Publications | Max Planck Institute for Intelligent Systems

2015

am ei Calandra, R., Ivaldi, S., Deisenroth, M., Peters, J. Learning Torque Control in Presence of Contacts using Tactile Sensing from Robot Skin In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 690-695, Humanoids, November 2015 (inproceedings)

Evaluation of Interactive Object Recognition with Tactile Sensing

Hoelscher, J., Peters, J., Hermans, T.

In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 310-317, Humanoids, November 2015 (inproceedings)

am ei

am ei Hoelscher, J., Peters, J., Hermans, T. Evaluation of Interactive Object Recognition with Tactile Sensing In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 310-317, Humanoids, November 2015 (inproceedings)

Optimizing Robot Striking Movement Primitives with Iterative Learning Control

Koc, O., Maeda, G., Neumann, G., Peters, J.

In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 80-87, Humanoids, November 2015 (inproceedings)

am ei

am ei Koc, O., Maeda, G., Neumann, G., Peters, J. Optimizing Robot Striking Movement Primitives with Iterative Learning Control In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 80-87, Humanoids, November 2015 (inproceedings)

A Comparison of Contact Distribution Representations for Learning to Predict Object Interactions

Leischnig, S., Luettgen, S., Kroemer, O., Peters, J.

In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 616-622, Humanoids, November 2015 (inproceedings)

am ei

am ei Leischnig, S., Luettgen, S., Kroemer, O., Peters, J. A Comparison of Contact Distribution Representations for Learning to Predict Object Interactions In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 616-622, Humanoids, November 2015 (inproceedings)

First-Person Tele-Operation of a Humanoid Robot

Fritsche, L., Unverzagt, F., Peters, J., Calandra, R.

In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 997-1002, Humanoids, November 2015 (inproceedings)

am ei

am ei Fritsche, L., Unverzagt, F., Peters, J., Calandra, R. First-Person Tele-Operation of a Humanoid Robot In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 997-1002, Humanoids, November 2015 (inproceedings)

Probabilistic Segmentation Applied to an Assembly Task

Lioutikov, R., Neumann, G., Maeda, G., Peters, J.

In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 533-540, Humanoids, November 2015 (inproceedings)

am ei

am ei Lioutikov, R., Neumann, G., Maeda, G., Peters, J. Probabilistic Segmentation Applied to an Assembly Task In 15th IEEE-RAS International Conference on Humanoid Robots, pages: 533-540, Humanoids, November 2015 (inproceedings)

Automatic LQR Tuning Based on Gaussian Process Optimization: Early Experimental Results

Marco, A., Hennig, P., Bohg, J., Schaal, S., Trimpe, S.

Machine Learning in Planning and Control of Robot Motion Workshop at the IEEE/RSJ International Conference on Intelligent Robots and Systems (iROS), pages: , , Machine Learning in Planning and Control of Robot Motion Workshop, October 2015 (conference)

Abstract

This paper proposes an automatic controller tuning framework based on linear optimal control combined with Bayesian optimization. With this framework, an initial set of controller gains is automatically improved according to a pre-defined performance objective evaluated from experimental data. The underlying Bayesian optimization algorithm is Entropy Search, which represents the latent objective as a Gaussian process and constructs an explicit belief over the location of the objective minimum. This is used to maximize the information gain from each experimental evaluation. Thus, this framework shall yield improved controllers with fewer evaluations compared to alternative approaches. A seven-degree-of-freedom robot arm balancing an inverted pole is used as the experimental demonstrator. Preliminary results of a low-dimensional tuning problem highlight the method’s potential for automatic controller tuning on robotic platforms.

am ei ics pn

am ei ics pn Marco, A., Hennig, P., Bohg, J., Schaal, S., Trimpe, S. Automatic LQR Tuning Based on Gaussian Process Optimization: Early Experimental Results Machine Learning in Planning and Control of Robot Motion Workshop at the IEEE/RSJ International Conference on Intelligent Robots and Systems (iROS), pages: , , Machine Learning in Planning and Control of Robot Motion Workshop, October 2015 (conference)

Stabilizing Novel Objects by Learning to Predict Tactile Slip

Veiga, F., van Hoof, H., Peters, J., Hermans, T.

In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 5065-5072, IROS, September 2015 (inproceedings)

am ei

am ei Veiga, F., van Hoof, H., Peters, J., Hermans, T. Stabilizing Novel Objects by Learning to Predict Tactile Slip In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 5065-5072, IROS, September 2015 (inproceedings)

Model-Free Probabilistic Movement Primitives for Physical Interaction

Paraschos, A., Rueckert, E., Peters, J., Neumann, G.

In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 2860-2866, IROS, September 2015 (inproceedings)

am ei

am ei Paraschos, A., Rueckert, E., Peters, J., Neumann, G. Model-Free Probabilistic Movement Primitives for Physical Interaction In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 2860-2866, IROS, September 2015 (inproceedings)

Combined Pose-Wrench and State Machine Representation for Modeling Robotic Assembly Skills

Wahrburg, A., Zeiss, S., Matthias, B., Peters, J., Ding, H.

In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 852-857, IROS, September 2015 (inproceedings)

am ei

am ei Wahrburg, A., Zeiss, S., Matthias, B., Peters, J., Ding, H. Combined Pose-Wrench and State Machine Representation for Modeling Robotic Assembly Skills In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 852-857, IROS, September 2015 (inproceedings)

Probabilistic Progress Prediction and Sequencing of Concurrent Movement Primitives

Manschitz, S., Kober, J., Gienger, M., Peters, J.

In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 449-455, IROS, September 2015 (inproceedings)

am ei

am ei Manschitz, S., Kober, J., Gienger, M., Peters, J. Probabilistic Progress Prediction and Sequencing of Concurrent Movement Primitives In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 449-455, IROS, September 2015 (inproceedings)

Reinforcement Learning vs Human Programming in Tetherball Robot Games

Parisi, S., Abdulsamad, H., Paraschos, A., Daniel, C., Peters, J.

In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 6428-6434, IROS, September 2015 (inproceedings)

am ei

am ei Parisi, S., Abdulsamad, H., Paraschos, A., Daniel, C., Peters, J. Reinforcement Learning vs Human Programming in Tetherball Robot Games In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 6428-6434, IROS, September 2015 (inproceedings)

Learning Motor Skills from Partially Observed Movements Executed at Different Speeds

Ewerton, M., Maeda, G., Peters, J., Neumann, G.

In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 456-463, IROS, September 2015 (inproceedings)

am ei

am ei Ewerton, M., Maeda, G., Peters, J., Neumann, G. Learning Motor Skills from Partially Observed Movements Executed at Different Speeds In Proceedings of the IEEE/RSJ Conference on Intelligent Robots and Systems, pages: 456-463, IROS, September 2015 (inproceedings)

Direct Loss Minimization Inverse Optimal Control

Doerr, A., Ratliff, N., Bohg, J., Toussaint, M., Schaal, S.

In Proceedings of Robotics: Science and Systems, Rome, Italy, Robotics: Science and Systems XI, July 2015 (inproceedings)

Abstract

Inverse Optimal Control (IOC) has strongly impacted the systems engineering process, enabling automated planner tuning through straightforward and intuitive demonstration. The most successful and established applications, though, have been in lower dimensional problems such as navigation planning where exact optimal planning or control is feasible. In higher dimensional systems, such as humanoid robots, research has made substantial progress toward generalizing the ideas to model free or locally optimal settings, but these systems are complicated to the point where demonstration itself can be difficult. Typically, real-world applications are restricted to at best noisy or even partial or incomplete demonstrations that prove cumbersome in existing frameworks. This work derives a very flexible method of IOC based on a form of Structured Prediction known as Direct Loss Minimization. The resulting algorithm is essentially Policy Search on a reward function that rewards similarity to demonstrated behavior (using Covariance Matrix Adaptation (CMA) in our experiments). Our framework blurs the distinction between IOC, other forms of Imitation Learning, and Reinforcement Learning, enabling us to derive simple, versatile, and practical algorithms that blend imitation and reinforcement signals into a unified framework. Our experiments analyze various aspects of its performance and demonstrate its efficacy on conveying preferences for motion shaping and combined reach and grasp quality optimization.

am ics

am ics Doerr, A., Ratliff, N., Bohg, J., Toussaint, M., Schaal, S. Direct Loss Minimization Inverse Optimal Control In Proceedings of Robotics: Science and Systems, Rome, Italy, Robotics: Science and Systems XI, July 2015 (inproceedings)

LMI-Based Synthesis for Distributed Event-Based State Estimation

Muehlebach, M., Trimpe, S.

In Proceedings of the American Control Conference, July 2015 (inproceedings)

Abstract

This paper presents an LMI-based synthesis procedure for distributed event-based state estimation. Multiple agents observe and control a dynamic process by sporadically exchanging data over a broadcast network according to an event-based protocol. In previous work [1], the synthesis of event-based state estimators is based on a centralized design. In that case three different types of communication are required: event-based communication of measurements, periodic reset of all estimates to their joint average, and communication of inputs. The proposed synthesis problem eliminates the communication of inputs as well as the periodic resets (under favorable circumstances) by accounting explicitly for the distributed structure of the control system.

am ics

am ics Muehlebach, M., Trimpe, S. LMI-Based Synthesis for Distributed Event-Based State Estimation In Proceedings of the American Control Conference, July 2015 (inproceedings)

Guaranteed H2 Performance in Distributed Event-Based State Estimation

Muehlebach, M., Trimpe, S.

In Proceeding of the First International Conference on Event-based Control, Communication, and Signal Processing, June 2015 (inproceedings)

am ics

am ics Muehlebach, M., Trimpe, S. Guaranteed H2 Performance in Distributed Event-Based State Estimation In Proceeding of the First International Conference on Event-based Control, Communication, and Signal Processing, June 2015 (inproceedings)

On the Choice of the Event Trigger in Event-based Estimation

Trimpe, S., Campi, M.

In Proceeding of the First International Conference on Event-based Control, Communication, and Signal Processing, June 2015 (inproceedings)

am ics

am ics Trimpe, S., Campi, M. On the Choice of the Event Trigger in Event-based Estimation In Proceeding of the First International Conference on Event-based Control, Communication, and Signal Processing, June 2015 (inproceedings)

Leveraging Big Data for Grasp Planning

Kappler, D., Bohg, B., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation, May 2015 (inproceedings)

Abstract

We propose a new large-scale database containing grasps that are applied to a large set of objects from numerous categories. These grasps are generated in simulation and are annotated with different grasp stability metrics. We use a descriptive and efficient representation of the local object shape at which each grasp is applied. Given this data, we present a two-fold analysis: (i) We use crowdsourcing to analyze the correlation of the metrics with grasp success as predicted by humans. The results show that the metric based on physics simulation is a more consistent predictor for grasp success than the standard Îµ-metric. The results also support the hypothesis that human labels are not required for good ground truth grasp data. Instead the physics-metric can be used to generate datasets in simulation that may then be used to bootstrap learning in the real world. (ii) We apply a deep learning method and show that it can better leverage the large-scale database for prediction of grasp success compared to logistic regression. Furthermore, the results suggest that labels based on the physics-metric are less noisy than those from the Îµ-metric and therefore lead to a better classification performance.

PDF data DOI Project Page [BibTex]

am Kappler, D., Bohg, B., Schaal, S. Leveraging Big Data for Grasp Planning In Proceedings of the IEEE International Conference on Robotics and Automation, May 2015 (inproceedings)

PDF data DOI Project Page [BibTex]

Event-based Estimation and Control for Remote Robot Operation with Reduced Communication

Trimpe, S., Buchli, J.

In Proceedings of the IEEE International Conference on Robotics and Automation, May 2015 (inproceedings)

Abstract

An event-based communication framework for remote operation of a robot via a bandwidth-limited network is proposed. The robot sends state and environment estimation data to the operator, and the operator transmits updated control commands or policies to the robot. Event-based communication protocols are designed to ensure that data is transmitted only when required: the robot sends new estimation data only if this yields a significant information gain at the operator, and the operator transmits an updated control policy only if this comes with a significant improvement in control performance. The developed framework is modular and can be used with any standard estimation and control algorithms. Simulation results of a robotic arm highlight its potential for an efficient use of limited communication resources, for example, in disaster response scenarios such as the DARPA Robotics Challenge.

am ics

am ics Trimpe, S., Buchli, J. Event-based Estimation and Control for Remote Robot Operation with Reduced Communication In Proceedings of the IEEE International Conference on Robotics and Automation, May 2015 (inproceedings)

arXiv Video Bayesian Filtering Framework Bayesian Object Tracking DOI Project Page [BibTex]

The Coordinate Particle Filter - A novel Particle Filter for High Dimensional Systems

Wüthrich, M., Bohg, J., Kappler, D., Pfreundt, C., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation, May 2015 (inproceedings)

Abstract

Parametric filters, such as the Extended Kalman Filter and the Unscented Kalman Filter, typically scale well with the dimensionality of the problem, but they are known to fail if the posterior state distribution cannot be closely approximated by a density of the assumed parametric form. For nonparametric filters, such as the Particle Filter, the converse holds. Such methods are able to approximate any posterior, but the computational requirements scale exponentially with the number of dimensions of the state space. In this paper, we present the Coordinate Particle Filter which alleviates this problem. We propose to compute the particle weights recursively, dimension by dimension. This allows us to explore one dimension at a time, and resample after each dimension if necessary. Experimental results on simulated as well as real data con- firm that the proposed method has a substantial performance advantage over the Particle Filter in high-dimensional systems where not all dimensions are highly correlated. We demonstrate the benefits of the proposed method for the problem of multi-object and robotic manipulator tracking.

am Wüthrich, M., Bohg, J., Kappler, D., Pfreundt, C., Schaal, S. The Coordinate Particle Filter - A novel Particle Filter for High Dimensional Systems In Proceedings of the IEEE International Conference on Robotics and Automation, May 2015 (inproceedings)

arXiv Video Bayesian Filtering Framework Bayesian Object Tracking DOI Project Page [BibTex]

Understanding the Geometry of Workspace Obstacles in Motion Optimization

Ratliff, N., Toussaint, M., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation, March 2015 (inproceedings)

am Ratliff, N., Toussaint, M., Schaal, S. Understanding the Geometry of Workspace Obstacles in Motion Optimization In Proceedings of the IEEE International Conference on Robotics and Automation, March 2015 (inproceedings)

Learning of Non-Parametric Control Policies with High-Dimensional State Features

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

In Proceedings of the 18th International Conference on Artificial Intelligence and Statistics, 38, pages: 995–1003, (Editors: Lebanon, G. and Vishwanathan, S.V.N. ), JMLR, AISTATS, 2015 (inproceedings)

am ei

am ei van Hoof, H., Peters, J., Neumann, G. Learning of Non-Parametric Control Policies with High-Dimensional State Features In Proceedings of the 18th International Conference on Artificial Intelligence and Statistics, 38, pages: 995–1003, (Editors: Lebanon, G. and Vishwanathan, S.V.N. ), JMLR, AISTATS, 2015 (inproceedings)

Data-Driven Online Decision Making for Autonomous Manipulation

Kappler, D., Pastor, P., Kalakrishnan, M., Wuthrich, M., Schaal, S.

In Proceedings of Robotics: Science and Systems, Rome, Italy, 2015 (inproceedings)

am Kappler, D., Pastor, P., Kalakrishnan, M., Wuthrich, M., Schaal, S. Data-Driven Online Decision Making for Autonomous Manipulation In Proceedings of Robotics: Science and Systems, Rome, Italy, 2015 (inproceedings)

Predicting Human Reaching Motion in Collaborative Tasks Using Inverse Optimal Control and Iterative Re-planning

Mainprice, J., Hayne, R., Berenson, D.

In Proceedings of the IEEE International Conference on Robotics and Automation, 2015 (inproceedings)

am Mainprice, J., Hayne, R., Berenson, D. Predicting Human Reaching Motion in Collaborative Tasks Using Inverse Optimal Control and Iterative Re-planning In Proceedings of the IEEE International Conference on Robotics and Automation, 2015 (inproceedings)

Semi-Autonomous 3rd-Hand Robot

Lopes, M., Peters, J., Piater, J., Toussaint, M., Baisero, A., Busch, B., Erkent, O., Kroemer, O., Lioutikov, R., Maeda, G., Mollard, Y., Munzer, T., Shukla, D.

In Workshop on Cognitive Robotics in Future Manufacturing Scenarios, European Robotics Forum, 2015 (inproceedings)

am ei

am ei Lopes, M., Peters, J., Piater, J., Toussaint, M., Baisero, A., Busch, B., Erkent, O., Kroemer, O., Lioutikov, R., Maeda, G., Mollard, Y., Munzer, T., Shukla, D. Semi-Autonomous 3rd-Hand Robot In Workshop on Cognitive Robotics in Future Manufacturing Scenarios, European Robotics Forum, 2015 (inproceedings)

Modeling interruption and resumption in a smartphone task: An ACT-R approach

Wirzberger, M., Russwinkel, N.

i-com, 14(2), Walter de Gruyter GmbH, 2015 (article)

Abstract

This research aims to inspect human cognition when being interrupted while performing a smartphone task with varying levels of mental demand. Due to its benefits especially in the early stages of interface development, a cognitive modeling approach is used. It applies the cognitive architecture ACT-R to shed light on task-related cognitive processing. The inspected task setting involves a shopping scenario, manipulating interruption via product advertisements and mental demands by the respective number of people shopping is done for. Model predictions are validated through a corresponding experimental setting with 62 human participants. Comparing model and human data in a defined set of performance-related parameters displays mixed results that indicate an acceptable fit – at least in some cases. Potential explanations for the observed differences are discussed at the end.

re Wirzberger, M., Russwinkel, N. Modeling interruption and resumption in a smartphone task: An ACT-R approach i-com, 14(2), Walter de Gruyter GmbH, 2015 (article)

Sensory synergy as environmental input integration

Alnajjar, F., Itkonen, M., Berenz, V., Tournier, M., Nagai, C., Shimoda, S.

Frontiers in Neuroscience, 8, pages: 436, 2015 (article)

Abstract

The development of a method to feed proper environmental inputs back to the central nervous system (CNS) remains one of the challenges in achieving natural movement when part of the body is replaced with an artificial device. Muscle synergies are widely accepted as a biologically plausible interpretation of the neural dynamics between the CNS and the muscular system. Yet the sensorineural dynamics of environmental feedback to the CNS has not been investigated in detail. In this study, we address this issue by exploring the concept of sensory synergy. In contrast to muscle synergy, we hypothesize that sensory synergy plays an essential role in integrating the overall environmental inputs to provide low-dimensional information to the CNS. We assume that sensor synergy and muscle synergy communicate using these low-dimensional signals. To examine our hypothesis, we conducted posture control experiments involving lateral disturbance with 9 healthy participants. Proprioceptive information represented by the changes on muscle lengths were estimated by using the musculoskeletal model analysis software SIMM. Changes on muscles lengths were then used to compute sensory synergies. The experimental results indicate that the environmental inputs were translated into the two dimensional signals and used to move the upper limb to the desired position immediately after the lateral disturbance. Participants who showed high skill in posture control were found to be likely to have a strong correlation between sensory and muscle signaling as well as high coordination between the utilized sensory synergies. These results suggest the importance of integrating environmental inputs into suitable low-dimensional signals before providing them to the CNS. This mechanism should be essential when designing the prosthesis’ sensory system to make the controller simpler

am Alnajjar, F., Itkonen, M., Berenz, V., Tournier, M., Nagai, C., Shimoda, S. Sensory synergy as environmental input integration Frontiers in Neuroscience, 8, pages: 436, 2015 (article)

Active Reward Learning with a Novel Acquisition Function

Daniel, C., Kroemer, O., Viering, M., Metz, J., Peters, J.

Autonomous Robots, 39(3):389-405, 2015 (article)

am ei

am ei Daniel, C., Kroemer, O., Viering, M., Metz, J., Peters, J. Active Reward Learning with a Novel Acquisition Function Autonomous Robots, 39(3):389-405, 2015 (article)

Learning Inverse Dynamics Models with Contacts

Calandra, R., Ivaldi, S., Deisenroth, M., Rückert, E., Peters, J.

In IEEE International Conference on Robotics and Automation, pages: 3186-3191, ICRA, 2015 (inproceedings)

am ei

am ei Calandra, R., Ivaldi, S., Deisenroth, M., Rückert, E., Peters, J. Learning Inverse Dynamics Models with Contacts In IEEE International Conference on Robotics and Automation, pages: 3186-3191, ICRA, 2015 (inproceedings)

A Probabilistic Framework for Semi-Autonomous Robots Based on Interaction Primitives with Phase Estimation

Maeda, G., Neumann, G., Ewerton, M., Lioutikov, R., Peters, J.

In Proceedings of the International Symposium of Robotics Research, ISRR, 2015 (inproceedings)

am ei

am ei Maeda, G., Neumann, G., Ewerton, M., Lioutikov, R., Peters, J. A Probabilistic Framework for Semi-Autonomous Robots Based on Interaction Primitives with Phase Estimation In Proceedings of the International Symposium of Robotics Research, ISRR, 2015 (inproceedings)

Learning Movement Primitive Attractor Goals and Sequential Skills from Kinesthetic Demonstrations

Manschitz, S., Kober, J., Gienger, M., Peters, J.

Robotics and Autonomous Systems, 74, Part A, pages: 97-107, 2015 (article)

am ei

am ei Manschitz, S., Kober, J., Gienger, M., Peters, J. Learning Movement Primitive Attractor Goals and Sequential Skills from Kinesthetic Demonstrations Robotics and Autonomous Systems, 74, Part A, pages: 97-107, 2015 (article)

Bayesian Optimization for Learning Gaits under Uncertainty

Calandra, R., Seyfarth, A., Peters, J., Deisenroth, M.

Annals of Mathematics and Artificial Intelligence, pages: 1-19, 2015 (article)

am ei

am ei Calandra, R., Seyfarth, A., Peters, J., Deisenroth, M. Bayesian Optimization for Learning Gaits under Uncertainty Annals of Mathematics and Artificial Intelligence, pages: 1-19, 2015 (article)

Towards Learning Hierarchical Skills for Multi-Phase Manipulation Tasks

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

In IEEE International Conference on Robotics and Automation, pages: 1503 - 1510, ICRA, 2015 (inproceedings)

am ei

am ei Kroemer, O., Daniel, C., Neumann, G., van Hoof, H., Peters, J. Towards Learning Hierarchical Skills for Multi-Phase Manipulation Tasks In IEEE International Conference on Robotics and Automation, pages: 1503 - 1510, ICRA, 2015 (inproceedings)

Force estimation and slip detection/classification for grip control using a biomimetic tactile sensor

Su, Z., Hausman, K., Chebotar, Y., Molchanov, A., Loeb, G. E., Sukhatme, G. S., Schaal, S.

In IEEE-RAS International Conference on Humanoid Robots (Humanoids), pages: 297-303, 2015 (inproceedings)

am Su, Z., Hausman, K., Chebotar, Y., Molchanov, A., Loeb, G. E., Sukhatme, G. S., Schaal, S. Force estimation and slip detection/classification for grip control using a biomimetic tactile sensor In IEEE-RAS International Conference on Humanoid Robots (Humanoids), pages: 297-303, 2015 (inproceedings)

Web Project Page [BibTex]

Policy Learning with Hypothesis Based Local Action Selection

Sankaran, B., Bohg, J., Ratliff, N., Schaal, S.

In Reinforcement Learning and Decision Making, 2015 (inproceedings)

Abstract

For robots to be able to manipulate in unknown and unstructured environments the robot should be capable of operating under partial observability of the environment. Object occlusions and unmodeled environments are some of the factors that result in partial observability. A common scenario where this is encountered is manipulation in clutter. In the case that the robot needs to locate an object of interest and manipulate it, it needs to perform a series of decluttering actions to accurately detect the object of interest. To perform such a series of actions, the robot also needs to account for the dynamics of objects in the environment and how they react to contact. This is a non trivial problem since one needs to reason not only about robot-object interactions but also object-object interactions in the presence of contact. In the example scenario of manipulation in clutter, the state vector would have to account for the pose of the object of interest and the structure of the surrounding environment. The process model would have to account for all the aforementioned robot-object, object-object interactions. The complexity of the process model grows exponentially as the number of objects in the scene increases. This is commonly the case in unstructured environments. Hence it is not reasonable to attempt to model all object-object and robot-object interactions explicitly. Under this setting we propose a hypothesis based action selection algorithm where we construct a hypothesis set of the possible poses of an object of interest given the current evidence in the scene and select actions based on our current set of hypothesis. This hypothesis set tends to represent the belief about the structure of the environment and the number of poses the object of interest can take. The agent's only stopping criterion is when the uncertainty regarding the pose of the object is fully resolved.

am Sankaran, B., Bohg, J., Ratliff, N., Schaal, S. Policy Learning with Hypothesis Based Local Action Selection In Reinforcement Learning and Decision Making, 2015 (inproceedings)

Web Project Page [BibTex]

Learning Optimal Striking Points for A Ping-Pong Playing Robot

Huang, Y., Schölkopf, B., Peters, J.

In IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 4587-4592, IROS, 2015 (inproceedings)

am ei

PDF DOI [BibTex]

am ei Huang, Y., Schölkopf, B., Peters, J. Learning Optimal Striking Points for A Ping-Pong Playing Robot In IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 4587-4592, IROS, 2015 (inproceedings)

PDF DOI [BibTex]

Model-Based Relative Entropy Stochastic Search

Abdolmaleki, A., Peters, J., Neumann, G.

In Advances in Neural Information Processing Systems 28, pages: 3523-3531, (Editors: C. Cortes, N.D. Lawrence, D.D. Lee, M. Sugiyama and R. Garnett), Curran Associates, Inc., 29th Annual Conference on Neural Information Processing Systems (NIPS), 2015 (inproceedings)

am ei

am ei Abdolmaleki, A., Peters, J., Neumann, G. Model-Based Relative Entropy Stochastic Search In Advances in Neural Information Processing Systems 28, pages: 3523-3531, (Editors: C. Cortes, N.D. Lawrence, D.D. Lee, M. Sugiyama and R. Garnett), Curran Associates, Inc., 29th Annual Conference on Neural Information Processing Systems (NIPS), 2015 (inproceedings)

Modeling Spatio-Temporal Variability in Human-Robot Interaction with Probabilistic Movement Primitives

Ewerton, M., Neumann, G., Lioutikov, R., Ben Amor, H., Peters, J., Maeda, G.

In Workshop on Machine Learning for Social Robotics, ICRA, 2015 (inproceedings)

am ei

am ei Ewerton, M., Neumann, G., Lioutikov, R., Ben Amor, H., Peters, J., Maeda, G. Modeling Spatio-Temporal Variability in Human-Robot Interaction with Probabilistic Movement Primitives In Workshop on Machine Learning for Social Robotics, ICRA, 2015 (inproceedings)

Extracting Low-Dimensional Control Variables for Movement Primitives

Rueckert, E., Mundo, J., Paraschos, A., Peters, J., Neumann, G.

In IEEE International Conference on Robotics and Automation, pages: 1511-1518, ICRA, 2015 (inproceedings)

am ei

am ei Rueckert, E., Mundo, J., Paraschos, A., Peters, J., Neumann, G. Extracting Low-Dimensional Control Variables for Movement Primitives In IEEE International Conference on Robotics and Automation, pages: 1511-1518, ICRA, 2015 (inproceedings)

A New Perspective and Extension of the Gaussian Filter

Wüthrich, M., Trimpe, S., Kappler, D., Schaal, S.

In Robotics: Science and Systems, 2015 (inproceedings)

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. GFs represent the belief of the current state by a Gaussian with the mean being an affine function of the measurement. We show that this representation can be too restrictive to accurately capture the dependencies 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 from a variational-inference perspective, and analyze how restrictions on the form of the belief can be relaxed while maintaining simplicity and efficiency. This analysis provides a basis for generalizations of the GF. We propose one such generalization which coincides with a GF using a virtual measurement, obtained by applying a nonlinear function to the actual measurement. Numerical experiments show that the proposed Feature Gaussian Filter (FGF) can have a substantial performance advantage over the standard GF for systems with nonlinear observation models.

am ics

Web PDF Project Page [BibTex]

am ics Wüthrich, M., Trimpe, S., Kappler, D., Schaal, S. A New Perspective and Extension of the Gaussian Filter In Robotics: Science and Systems, 2015 (inproceedings)

Web PDF Project Page [BibTex]

Learning multiple collaborative tasks with a mixture of Interaction Primitives

Ewerton, M., Neumann, G., Lioutikov, R., Ben Amor, H., Peters, J., Maeda, G.

In IEEE International Conference on Robotics and Automation, pages: 1535-1542, ICRA, 2015 (inproceedings)

am ei

am ei Ewerton, M., Neumann, G., Lioutikov, R., Ben Amor, H., Peters, J., Maeda, G. Learning multiple collaborative tasks with a mixture of Interaction Primitives In IEEE International Conference on Robotics and Automation, pages: 1535-1542, ICRA, 2015 (inproceedings)

Whole-body motor strategies for balancing on a beam when changing the number of available degrees of freedom

Chiovetto, E, Huber, M, Righetti, L., Schaal, S., Sternad, D, Giese, M.

In Progress in Motor Control X, Budapest, Hungry, 2015 (inproceedings)

am Chiovetto, E, Huber, M, Righetti, L., Schaal, S., Sternad, D, Giese, M. Whole-body motor strategies for balancing on a beam when changing the number of available degrees of freedom In Progress in Motor Control X, Budapest, Hungry, 2015 (inproceedings)

Learning from others: Adult and child strategies in assessing conflicting ratings

Hu, J., Lieder, F., Griffiths, T. L., Xu, F.

In Biennial Meeting of the Society for Research in Child Development, Philadelphia, Pennsylvania, USA, 2015 (inproceedings)

re Hu, J., Lieder, F., Griffiths, T. L., Xu, F. Learning from others: Adult and child strategies in assessing conflicting ratings In Biennial Meeting of the Society for Research in Child Development, Philadelphia, Pennsylvania, USA, 2015 (inproceedings)

The optimism bias may support rational action

Lieder, F., Goel, S., Kwan, R., Griffiths, T. L.

NIPS 2015 Workshop on Bounded Optimality and Rational Metareasoning, 2015 (article)

re Lieder, F., Goel, S., Kwan, R., Griffiths, T. L. The optimism bias may support rational action NIPS 2015 Workshop on Bounded Optimality and Rational Metareasoning, 2015 (article)

Rational use of cognitive resources: Levels of analysis between the computational and the algorithmic

Griffiths, T. L., Lieder, F., Goodman, N. D.

Topics in Cognitive Science, 7(2):217-229, Wiley, 2015 (article)

re Griffiths, T. L., Lieder, F., Goodman, N. D. Rational use of cognitive resources: Levels of analysis between the computational and the algorithmic Topics in Cognitive Science, 7(2):217-229, Wiley, 2015 (article)

When to use which heuristic: A rational solution to the strategy selection problem

Lieder, F., Griffiths, T. L.

In Proceedings of the 37th Annual Conference of the Cognitive Science Society, 2015 (inproceedings)

re Lieder, F., Griffiths, T. L. When to use which heuristic: A rational solution to the strategy selection problem In Proceedings of the 37th Annual Conference of the Cognitive Science Society, 2015 (inproceedings)

From Humans to Robots and Back: Role of Arm Movement in Medio-lateral Balance Control

Huber, M, Chiovetto, E, Schaal, S., Giese, M., Sternad, D

In Annual Meeting of Neural Control of Movement, Charleston, NC, 2015 (inproceedings)

am Huber, M, Chiovetto, E, Schaal, S., Giese, M., Sternad, D From Humans to Robots and Back: Role of Arm Movement in Medio-lateral Balance Control In Annual Meeting of Neural Control of Movement, Charleston, NC, 2015 (inproceedings)

Children and adults differ in their strategies for social learning

Lieder, F., Sim, Z., Hu, J., Griffiths, T., Xu, F.

In Proceedings of the 37th Annual Conference of the Cognitive Science Society, 2015 (inproceedings)

re Lieder, F., Sim, Z., Hu, J., Griffiths, T., Xu, F. Children and adults differ in their strategies for social learning In Proceedings of the 37th Annual Conference of the Cognitive Science Society, 2015 (inproceedings)

Trajectory generation for multi-contact momentum control

Herzog, A., Rotella, N., Schaal, S., Righetti, L.

In 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pages: 874-880, IEEE, Seoul, South Korea, 2015 (inproceedings)

Abstract

Simplified models of the dynamics such as the linear inverted pendulum model (LIPM) have proven to perform well for biped walking on flat ground. However, for more complex tasks the assumptions of these models can become limiting. For example, the LIPM does not allow for the control of contact forces independently, is limited to co-planar contacts and assumes that the angular momentum is zero. In this paper, we propose to use the full momentum equations of a humanoid robot in a trajectory optimization framework to plan its center of mass, linear and angular momentum trajectories. The model also allows for planning desired contact forces for each end-effector in arbitrary contact locations. We extend our previous results on linear quadratic regulator (LQR) design for momentum control by computing the (linearized) optimal momentum feedback law in a receding horizon fashion. The resulting desired momentum and the associated feedback law are then used in a hierarchical whole body control approach. Simulation experiments show that the approach is computationally fast and is able to generate plans for locomotion on complex terrains while demonstrating good tracking performance for the full humanoid control.

am mg

am mg Herzog, A., Rotella, N., Schaal, S., Righetti, L. Trajectory generation for multi-contact momentum control In 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pages: 874-880, IEEE, Seoul, South Korea, 2015 (inproceedings)

Utility-weighted sampling in decisions from experience

Lieder, F., Griffiths, T. L., Hsu, M.

In The 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making, 2015 (inproceedings)

re Lieder, F., Griffiths, T. L., Hsu, M. Utility-weighted sampling in decisions from experience In The 2nd Multidisciplinary Conference on Reinforcement Learning and Decision Making, 2015 (inproceedings)