, as typically explored in wheeled robots [3]â??6], and we emphasize learning in continuous state-action spaces rather than discrete state-action spaces [7], [8]. We will illustrate the different topics of robot learning with examples from our own research with anthropomorphic and humanoid robots.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Learning, planning, and control for quadruped locomotion over challenging terrain

Kalakrishnan, M., Buchli, J., Pastor, P., Mistry, M., Schaal, S.

International Journal of Robotics Research, 30(2):236-258, 2010, clmc (article)

Abstract
We present a control architecture for fast quadruped locomotion over rough terrain. We approach the problem by decomposing it into many sub-systems, in which we apply state-of-the-art learning, planning, optimization, and control techniques to achieve robust, fast locomotion. Unique features of our control strategy include: (1) a system that learns optimal foothold choices from expert demonstration using terrain templates, (2) a body trajectory optimizer based on the Zero- Moment Point (ZMP) stability criterion, and (3) a floating-base inverse dynamics controller that, in conjunction with force control, allows for robust, compliant locomotion over unperceived obstacles. We evaluate the performance of our controller by testing it on the LittleDog quadruped robot, over a wide variety of rough terrains of varying difficulty levels. The terrain that the robot was tested on includes rocks, logs, steps, barriers, and gaps, with obstacle sizes up to the leg length of the robot. We demonstrate the generalization ability of this controller by presenting results from testing performed by an independent external test team on terrain that has never been shown to us.

am

link (url) Project Page [BibTex]

link (url) Project Page [BibTex]

2001


no image
Synchronized robot drumming by neural oscillator

Kotosaka, S., Schaal, S.

Journal of the Robotics Society of Japan, 19(1):116-123, 2001, clmc (article)

Abstract
Sensory-motor integration is one of the key issues in robotics. In this paper, we propose an approach to rhythmic arm movement control that is synchronized with an external signal based on exploiting a simple neural oscillator network. Trajectory generation by the neural oscillator is a biologically inspired method that can allow us to generate a smooth and continuous trajectory. The parameter tuning of the oscillators is used to generate a synchronized movement with wide intervals. We adopted the method for the drumming task as an example task. By using this method, the robot can realize synchronized drumming with wide drumming intervals in real time. The paper also shows the experimental results of drumming by a humanoid robot.

am

[BibTex]

2001


[BibTex]


no image
Origins and violations of the 2/3 power law in rhythmic 3D movements

Schaal, S., Sternad, D.

Experimental Brain Research, 136, pages: 60-72, 2001, clmc (article)

Abstract
The 2/3 power law, the nonlinear relationship between tangential velocity and radius of curvature of the endeffector trajectory, has been suggested as a fundamental constraint of the central nervous system in the formation of rhythmic endpoint trajectories. However, studies on the 2/3 power law have largely been confined to planar drawing patterns of relatively small size. With the hypothesis that this strategy overlooks nonlinear effects that are constitutive in movement generation, the present experiments tested the validity of the power law in elliptical patterns which were not confined to a planar surface and which were performed by the unconstrained 7-DOF arm with significant variations in pattern size and workspace orientation. Data were recorded from five human subjects where the seven joint angles and the endpoint trajectories were analyzed. Additionally, an anthropomorphic 7-DOF robot arm served as a "control subject" whose endpoint trajectories were generated on the basis of the human joint angle data, modeled as simple harmonic oscillations. Analyses of the endpoint trajectories demonstrate that the power law is systematically violated with increasing pattern size, in both exponent and the goodness of fit. The origins of these violations can be explained analytically based on smooth rhythmic trajectory formation and the kinematic structure of the human arm. We conclude that in unconstrained rhythmic movements, the power law seems to be a by-product of a movement system that favors smooth trajectories, and that it is unlikely to serve as a primary movement generating principle. Our data rather suggests that subjects employed smooth oscillatory pattern generators in joint space to realize the required movement patterns.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Graph-matching vs. entropy-based methods for object detection
Neural Networks, 14(3):345-354, 2001, clmc (article)

Abstract
Labeled Graph Matching (LGM) has been shown successful in numerous ob-ject vision tasks. This method is the basis for arguably the best face recognition system in the world. We present an algorithm for visual pattern recognition that is an extension of LGM ("LGM+"). We compare the performance of LGM and LGM+ algorithms with a state of the art statistical method based on Mutual Information Maximization (MIM). We present an adaptation of the MIM method for multi-dimensional Gabor wavelet features. The three pattern recognition methods were evaluated on an object detection task, using a set of stimuli on which none of the methods had been tested previously. The results indicate that while the performance of the MIM method operating upon Gabor wavelets is superior to the same method operating on pixels and to LGM, it is surpassed by LGM+. LGM+ offers a significant improvement in performance over LGM without losing LGMâ??s virtues of simplicity, biological plausibility, and a computational cost that is 2-3 orders of magnitude lower than that of the MIM algorithm. 

am

link (url) [BibTex]

link (url) [BibTex]


no image
Biomimetic gaze stabilization based on feedback-error learning with nonparametric regression networks

Shibata, T., Schaal, S.

Neural Networks, 14(2):201-216, 2001, clmc (article)

Abstract
Oculomotor control in a humanoid robot faces similar problems as biological oculomotor systems, i.e. the stabilization of gaze in face of unknown perturbations of the body, selective attention, stereo vision, and dealing with large information processing delays. Given the nonlinearities of the geometry of binocular vision as well as the possible nonlinearities of the oculomotor plant, it is desirable to accomplish accurate control of these behaviors through learning approaches. This paper develops a learning control system for the phylogenetically oldest behaviors of oculomotor control, the stabilization reflexes of gaze. In a step-wise procedure, we demonstrate how control theoretic reasonable choices of control components result in an oculomotor control system that resembles the known functional anatomy of the primate oculomotor system. The core of the learning system is derived from the biologically inspired principle of feedback-error learning combined with a state-of-the-art non-parametric statistical learning network. With this circuitry, we demonstrate that our humanoid robot is able to acquire high performance visual stabilization reflexes after about 40 s of learning despite significant nonlinearities and processing delays in the system.

am

link (url) [BibTex]


no image
Fast learning of biomimetic oculomotor control with nonparametric regression networks (in Japanese)

Shibata, T., Schaal, S.

Journal of the Robotics Society of Japan, 19(4):468-479, 2001, clmc (article)

am

[BibTex]

[BibTex]


no image
Bouncing a ball: Tuning into dynamic stability

Sternad, D., Duarte, M., Katsumata, H., Schaal, S.

Journal of Experimental Psychology: Human Perception and Performance, 27(5):1163-1184, 2001, clmc (article)

Abstract
Rhythmically bouncing a ball with a racket was investigated and modeled with a nonlinear map. Model analyses provided a variable defining a dynamically stable solution that obviates computationally expensive corrections. Three experiments evaluated whether dynamic stability is optimized and what perceptual support is necessary for stable behavior. Two hypotheses were tested: (a) Performance is stable if racket acceleration is negative at impact, and (b) variability is lowest at an impact acceleration between -4 and -1 m/s2. In Experiment 1 participants performed the task, eyes open or closed, bouncing a ball confined to a 1-dimensional trajectory. Experiment 2 eliminated constraints on racket and ball trajectory. Experiment 3 excluded visual or haptic information. Movements were performed with negative racket accelerations in the range of highest stability. Performance with eyes closed was more variable, leaving acceleration unaffected. With haptic information, performance was more stable than with visual information alone.

am

[BibTex]

[BibTex]