Header logo is


2015


no image
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

PDF DOI Project Page [BibTex]

2015


PDF DOI Project Page [BibTex]


no image
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

PDF DOI Project Page [BibTex]

PDF DOI Project Page [BibTex]


no image
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

PDF DOI Project Page [BibTex]

PDF DOI Project Page [BibTex]


Thumb xl publications toc
Fiberbot: A miniature crawling robot using a directional fibrillar pad

Han, Y., Marvi, H., Sitti, M.

In Robotics and Automation (ICRA), 2015 IEEE International Conference on, pages: 3122-3127, May 2015 (inproceedings)

Abstract
Vibration-driven locomotion has been widely used for crawling robot studies. Such robots usually have a vibration motor as the actuator and a fibrillar structure for providing directional friction on the substrate. However, there has not been any studies about the effect of fiber structure on robot crawling performance. In this paper, we develop Fiberbot, a custom made mini vibration robot, for studying the effect of fiber angle on robot velocity, steering, and climbing performance. It is known that the friction force with and against fibers depends on the fiber angle. Thus, we first present a new fabrication method for making millimeter scale fibers at a wide range of angles. We then show that using 30° angle fibers that have the highest friction anisotropy (ratio of backward to forward friction force) among the other fibers we fabricated in this study, Fiberbot speed on glass increases to 13.8±0.4 cm/s (compared to ν = 0.6±0.1 cm/s using vertical fibers). We also demonstrate that the locomotion direction of Fiberbot depends on the tilting direction of fibers and we can steer the robot by rotating the fiber pad. Fiberbot could also climb on glass at inclinations of up to 10° when equipped with fibers of high friction anisotropy. We show that adding a rigid tail to the robot it can climb on glass at 25° inclines. Moreover, the robot is able to crawl on rough surfaces such as wood (ν = 10.0±0.2 cm/s using 30° fiber pad). Fiberbot, a low-cost vibration robot equipped with a custom-designed fiber pad with steering and climbing capabilities could be used for studies on collective behavior on a wide range of topographies as well as search and exploratory missions.

pi

DOI [BibTex]

DOI [BibTex]


Thumb xl publications toc
Platform design and tethered flight of a motor-driven flapping-wing system

Hines, L., Colmenares, D., Sitti, M.

In Robotics and Automation (ICRA), 2015 IEEE International Conference on, pages: 5838-5845, May 2015 (inproceedings)

Abstract
In this work, we examine two design modifications to a tethered motor-driven flapping-wing system. Previously, we had demonstrated a simple mechanism utilizing a linear transmission for resonant operation and direct drive of the wing flapping angle for control. The initial two-wing system had a weight of 2.7 grams and a maximum lift-to-weight ratio of 1.4. While capable of vertical takeoff, in open-loop flight it demonstrated instability and pitch oscillations at the wing flapping frequency, leading to flight times of only a few wing strokes. Here the effect of vertical wing offset as well as an alternative multi-wing layout is investigated and experimentally tested with newly constructed prototypes. With only a change in vertical wing offset, stable open-loop flight of the two-wing flapping system is shown to be theoretically possible, but difficult to achieve with our current design and operating parameters. Both of the new two and four-wing systems, however, prove capable of flying to the end of the tether, with the four-wing system prototype eliminating disruptive wing beat oscillations.

pi

DOI [BibTex]

DOI [BibTex]


Thumb xl bottle noise
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 ε-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 ε-metric and therefore lead to a better classification performance.

am

PDF data DOI Project Page [BibTex]

PDF data DOI Project Page [BibTex]


no image
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

PDF DOI Project Page [BibTex]

PDF DOI Project Page [BibTex]


Thumb xl tracking
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

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


no image
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

PDF Video Project Page [BibTex]

PDF Video Project Page [BibTex]


no image
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

link (url) [BibTex]

link (url) [BibTex]


no image
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

Project Page [BibTex]

Project Page [BibTex]


Thumb xl screenshot from 2015 09 14 11 58 36
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

Project Page [BibTex]

Project Page [BibTex]


no image
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

link (url) [BibTex]

link (url) [BibTex]


no image
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

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
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

link (url) [BibTex]

link (url) [BibTex]


no image
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

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Thumb xl rsz slip objects
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

link (url) [BibTex]

link (url) [BibTex]


Thumb xl screen shot 2015 08 22 at 22.13.35
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

Web Project Page [BibTex]


no image
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]

PDF DOI [BibTex]


no image
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

link (url) [BibTex]

link (url) [BibTex]


no image
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

link (url) [BibTex]

link (url) [BibTex]


no image
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

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
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]


no image
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

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
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

[BibTex]

[BibTex]


no image
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

[BibTex]

[BibTex]


no image
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

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Humanoid Momentum Estimation Using Sensed Contact Wrenches

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

In 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), pages: 556-563, IEEE, Seoul, South Korea, 2015 (inproceedings)

Abstract
This work presents approaches for the estimation of quantities important for the control of the momentum of a humanoid robot. In contrast to previous approaches which use simplified models such as the Linear Inverted Pendulum Model, we present estimators based on the momentum dynamics of the robot. By using this simple yet dynamically-consistent model, we avoid the issues of using simplified models for estimation. We develop an estimator for the center of mass and full momentum which can be reformulated to estimate center of mass offsets as well as external wrenches applied to the robot. The observability of these estimators is investigated and their performance is evaluated in comparison to previous approaches.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2013


Thumb xl impact battery
Probabilistic Object Tracking Using a Range Camera

Wüthrich, M., Pastor, P., Kalakrishnan, M., Bohg, J., Schaal, S.

In IEEE/RSJ International Conference on Intelligent Robots and Systems, pages: 3195-3202, IEEE, November 2013 (inproceedings)

Abstract
We address the problem of tracking the 6-DoF pose of an object while it is being manipulated by a human or a robot. We use a dynamic Bayesian network to perform inference and compute a posterior distribution over the current object pose. Depending on whether a robot or a human manipulates the object, we employ a process model with or without knowledge of control inputs. Observations are obtained from a range camera. As opposed to previous object tracking methods, we explicitly model self-occlusions and occlusions from the environment, e.g, the human or robotic hand. This leads to a strongly non-linear observation model and additional dependencies in the Bayesian network. We employ a Rao-Blackwellised particle filter to compute an estimate of the object pose at every time step. In a set of experiments, we demonstrate the ability of our method to accurately and robustly track the object pose in real-time while it is being manipulated by a human or a robot.

am

arXiv Video Code Video DOI Project Page [BibTex]

2013


arXiv Video Code Video DOI Project Page [BibTex]


Thumb xl featureextraction
Hypothesis Testing Framework for Active Object Detection

Sankaran, B., Atanasov, N., Le Ny, J., Koletschka, T., Pappas, G., Daniilidis, K.

In IEEE International Conference on Robotics and Automation (ICRA), May 2013, clmc (inproceedings)

Abstract
One of the central problems in computer vision is the detection of semantically important objects and the estimation of their pose. Most of the work in object detection has been based on single image processing and its performance is limited by occlusions and ambiguity in appearance and geometry. This paper proposes an active approach to object detection by controlling the point of view of a mobile depth camera. When an initial static detection phase identifies an object of interest, several hypotheses are made about its class and orientation. The sensor then plans a sequence of view-points, which balances the amount of energy used to move with the chance of identifying the correct hypothesis. We formulate an active M-ary hypothesis testing problem, which includes sensor mobility, and solve it using a point-based approximate POMDP algorithm. The validity of our approach is verified through simulation and experiments with real scenes captured by a kinect sensor. The results suggest a significant improvement over static object detection.

am

pdf [BibTex]

pdf [BibTex]


no image
Action and Goal Related Decision Variables Modulate the Competition Between Multiple Potential Targets

Enachescu, V, Christopoulos, Vassilios N, Schrater, P. R., Schaal, S.

In Abstracts of Neural Control of Movement Conference (NCM 2013), February 2013 (inproceedings)

am

[BibTex]

[BibTex]


Thumb xl screen shot 2015 08 23 at 00.29.36
Fusing visual and tactile sensing for 3-D object reconstruction while grasping

Ilonen, J., Bohg, J., Kyrki, V.

In IEEE International Conference on Robotics and Automation (ICRA), pages: 3547-3554, 2013 (inproceedings)

Abstract
In this work, we propose to reconstruct a complete 3-D model of an unknown object by fusion of visual and tactile information while the object is grasped. Assuming the object is symmetric, a first hypothesis of its complete 3-D shape is generated from a single view. This initial model is used to plan a grasp on the object which is then executed with a robotic manipulator equipped with tactile sensors. Given the detected contacts between the fingers and the object, the full object model including the symmetry parameters can be refined. This refined model will then allow the planning of more complex manipulation tasks. The main contribution of this work is an optimal estimation approach for the fusion of visual and tactile data applying the constraint of object symmetry. The fusion is formulated as a state estimation problem and solved with an iterative extended Kalman filter. The approach is validated experimentally using both artificial and real data from two different robotic platforms.

am

DOI Project Page [BibTex]

DOI Project Page [BibTex]


no image
Angular Motion Control Using a Closed-Loop CPG for a Water-Running Robot

Thatte, N., Khoramshahi, M., Ijspeert, A., Sitti, M.

In Dynamic Walking 2013, (EPFL-CONF-199763), 2013 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Learning Objective Functions for Manipulation

Kalakrishnan, M., Pastor, P., Righetti, L., Schaal, S.

In 2013 IEEE International Conference on Robotics and Automation, IEEE, Karlsruhe, Germany, 2013 (inproceedings)

Abstract
We present an approach to learning objective functions for robotic manipulation based on inverse reinforcement learning. Our path integral inverse reinforcement learning algorithm can deal with high-dimensional continuous state-action spaces, and only requires local optimality of demonstrated trajectories. We use L 1 regularization in order to achieve feature selection, and propose an efficient algorithm to minimize the resulting convex objective function. We demonstrate our approach by applying it to two core problems in robotic manipulation. First, we learn a cost function for redundancy resolution in inverse kinematics. Second, we use our method to learn a cost function over trajectories, which is then used in optimization-based motion planning for grasping and manipulation tasks. Experimental results show that our method outperforms previous algorithms in high-dimensional settings.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
A hybrid topological and structural optimization method to design a 3-DOF planar motion compliant mechanism

Lum, G. Z., Teo, T. J., Yang, G., Yeo, S. H., Sitti, M.

In Advanced Intelligent Mechatronics (AIM), 2013 IEEE/ASME International Conference on, pages: 247-254, 2013 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Light-induced microbubble poration of localized cells

Fan, Qihui, Hu, Wenqi, Ohta, Aaron T

In Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE, pages: 4482-4485, 2013 (inproceedings)

pi

[BibTex]

[BibTex]


no image
SoftCubes: towards a soft modular matter

Yim, S., Sitti, M.

In Robotics and Automation (ICRA), 2013 IEEE International Conference on, pages: 530-536, 2013 (inproceedings)

pi

Project Page [BibTex]

Project Page [BibTex]


no image
Flapping wings via direct-driving by DC motors

Azhar, M., Campolo, D., Lau, G., Hines, L., Sitti, M.

In Robotics and Automation (ICRA), 2013 IEEE International Conference on, pages: 1397-1402, 2013 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Three dimensional independent control of multiple magnetic microrobots

Diller, E., Giltinan, J., Jena, P., Sitti, M.

In Robotics and Automation (ICRA), 2013 IEEE International Conference on, pages: 2576-2581, 2013 (inproceedings)

pi

[BibTex]

[BibTex]


no image
A Perching Mechanism for Flying Robots Using a Fibre-Based Adhesive

Daler, L., Klaptocz, A., Briod, A., Sitti, M., Floreano, D.

In Robotics and Automation (ICRA), 2013 IEEE International Conference on, 2013 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Bonding methods for modular micro-robotic assemblies

Diller, E., Zhang, N., Sitti, M.

In Robotics and Automation (ICRA), 2013 IEEE International Conference on, pages: 2588-2593, 2013 (inproceedings)

pi

[BibTex]

[BibTex]


no image
Learning Task Error Models for Manipulation

Pastor, P., Kalakrishnan, M., Binney, J., Kelly, J., Righetti, L., Sukhatme, G. S., Schaal, S.

In 2013 IEEE Conference on Robotics and Automation, IEEE, Karlsruhe, Germany, 2013 (inproceedings)

Abstract
Precise kinematic forward models are important for robots to successfully perform dexterous grasping and manipulation tasks, especially when visual servoing is rendered infeasible due to occlusions. A lot of research has been conducted to estimate geometric and non-geometric parameters of kinematic chains to minimize reconstruction errors. However, kinematic chains can include non-linearities, e.g. due to cable stretch and motor-side encoders, that result in significantly different errors for different parts of the state space. Previous work either does not consider such non-linearities or proposes to estimate non-geometric parameters of carefully engineered models that are robot specific. We propose a data-driven approach that learns task error models that account for such unmodeled non-linearities. We argue that in the context of grasping and manipulation, it is sufficient to achieve high accuracy in the task relevant state space. We identify this relevant state space using previously executed joint configurations and learn error corrections for those. Therefore, our system is developed to generate subsequent executions that are similar to previous ones. The experiments show that our method successfully captures the non-linearities in the head kinematic chain (due to a counterbalancing spring) and the arm kinematic chains (due to cable stretch) of the considered experimental platform, see Fig. 1. The feasibility of the presented error learning approach has also been evaluated in independent DARPA ARM-S testing contributing to successfully complete 67 out of 72 grasping and manipulation tasks.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2007


no image
Towards Machine Learning of Motor Skills

Peters, J., Schaal, S., Schölkopf, B.

In Proceedings of Autonome Mobile Systeme (AMS), pages: 138-144, (Editors: K Berns and T Luksch), 2007, clmc (inproceedings)

Abstract
Autonomous robots that can adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. Early approaches to this goal during the heydays of artificial intelligence research in the late 1980s, however, made it clear that an approach purely based on reasoning or human insights would not be able to model all the perceptuomotor tasks that a robot should fulfill. Instead, new hope was put in the growing wake of machine learning that promised fully adaptive control algorithms which learn both by observation and trial-and-error. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach to motor skill learning in order to get one step closer towards human-like performance. For doing so, we study two ma jor components for such an approach, i.e., firstly, a theoretically well-founded general approach to representing the required control structures for task representation and execution and, secondly, appropriate learning algorithms which can be applied in this setting.

am ei

PDF DOI [BibTex]

2007


PDF DOI [BibTex]


no image
Reinforcement Learning for Optimal Control of Arm Movements

Theodorou, E., Peters, J., Schaal, S.

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

Abstract
Every day motor behavior consists of a plethora of challenging motor skills from discrete movements such as reaching and throwing to rhythmic movements such as walking, drumming and running. How this plethora of motor skills can be learned remains an open question. In particular, is there any unifying computa-tional framework that could model the learning process of this variety of motor behaviors and at the same time be biologically plausible? In this work we aim to give an answer to these questions by providing a computational framework that unifies the learning mechanism of both rhythmic and discrete movements under optimization criteria, i.e., in a non-supervised trial-and-error fashion. Our suggested framework is based on Reinforcement Learning, which is mostly considered as too costly to be a plausible mechanism for learning com-plex limb movement. However, recent work on reinforcement learning with pol-icy gradients combined with parameterized movement primitives allows novel and more efficient algorithms. By using the representational power of such mo-tor primitives we show how rhythmic motor behaviors such as walking, squash-ing and drumming as well as discrete behaviors like reaching and grasping can be learned with biologically plausible algorithms. Using extensive simulations and by using different reward functions we provide results that support the hy-pothesis that Reinforcement Learning could be a viable candidate for motor learning of human motor behavior when other learning methods like supervised learning are not feasible.

am ei

[BibTex]

[BibTex]


no image
Reinforcement learning by reward-weighted regression for operational space control

Peters, J., Schaal, S.

In Proceedings of the 24th Annual International Conference on Machine Learning, pages: 745-750, ICML, 2007, clmc (inproceedings)

Abstract
Many robot control problems of practical importance, including operational space control, can be reformulated as immediate reward reinforcement learning problems. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-base reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Policy gradient methods for machine learning

Peters, J., Theodorou, E., Schaal, S.

In Proceedings of the 14th INFORMS Conference of the Applied Probability Society, pages: 97-98, Eindhoven, Netherlands, July 9-11, 2007, 2007, clmc (inproceedings)

Abstract
We present an in-depth survey of policy gradient methods as they are used in the machine learning community for optimizing parameterized, stochastic control policies in Markovian systems with respect to the expected reward. Despite having been developed separately in the reinforcement learning literature, policy gradient methods employ likelihood ratio gradient estimators as also suggested in the stochastic simulation optimization community. It is well-known that this approach to policy gradient estimation traditionally suffers from three drawbacks, i.e., large variance, a strong dependence on baseline functions and a inefficient gradient descent. In this talk, we will present a series of recent results which tackles each of these problems. The variance of the gradient estimation can be reduced significantly through recently introduced techniques such as optimal baselines, compatible function approximations and all-action gradients. However, as even the analytically obtainable policy gradients perform unnaturally slow, it required the step from ÔvanillaÕ policy gradient methods towards natural policy gradients in order to overcome the inefficiency of the gradient descent. This development resulted into the Natural Actor-Critic architecture which can be shown to be very efficient in application to motor primitive learning for robotics.

am ei

[BibTex]

[BibTex]


no image
Policy Learning for Motor Skills

Peters, J., Schaal, S.

In Proceedings of 14th International Conference on Neural Information Processing (ICONIP), pages: 233-242, (Editors: Ishikawa, M. , K. Doya, H. Miyamoto, T. Yamakawa), 2007, clmc (inproceedings)

Abstract
Policy learning which allows autonomous robots to adapt to novel situations has been a long standing vision of robotics, artificial intelligence, and cognitive sciences. However, to date, learning techniques have yet to fulfill this promise as only few methods manage to scale into the high-dimensional domains of manipulator robotics, or even the new upcoming trend of humanoid robotics, and usually scaling was only achieved in precisely pre-structured domains. In this paper, we investigate the ingredients for a general approach policy learning with the goal of an application to motor skill refinement in order to get one step closer towards human-like performance. For doing so, we study two major components for such an approach, i.e., firstly, we study policy learning algorithms which can be applied in the general setting of motor skill learning, and, secondly, we study a theoretically well-founded general approach to representing the required control structures for task representation and execution.

am ei

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Reinforcement learning for operational space control

Peters, J., Schaal, S.

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

Abstract
While operational space control is of essential importance for robotics and well-understood from an analytical point of view, it can be prohibitively hard to achieve accurate control in face of modeling errors, which are inevitable in complex robots, e.g., humanoid robots. In such cases, learning control methods can offer an interesting alternative to analytical control algorithms. However, the resulting supervised learning problem is ill-defined as it requires to learn an inverse mapping of a usually redundant system, which is well known to suffer from the property of non-convexity of the solution space, i.e., the learning system could generate motor commands that try to steer the robot into physically impossible configurations. The important insight that many operational space control algorithms can be reformulated as optimal control problems, however, allows addressing this inverse learning problem in the framework of reinforcement learning. However, few of the known optimization or reinforcement learning algorithms can be used in online learning control for robots, as they are either prohibitively slow, do not scale to interesting domains of complex robots, or require trying out policies generated by random search, which are infeasible for a physical system. Using a generalization of the EM-based reinforcement learning framework suggested by Dayan & Hinton, we reduce the problem of learning with immediate rewards to a reward-weighted regression problem with an adaptive, integrated reward transformation for faster convergence. The resulting algorithm is efficient, learns smoothly without dangerous jumps in solution space, and works well in applications of complex high degree-of-freedom robots.

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


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

Peters, J., Schaal, S.

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

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

am ei

link (url) DOI [BibTex]

link (url) DOI [BibTex]


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

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

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

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

am ei

PDF [BibTex]

PDF [BibTex]