Header logo is de


2019


no image
On the Transfer of Inductive Bias from Simulation to the Real World: a New Disentanglement Dataset

Gondal, M. W., Wuthrich, M., Miladinovic, D., Locatello, F., Breidt, M., Volchkov, V., Akpo, J., Bachem, O., Schölkopf, B., Bauer, S.

Advances in Neural Information Processing Systems 32, pages: 15714-15725, (Editors: H. Wallach and H. Larochelle and A. Beygelzimer and F. d’Alché-Buc and E. Fox and R. Garnett), Curran Associates, Inc., 33rd Annual Conference on Neural Information Processing Systems, December 2019 (conference)

am ei sf

link (url) [BibTex]

2019


link (url) [BibTex]


no image
Deep Neural Network Approach in Electrical Impedance Tomography-Based Real-Time Soft Tactile Sensor

Park, H., Lee, H., Park, K., Mo, S., Kim, J.

In Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages: 7447-7452, Macau, China, November 2019 (inproceedings)

Abstract
Recently, a whole-body tactile sensing have emerged in robotics for safe human-robot interaction. A key issue in the whole-body tactile sensing is ensuring large-area manufacturability and high durability. To fulfill these requirements, a reconstruction method called electrical impedance tomography (EIT) was adopted in large-area tactile sensing. This method maps voltage measurements to conductivity distribution using only a few number of measurement electrodes. A common approach for the mapping is using a linearized model derived from the Maxwell's equation. This linearized model shows fast computation time and moderate robustness against measurement noise but reconstruction accuracy is limited. In this paper, we propose a novel nonlinear EIT algorithm through Deep Neural Network (DNN) approach to improve the reconstruction accuracy of EIT-based tactile sensors. The neural network architecture with rectified linear unit (ReLU) function ensured extremely low computational time (0.002 seconds) and nonlinear network structure which provides superior measurement accuracy. The DNN model was trained with dataset synthesized in simulation environment. To achieve the robustness against measurement noise, the training proceeded with additive Gaussian noise that estimated through actual measurement noise. For real sensor application, the trained DNN model was transferred to a conductive fabric-based soft tactile sensor. For validation, the reconstruction error and noise robustness were mainly compared using conventional linearized model and proposed approach in simulation environment. As a demonstration, the tactile sensor equipped with the trained DNN model is presented for a contact force estimation.

hi

DOI [BibTex]

DOI [BibTex]


Soft Continuous Surface for Micromanipulation driven by Light-controlled Hydrogels
Soft Continuous Surface for Micromanipulation driven by Light-controlled Hydrogels

Choi, E., Jeong, H., Qiu, T., Fischer, P., Palagi, S.

4th IEEE International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS), July 2019 (conference)

Abstract
Remotely controlled, automated actuation and manipulation at the microscale is essential for a number of micro-manufacturing, biology, and lab-on-a-chip applications. To transport and manipulate micro-objects, arrays of remotely controlled micro-actuators are required, which, in turn, typically require complex and expensive solid-state chips. Here, we show that a continuous surface can function as a highly parallel, many-degree of freedom, wirelessly-controlled microactuator with seamless deformation. The soft continuous surface is based on a hydrogel that undergoes a volume change in response to applied light. The fabrication of the hydrogels and the characterization of their optical and thermomechanical behaviors are reported. The temperature-dependent localized deformation of the hydrogel is also investigated by numerical simulations. Static and dynamic deformations are obtained in the soft material by projecting light fields at high spatial resolution onto the surface. By controlling such deformations in open loop and especially closed loop, automated photoactuation is achieved. The surface deformations are then exploited to examine how inert microbeads can be manipulated autonomously on the surface. We believe that the proposed approach suggests ways to implement universal 2D micromanipulation schemes that can be useful for automation in microfabrication and lab-on-a-chip applications.

pf

[BibTex]

[BibTex]


Soft Phantom for the Training of Renal Calculi Diagnostics and  Lithotripsy
Soft Phantom for the Training of Renal Calculi Diagnostics and Lithotripsy

Li., D., Suarez-Ibarrola, R., Choi, E., Jeong, M., Gratzke, C., Miernik, A., Fischer, P., Qiu, T.

41st Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), July 2019 (conference)

Abstract
Organ models are important for medical training and surgical planning. With the fast development of additive fabrication technologies, including 3D printing, the fabrication of 3D organ phantoms with precise anatomical features becomes possible. Here, we develop the first high-resolution kidney phantom based on soft material assembly, by combining 3D printing and polymer molding techniques. The phantom exhibits both the detailed anatomy of a human kidney and the elasticity of soft tissues. The phantom assembly can be separated into two parts on the coronal plane, thus large renal calculi are readily placed at any desired location of the calyx. With our sealing method, the assembled phantom withstands a hydraulic pressure that is four times the normal intrarenal pressure, thus it allows the simulation of medical procedures under realistic pressure conditions. The medical diagnostics of the renal calculi is performed by multiple imaging modalities, including X-ray, ultrasound imaging and endoscopy. The endoscopic lithotripsy is also successfully performed on the phantom. The use of a multifunctional soft phantom assembly thus shows great promise for the simulation of minimally invasive medical procedures under realistic conditions.

pf

[BibTex]

[BibTex]


A Magnetic Actuation System for the  Active Microrheology in Soft Biomaterials
A Magnetic Actuation System for the Active Microrheology in Soft Biomaterials

Jeong, M., Choi, E., Li., D., Palagi, S., Fischer, P., Qiu, T.

4th IEEE International Conference on Manipulation, Automation and Robotics at Small Scales (MARSS), July 2019 (conference)

Abstract
Microrheology is a key technique to characterize soft materials at small scales. The microprobe is wirelessly actuated and therefore typically only low forces or torques can be applied, which limits the range of the applied strain. Here, we report a new magnetic actuation system for microrheology consisting of an array of rotating permanent magnets, which achieves a rotating magnetic field with a spatially homogeneous high field strength of ~100 mT in a working volume of ~20×20×20 mm3. Compared to a traditional electromagnetic coil system, the permanent magnet assembly is portable and does not require cooling, and it exerts a large magnetic torque on the microprobe that is an order of magnitude higher than previous setups. Experimental results demonstrate that the measurement range of the soft gels’ elasticity covers at least five orders of magnitude. With the large actuation torque, it is also possible to study the fracture mechanics of soft biomaterials at small scales.

pf

[BibTex]

[BibTex]


Effect of Remote Masking on Detection of Electrovibration
Effect of Remote Masking on Detection of Electrovibration

Jamalzadeh, M., Güçlü, B., Vardar, Y., Basdogan, C.

In Proceedings of the IEEE World Haptics Conference (WHC), pages: 229-234, Tokyo, Japan, July 2019 (inproceedings)

Abstract
Masking has been used to study human perception of tactile stimuli, including those created on haptic touch screens. Earlier studies have investigated the effect of in-site masking on tactile perception of electrovibration. In this study, we investigated whether it is possible to change detection threshold of electrovibration at fingertip of index finger via remote masking, i.e. by applying a (mechanical) vibrotactile stimulus on the proximal phalanx of the same finger. The masking stimuli were generated by a voice coil (Haptuator). For eight participants, we first measured the detection thresholds for electrovibration at the fingertip and for vibrotactile stimuli at the proximal phalanx. Then, the vibrations on the skin were measured at four different locations on the index finger of subjects to investigate how the mechanical masking stimulus propagated as the masking level was varied. Finally, electrovibration thresholds measured in the presence of vibrotactile masking stimuli. Our results show that vibrotactile masking stimuli generated sub-threshold vibrations around fingertip, and hence did not mechanically interfere with the electrovibration stimulus. However, there was a clear psychophysical masking effect due to central neural processes. Electrovibration absolute threshold increased approximately 0.19 dB for each dB increase in the masking level.

hi

DOI [BibTex]

DOI [BibTex]


Objective and Subjective Assessment of Algorithms for Reducing Three-Axis Vibrations to One-Axis Vibrations
Objective and Subjective Assessment of Algorithms for Reducing Three-Axis Vibrations to One-Axis Vibrations

Park, G., Kuchenbecker, K. J.

In Proceedings of the IEEE World Haptics Conference, pages: 467-472, July 2019 (inproceedings)

Abstract
A typical approach to creating realistic vibrotactile feedback is reducing 3D vibrations recorded by an accelerometer to 1D signals that can be played back on a haptic actuator, but some of the information is often lost in this dimensional reduction process. This paper describes seven representative algorithms and proposes four metrics based on the spectral match, the temporal match, and the average value and the variability of them across 3D rotations. These four performance metrics were applied to four texture recordings, and the method utilizing the discrete fourier transform (DFT) was found to be the best regardless of the sensing axis. We also recruited 16 participants to assess the perceptual similarity achieved by each algorithm in real time. We found the four metrics correlated well with the subjectively rated similarities for the six dimensional reduction algorithms, with the exception of taking the 3D vector magnitude, which was perceived to be good despite its low spectral and temporal match metrics.

hi

DOI [BibTex]

DOI [BibTex]


Fingertip Interaction Metrics Correlate with Visual and Haptic Perception of Real Surfaces
Fingertip Interaction Metrics Correlate with Visual and Haptic Perception of Real Surfaces

Vardar, Y., Wallraven, C., Kuchenbecker, K. J.

In Proceedings of the IEEE World Haptics Conference (WHC), pages: 395-400, Tokyo, Japan, July 2019 (inproceedings)

Abstract
Both vision and touch contribute to the perception of real surfaces. Although there have been many studies on the individual contributions of each sense, it is still unclear how each modality’s information is processed and integrated. To fill this gap, we investigated the similarity of visual and haptic perceptual spaces, as well as how well they each correlate with fingertip interaction metrics. Twenty participants interacted with ten different surfaces from the Penn Haptic Texture Toolkit by either looking at or touching them and judged their similarity in pairs. By analyzing the resulting similarity ratings using multi-dimensional scaling (MDS), we found that surfaces are similarly organized within the three-dimensional perceptual spaces of both modalities. Also, between-participant correlations were significantly higher in the haptic condition. In a separate experiment, we obtained the contact forces and accelerations acting on one finger interacting with each surface in a controlled way. We analyzed the collected fingertip interaction data in both the time and frequency domains. Our results suggest that the three perceptual dimensions for each modality can be represented by roughness/smoothness, hardness/softness, and friction, and that these dimensions can be estimated by surface vibration power, tap spectral centroid, and kinetic friction coefficient, respectively.

hi

DOI Project Page [BibTex]

DOI Project Page [BibTex]


Haptipedia: Accelerating Haptic Device Discovery to Support Interaction & Engineering Design
Haptipedia: Accelerating Haptic Device Discovery to Support Interaction & Engineering Design

Seifi, H., Fazlollahi, F., Oppermann, M., Sastrillo, J. A., Ip, J., Agrawal, A., Park, G., Kuchenbecker, K. J., MacLean, K. E.

In Proceedings of the ACM SIGCHI Conference on Human Factors in Computing Systems (CHI), Glasgow, Scotland, May 2019 (inproceedings)

Abstract
Creating haptic experiences often entails inventing, modifying, or selecting specialized hardware. However, experience designers are rarely engineers, and 30 years of haptic inventions are buried in a fragmented literature that describes devices mechanically rather than by potential purpose. We conceived of Haptipedia to unlock this trove of examples: Haptipedia presents a device corpus for exploration through metadata that matter to both device and experience designers. It is a taxonomy of device attributes that go beyond physical description to capture potential utility, applied to a growing database of 105 grounded force-feedback devices, and accessed through a public visualization that links utility to morphology. Haptipedia's design was driven by both systematic review of the haptic device literature and rich input from diverse haptic designers. We describe Haptipedia's reception (including hopes it will redefine device reporting standards) and our plans for its sustainability through community participation.

hi

Project Page [BibTex]

Project Page [BibTex]


no image
Internal Array Electrodes Improve the Spatial Resolution of Soft Tactile Sensors Based on Electrical Resistance Tomography

Lee, H., Park, K., Kim, J., Kuchenbecker, K. J.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 5411-5417, Montreal, Canada, May 2019, Hyosang Lee and Kyungseo Park contributed equally to this publication (inproceedings)

hi

link (url) DOI Project Page [BibTex]

link (url) DOI Project Page [BibTex]


no image
A Clustering Approach to Categorizing 7 Degree-of-Freedom Arm Motions during Activities of Daily Living

Gloumakov, Y., Spiers, A. J., Dollar, A. M.

In Proceedings of the International Conference on Robotics and Automation (ICRA), pages: 7214-7220, Montreal, Canada, May 2019 (inproceedings)

Abstract
In this paper we present a novel method of categorizing naturalistic human arm motions during activities of daily living using clustering techniques. While many current approaches attempt to define all arm motions using heuristic interpretation, or a combination of several abstract motion primitives, our unsupervised approach generates a hierarchical description of natural human motion with well recognized groups. Reliable recommendation of a subset of motions for task achievement is beneficial to various fields, such as robotic and semi-autonomous prosthetic device applications. The proposed method makes use of well-known techniques such as dynamic time warping (DTW) to obtain a divergence measure between motion segments, DTW barycenter averaging (DBA) to get a motion average, and Ward's distance criterion to build the hierarchical tree. The clusters that emerge summarize the variety of recorded motions into the following general tasks: reach-to-front, transfer-box, drinking from vessel, on-table motion, turning a key or door knob, and reach-to-back pocket. The clustering methodology is justified by comparing against an alternative measure of divergence using Bezier coefficients and K-medoids clustering.

hi

DOI [BibTex]

DOI [BibTex]


Accurate Vision-based Manipulation through Contact Reasoning
Accurate Vision-based Manipulation through Contact Reasoning

Kloss, A., Bauza, M., Wu, J., Tenenbaum, J. B., Rodriguez, A., Bohg, J.

In International Conference on Robotics and Automation, May 2019 (inproceedings) Accepted

Abstract
Planning contact interactions is one of the core challenges of many robotic tasks. Optimizing contact locations while taking dynamics into account is computationally costly and in only partially observed environments, executing contact-based tasks often suffers from low accuracy. We present an approach that addresses these two challenges for the problem of vision-based manipulation. First, we propose to disentangle contact from motion optimization. Thereby, we improve planning efficiency by focusing computation on promising contact locations. Second, we use a hybrid approach for perception and state estimation that combines neural networks with a physically meaningful state representation. In simulation and real-world experiments on the task of planar pushing, we show that our method is more efficient and achieves a higher manipulation accuracy than previous vision-based approaches.

am

Video link (url) [BibTex]

Video link (url) [BibTex]


Improving Haptic Adjective Recognition with Unsupervised Feature Learning
Improving Haptic Adjective Recognition with Unsupervised Feature Learning

Richardson, B. A., Kuchenbecker, K. J.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), pages: 3804-3810, Montreal, Canada, May 2019 (inproceedings)

Abstract
Humans can form an impression of how a new object feels simply by touching its surfaces with the densely innervated skin of the fingertips. Many haptics researchers have recently been working to endow robots with similar levels of haptic intelligence, but these efforts almost always employ hand-crafted features, which are brittle, and concrete tasks, such as object recognition. We applied unsupervised feature learning methods, specifically K-SVD and Spatio-Temporal Hierarchical Matching Pursuit (ST-HMP), to rich multi-modal haptic data from a diverse dataset. We then tested the learned features on 19 more abstract binary classification tasks that center on haptic adjectives such as smooth and squishy. The learned features proved superior to traditional hand-crafted features by a large margin, almost doubling the average F1 score across all adjectives. Additionally, particular exploratory procedures (EPs) and sensor channels were found to support perception of certain haptic adjectives, underlining the need for diverse interactions and multi-modal haptic data.

hi

link (url) DOI Project Page [BibTex]

link (url) DOI Project Page [BibTex]


Learning Latent Space Dynamics for Tactile Servoing
Learning Latent Space Dynamics for Tactile Servoing

Sutanto, G., Ratliff, N., Sundaralingam, B., Chebotar, Y., Su, Z., Handa, A., Fox, D.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019, IEEE, International Conference on Robotics and Automation, May 2019 (inproceedings) Accepted

am

pdf video [BibTex]

pdf video [BibTex]


Leveraging Contact Forces for Learning to Grasp
Leveraging Contact Forces for Learning to Grasp

Merzic, H., Bogdanovic, M., Kappler, D., Righetti, L., Bohg, J.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2019, IEEE, International Conference on Robotics and Automation, May 2019 (inproceedings)

Abstract
Grasping objects under uncertainty remains an open problem in robotics research. This uncertainty is often due to noisy or partial observations of the object pose or shape. To enable a robot to react appropriately to unforeseen effects, it is crucial that it continuously takes sensor feedback into account. While visual feedback is important for inferring a grasp pose and reaching for an object, contact feedback offers valuable information during manipulation and grasp acquisition. In this paper, we use model-free deep reinforcement learning to synthesize control policies that exploit contact sensing to generate robust grasping under uncertainty. We demonstrate our approach on a multi-fingered hand that exhibits more complex finger coordination than the commonly used two- fingered grippers. We conduct extensive experiments in order to assess the performance of the learned policies, with and without contact sensing. While it is possible to learn grasping policies without contact sensing, our results suggest that contact feedback allows for a significant improvement of grasping robustness under object pose uncertainty and for objects with a complex shape.

am mg

video arXiv [BibTex]

video arXiv [BibTex]


A Novel Texture Rendering Approach for Electrostatic Displays
A Novel Texture Rendering Approach for Electrostatic Displays

Fiedler, T., Vardar, Y.

In Proceedings of International Workshop on Haptic and Audio Interaction Design (HAID), Lille, France, March 2019 (inproceedings)

Abstract
Generating realistic texture feelings on tactile displays using data-driven methods has attracted a lot of interest in the last decade. However, the need for large data storages and transmission rates complicates the use of these methods for the future commercial displays. In this paper, we propose a new texture rendering approach which can compress the texture data signicantly for electrostatic displays. Using three sample surfaces, we first explain how to record, analyze and compress the texture data, and render them on a touchscreen. Then, through psychophysical experiments conducted with nineteen participants, we show that the textures can be reproduced by a signicantly less number of frequency components than the ones in the original signal without inducing perceptual degradation. Moreover, our results indicate that the possible degree of compression is affected by the surface properties.

hi

Fiedler19-HAID-Electrostatic [BibTex]

Fiedler19-HAID-Electrostatic [BibTex]

2018


Motion-based Object Segmentation based on Dense RGB-D Scene Flow
Motion-based Object Segmentation based on Dense RGB-D Scene Flow

Shao, L., Shah, P., Dwaracherla, V., Bohg, J.

IEEE Robotics and Automation Letters, 3(4):3797-3804, IEEE, IEEE/RSJ International Conference on Intelligent Robots and Systems, October 2018 (conference)

Abstract
Given two consecutive RGB-D images, we propose a model that estimates a dense 3D motion field, also known as scene flow. We take advantage of the fact that in robot manipulation scenarios, scenes often consist of a set of rigidly moving objects. Our model jointly estimates (i) the segmentation of the scene into an unknown but finite number of objects, (ii) the motion trajectories of these objects and (iii) the object scene flow. We employ an hourglass, deep neural network architecture. In the encoding stage, the RGB and depth images undergo spatial compression and correlation. In the decoding stage, the model outputs three images containing a per-pixel estimate of the corresponding object center as well as object translation and rotation. This forms the basis for inferring the object segmentation and final object scene flow. To evaluate our model, we generated a new and challenging, large-scale, synthetic dataset that is specifically targeted at robotic manipulation: It contains a large number of scenes with a very diverse set of simultaneously moving 3D objects and is recorded with a commonly-used RGB-D camera. In quantitative experiments, we show that we significantly outperform state-of-the-art scene flow and motion-segmentation methods. In qualitative experiments, we show how our learned model transfers to challenging real-world scenes, visually generating significantly better results than existing methods.

am

Project Page arXiv DOI [BibTex]

2018


Project Page arXiv DOI [BibTex]


Gait learning for soft microrobots controlled by light fields
Gait learning for soft microrobots controlled by light fields

Rohr, A. V., Trimpe, S., Marco, A., Fischer, P., Palagi, S.

In International Conference on Intelligent Robots and Systems (IROS) 2018, pages: 6199-6206, International Conference on Intelligent Robots and Systems 2018, October 2018 (inproceedings)

Abstract
Soft microrobots based on photoresponsive materials and controlled by light fields can generate a variety of different gaits. This inherent flexibility can be exploited to maximize their locomotion performance in a given environment and used to adapt them to changing environments. However, because of the lack of accurate locomotion models, and given the intrinsic variability among microrobots, analytical control design is not possible. Common data-driven approaches, on the other hand, require running prohibitive numbers of experiments and lead to very sample-specific results. Here we propose a probabilistic learning approach for light-controlled soft microrobots based on Bayesian Optimization (BO) and Gaussian Processes (GPs). The proposed approach results in a learning scheme that is highly data-efficient, enabling gait optimization with a limited experimental budget, and robust against differences among microrobot samples. These features are obtained by designing the learning scheme through the comparison of different GP priors and BO settings on a semisynthetic data set. The developed learning scheme is validated in microrobot experiments, resulting in a 115% improvement in a microrobot’s locomotion performance with an experimental budget of only 20 tests. These encouraging results lead the way toward self-adaptive microrobotic systems based on lightcontrolled soft microrobots and probabilistic learning control.

ics pf

arXiv IEEE Xplore DOI Project Page [BibTex]

arXiv IEEE Xplore DOI Project Page [BibTex]


no image
Assessment Of Atypical Motor Development In Infants Through Toy-Stimulated Play And Center Of Pressure Analysis

Zhao, S., Mohan, M., Torres, W. O., Bogen, D. K., Shofer, F. S., Prosser, L., Loeb, H., Johnson, M. J.

In Proceedings of the Annual Rehabilitation Engineering and Assistive Technology Society of North America (RESNA) Conference, Arlington, USA, July 2018 (inproceedings)

Abstract
There is a need to identify measures and create systems to assess motor development at an early stage. Center of Pressure (CoP) is a quantifiable metric that has been used to investigate postural control in healthy young children [6], children with CP [7], and infants just beginning to sit [8]. It was found that infants born prematurely exhibit different patterns of CoP movement than infants born full-term when assessing development impairments relating to postural control [9]. Preterm infants exhibited greater CoP excursions but had greater variability in their movements than fullterm infants. Our solution, the Play And Neuro-Development Assessment (PANDA) Gym, is a sensorized environment that aims to provide early diagnosis of neuromotor disorder in infants and improve current screening processes by providing quantitative measures rather than subjective ones, and promoting natural play with the stimulus of toys. Previous studies have documented stages in motor development in infants [10, 11], and developmental delays could become more apparent through toy interactions. This study examines the sensitivity of the pressure-sensitive mat subsystem to detect differences in CoP movement patterns for preterm and fullterm infants less than 6 months of age, with varying risk levels. This study aims to distinguish between typical and atypical motor development through assessment of the CoP data of infants in a natural play environment, in conditions where movement may be further stimulated with the presence of a toy.

hi

link (url) [BibTex]

link (url) [BibTex]


Probabilistic Recurrent State-Space Models
Probabilistic Recurrent State-Space Models

Doerr, A., Daniel, C., Schiegg, M., Nguyen-Tuong, D., Schaal, S., Toussaint, M., Trimpe, S.

In Proceedings of the International Conference on Machine Learning (ICML), International Conference on Machine Learning (ICML), July 2018 (inproceedings)

Abstract
State-space models (SSMs) are a highly expressive model class for learning patterns in time series data and for system identification. Deterministic versions of SSMs (e.g., LSTMs) proved extremely successful in modeling complex time-series data. Fully probabilistic SSMs, however, unfortunately often prove hard to train, even for smaller problems. To overcome this limitation, we propose a scalable initialization and training algorithm based on doubly stochastic variational inference and Gaussian processes. In the variational approximation we propose in contrast to related approaches to fully capture the latent state temporal correlations to allow for robust training.

am ics

arXiv pdf Project Page [BibTex]

arXiv pdf Project Page [BibTex]


Soft Miniaturized Linear Actuators Wirelessly Powered by Rotating Permanent Magnets
Soft Miniaturized Linear Actuators Wirelessly Powered by Rotating Permanent Magnets

Qiu, T., Palagi, S., Sachs, J., Fischer, P.

In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages: 3595-3600, May 2018 (inproceedings)

Abstract
Wireless actuation by magnetic fields allows for the operation of untethered miniaturized devices, e.g. in biomedical applications. Nevertheless, generating large controlled forces over relatively large distances is challenging. Magnetic torques are easier to generate and control, but they are not always suitable for the tasks at hand. Moreover, strong magnetic fields are required to generate a sufficient torque, which are difficult to achieve with electromagnets. Here, we demonstrate a soft miniaturized actuator that transforms an externally applied magnetic torque into a controlled linear force. We report the design, fabrication and characterization of both the actuator and the magnetic field generator. We show that the magnet assembly, which is based on a set of rotating permanent magnets, can generate strong controlled oscillating fields over a relatively large workspace. The actuator, which is 3D-printed, can lift a load of more than 40 times its weight. Finally, we show that the actuator can be further miniaturized, paving the way towards strong, wirelessly powered microactuators.

pf

link (url) DOI [BibTex]

link (url) DOI [BibTex]


Online Learning of a Memory for Learning Rates
Online Learning of a Memory for Learning Rates

(nominated for best paper award)

Meier, F., Kappler, D., Schaal, S.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2018, IEEE, International Conference on Robotics and Automation, May 2018, accepted (inproceedings)

Abstract
The promise of learning to learn for robotics rests on the hope that by extracting some information about the learning process itself we can speed up subsequent similar learning tasks. Here, we introduce a computationally efficient online meta-learning algorithm that builds and optimizes a memory model of the optimal learning rate landscape from previously observed gradient behaviors. While performing task specific optimization, this memory of learning rates predicts how to scale currently observed gradients. After applying the gradient scaling our meta-learner updates its internal memory based on the observed effect its prediction had. Our meta-learner can be combined with any gradient-based optimizer, learns on the fly and can be transferred to new optimization tasks. In our evaluations we show that our meta-learning algorithm speeds up learning of MNIST classification and a variety of learning control tasks, either in batch or online learning settings.

am

pdf video code [BibTex]

pdf video code [BibTex]


Learning Sensor Feedback Models from Demonstrations via Phase-Modulated Neural Networks
Learning Sensor Feedback Models from Demonstrations via Phase-Modulated Neural Networks

Sutanto, G., Su, Z., Schaal, S., Meier, F.

In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2018, IEEE, International Conference on Robotics and Automation, May 2018 (inproceedings)

am

pdf video [BibTex]

pdf video [BibTex]


no image
Travelling Ultrasonic Wave Enhances Keyclick Sensation

Gueorguiev, D., Kaci, A., Amberg, M., Giraud, F., Lemaire-Semail, B.

In Haptics: Science, Technology, and Applications, pages: 302-312, Springer International Publishing, Cham, 2018 (inproceedings)

Abstract
A realistic keyclick sensation is a serious challenge for haptic feedback since vibrotactile rendering faces the limitation of the absence of contact force as experienced on physical buttons. It has been shown that creating a keyclick sensation is possible with stepwise ultrasonic friction modulation. However, the intensity of the sensation is limited by the impedance of the fingertip and by the absence of a lateral force component external to the finger. In our study, we compare this technique to rendering with an ultrasonic travelling wave, which exerts a lateral force on the fingertip. For both techniques, participants were asked to report the detection (or not) of a keyclick during a forced choice one interval procedure. In experiment 1, participants could press the surface as many time as they wanted for a given trial. In experiment 2, they were constrained to press only once. The results show a lower perceptual threshold for travelling waves. Moreover, participants pressed less times per trial and exerted smaller normal force on the surface. The subjective quality of the sensation was found similar for both techniques. In general, haptic feedback based on travelling ultrasonic waves is promising for applications without lateral motion of the finger.

hi

[BibTex]

[BibTex]


no image
On Time Optimization of Centroidal Momentum Dynamics

Ponton, B., Herzog, A., Del Prete, A., Schaal, S., Righetti, L.

In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages: 5776-5782, IEEE, Brisbane, Australia, 2018 (inproceedings)

Abstract
Recently, the centroidal momentum dynamics has received substantial attention to plan dynamically consistent motions for robots with arms and legs in multi-contact scenarios. However, it is also non convex which renders any optimization approach difficult and timing is usually kept fixed in most trajectory optimization techniques to not introduce additional non convexities to the problem. But this can limit the versatility of the algorithms. In our previous work, we proposed a convex relaxation of the problem that allowed to efficiently compute momentum trajectories and contact forces. However, our approach could not minimize a desired angular momentum objective which seriously limited its applicability. Noticing that the non-convexity introduced by the time variables is of similar nature as the centroidal dynamics one, we propose two convex relaxations to the problem based on trust regions and soft constraints. The resulting approaches can compute time-optimized dynamically consistent trajectories sufficiently fast to make the approach realtime capable. The performance of the algorithm is demonstrated in several multi-contact scenarios for a humanoid robot. In particular, we show that the proposed convex relaxation of the original problem finds solutions that are consistent with the original non-convex problem and illustrate how timing optimization allows to find motion plans that would be difficult to plan with fixed timing † †Implementation details and demos can be found in the source code available at https://git-amd.tuebingen.mpg.de/bponton/timeoptimization.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Exploring Fingers’ Limitation of Texture Density Perception on Ultrasonic Haptic Displays

Kalantari, F., Gueorguiev, D., Lank, E., Bremard, N., Grisoni, L.

In Haptics: Science, Technology, and Applications, pages: 354-365, Springer International Publishing, Cham, 2018 (inproceedings)

Abstract
Recent research in haptic feedback is motivated by the crucial role that tactile perception plays in everyday touch interactions. In this paper, we describe psychophysical experiments to investigate the perceptual threshold of individual fingers on both the right and left hand of right-handed participants using active dynamic touch for spatial period discrimination of both sinusoidal and square-wave gratings on ultrasonic haptic touchscreens. Both one-finger and multi-finger touch were studied and compared. Our results indicate that users' finger identity (index finger, middle finger, etc.) significantly affect the perception of both gratings in the case of one-finger exploration. We show that index finger and thumb are the most sensitive in all conditions whereas little finger followed by ring are the least sensitive for haptic perception. For multi-finger exploration, the right hand was found to be more sensitive than the left hand for both gratings. Our findings also demonstrate similar perception sensitivity between multi-finger exploration and the index finger of users' right hands (i.e. dominant hand in our study), while significant difference was found between single and multi-finger perception sensitivity for the left hand.

hi

[BibTex]

[BibTex]


no image
Unsupervised Contact Learning for Humanoid Estimation and Control

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

In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages: 411-417, IEEE, Brisbane, Australia, 2018 (inproceedings)

Abstract
This work presents a method for contact state estimation using fuzzy clustering to learn contact probability for full, six-dimensional humanoid contacts. The data required for training is solely from proprioceptive sensors - endeffector contact wrench sensors and inertial measurement units (IMUs) - and the method is completely unsupervised. The resulting cluster means are used to efficiently compute the probability of contact in each of the six endeffector degrees of freedom (DoFs) independently. This clustering-based contact probability estimator is validated in a kinematics-based base state estimator in a simulation environment with realistic added sensor noise for locomotion over rough, low-friction terrain on which the robot is subject to foot slip and rotation. The proposed base state estimator which utilizes these six DoF contact probability estimates is shown to perform considerably better than that which determines kinematic contact constraints purely based on measured normal force.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Learning Task-Specific Dynamics to Improve Whole-Body Control

Gams, A., Mason, S., Ude, A., Schaal, S., Righetti, L.

In Hua, IEEE, Beijing, China, November 2018 (inproceedings)

Abstract
In task-based inverse dynamics control, reference accelerations used to follow a desired plan can be broken down into feedforward and feedback trajectories. The feedback term accounts for tracking errors that are caused from inaccurate dynamic models or external disturbances. On underactuated, free-floating robots, such as humanoids, high feedback terms can be used to improve tracking accuracy; however, this can lead to very stiff behavior or poor tracking accuracy due to limited control bandwidth. In this paper, we show how to reduce the required contribution of the feedback controller by incorporating learned task-space reference accelerations. Thus, we i) improve the execution of the given specific task, and ii) offer the means to reduce feedback gains, providing for greater compliance of the system. With a systematic approach we also reduce heuristic tuning of the model parameters and feedback gains, often present in real-world experiments. In contrast to learning task-specific joint-torques, which might produce a similar effect but can lead to poor generalization, our approach directly learns the task-space dynamics of the center of mass of a humanoid robot. Simulated and real-world results on the lower part of the Sarcos Hermes humanoid robot demonstrate the applicability of the approach.

am mg

link (url) [BibTex]

link (url) [BibTex]


no image
An MPC Walking Framework With External Contact Forces

Mason, S., Rotella, N., Schaal, S., Righetti, L.

In 2018 IEEE International Conference on Robotics and Automation (ICRA), pages: 1785-1790, IEEE, Brisbane, Australia, May 2018 (inproceedings)

Abstract
In this work, we present an extension to a linear Model Predictive Control (MPC) scheme that plans external contact forces for the robot when given multiple contact locations and their corresponding friction cone. To this end, we set up a two-step optimization problem. In the first optimization, we compute the Center of Mass (CoM) trajectory, foot step locations, and introduce slack variables to account for violating the imposed constraints on the Zero Moment Point (ZMP). We then use the slack variables to trigger the second optimization, in which we calculate the optimal external force that compensates for the ZMP tracking error. This optimization considers multiple contacts positions within the environment by formulating the problem as a Mixed Integer Quadratic Program (MIQP) that can be solved at a speed between 100-300 Hz. Once contact is created, the MIQP reduces to a single Quadratic Program (QP) that can be solved in real-time ({\textless}; 1kHz). Simulations show that the presented walking control scheme can withstand disturbances 2-3× larger with the additional force provided by a hand contact.

am mg

link (url) DOI [BibTex]

link (url) DOI [BibTex]

2010


no image
Reinforcement learning of full-body humanoid motor skills

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

In Humanoid Robots (Humanoids), 2010 10th IEEE-RAS International Conference on, pages: 405-410, December 2010, clmc (inproceedings)

Abstract
Applying reinforcement learning to humanoid robots is challenging because humanoids have a large number of degrees of freedom and state and action spaces are continuous. Thus, most reinforcement learning algorithms would become computationally infeasible and require a prohibitive amount of trials to explore such high-dimensional spaces. In this paper, we present a probabilistic reinforcement learning approach, which is derived from the framework of stochastic optimal control and path integrals. The algorithm, called Policy Improvement with Path Integrals (PI2), has a surprisingly simple form, has no open tuning parameters besides the exploration noise, is model-free, and performs numerically robustly in high dimensional learning problems. We demonstrate how PI2 is able to learn full-body motor skills on a 34-DOF humanoid robot. To demonstrate the generality of our approach, we also apply PI2 in the context of variable impedance control, where both planned trajectories and gain schedules for each joint are optimized simultaneously.

am

link (url) [BibTex]

2010


link (url) [BibTex]


Enhanced Visual Scene Understanding through Human-Robot Dialog
Enhanced Visual Scene Understanding through Human-Robot Dialog

Johnson-Roberson, M., Bohg, J., Kragic, D., Skantze, G., Gustafson, J., Carlson, R.

In Proceedings of AAAI 2010 Fall Symposium: Dialog with Robots, November 2010 (inproceedings)

am

pdf [BibTex]

pdf [BibTex]


Scene Representation and Object Grasping Using Active Vision
Scene Representation and Object Grasping Using Active Vision

Gratal, X., Bohg, J., Björkman, M., Kragic, D.

In IROS’10 Workshop on Defining and Solving Realistic Perception Problems in Personal Robotics, October 2010 (inproceedings)

Abstract
Object grasping and manipulation pose major challenges for perception and control and require rich interaction between these two fields. In this paper, we concentrate on the plethora of perceptual problems that have to be solved before a robot can be moved in a controlled way to pick up an object. A vision system is presented that integrates a number of different computational processes, e.g. attention, segmentation, recognition or reconstruction to incrementally build up a representation of the scene suitable for grasping and manipulation of objects. Our vision system is equipped with an active robotic head and a robot arm. This embodiment enables the robot to perform a number of different actions like saccading, fixating, and grasping. By applying these actions, the robot can incrementally build a scene representation and use it for interaction. We demonstrate our system in a scenario for picking up known objects from a table top. We also show the system’s extendibility towards grasping of unknown and familiar objects.

am

video pdf slides [BibTex]

video pdf slides [BibTex]


Strategies for multi-modal scene exploration
Strategies for multi-modal scene exploration

Bohg, J., Johnson-Roberson, M., Björkman, M., Kragic, D.

In Intelligent Robots and Systems (IROS), 2010 IEEE/RSJ International Conference on, pages: 4509-4515, October 2010 (inproceedings)

Abstract
We propose a method for multi-modal scene exploration where initial object hypothesis formed by active visual segmentation are confirmed and augmented through haptic exploration with a robotic arm. We update the current belief about the state of the map with the detection results and predict yet unknown parts of the map with a Gaussian Process. We show that through the integration of different sensor modalities, we achieve a more complete scene model. We also show that the prediction of the scene structure leads to a valid scene representation even if the map is not fully traversed. Furthermore, we propose different exploration strategies and evaluate them both in simulation and on our robotic platform.

am

video pdf DOI Project Page [BibTex]

video pdf DOI Project Page [BibTex]


Attention-based active 3D point cloud segmentation
Attention-based active 3D point cloud segmentation

Johnson-Roberson, M., Bohg, J., Björkman, M., Kragic, D.

In Intelligent Robots and Systems (IROS), 2010 IEEE/RSJ International Conference on, pages: 1165-1170, October 2010 (inproceedings)

Abstract
In this paper we present a framework for the segmentation of multiple objects from a 3D point cloud. We extend traditional image segmentation techniques into a full 3D representation. The proposed technique relies on a state-of-the-art min-cut framework to perform a fully 3D global multi-class labeling in a principled manner. Thereby, we extend our previous work in which a single object was actively segmented from the background. We also examine several seeding methods to bootstrap the graphical model-based energy minimization and these methods are compared over challenging scenes. All results are generated on real-world data gathered with an active vision robotic head. We present quantitive results over aggregate sets as well as visual results on specific examples.

am

pdf DOI [BibTex]

pdf DOI [BibTex]


no image
Relative Entropy Policy Search

Peters, J., Mülling, K., Altun, Y.

In Proceedings of the Twenty-Fourth National Conference on Artificial Intelligence, pages: 1607-1612, (Editors: Fox, M. , D. Poole), AAAI Press, Menlo Park, CA, USA, Twenty-Fourth National Conference on Artificial Intelligence (AAAI-10), July 2010 (inproceedings)

Abstract
Policy search is a successful approach to reinforcement learning. However, policy improvements often result in the loss of information. Hence, it has been marred by premature convergence and implausible solutions. As first suggested in the context of covariant policy gradients (Bagnell and Schneider 2003), many of these problems may be addressed by constraining the information loss. In this paper, we continue this path of reasoning and suggest the Relative Entropy Policy Search (REPS) method. The resulting method differs significantly from previous policy gradient approaches and yields an exact update step. It works well on typical reinforcement learning benchmark problems.

am ei

PDF Web [BibTex]

PDF Web [BibTex]


no image
VerroTouch: High-Frequency Acceleration Feedback for Telerobotic Surgery

Kuchenbecker, K. J., Gewirtz, J., McMahan, W., Standish, D., Martin, P., Bohren, J., Mendoza, P. J., Lee, D. I.

In Haptics: Generating and Perceiving Tangible Sensations, Proc. EuroHaptics, Part I, 6191, pages: 189-196, Lecture Notes in Computer Science, Springer, Amsterdam, Netherlands, July 2010, Oral presentation given by Kuchenbecker (inproceedings)

hi

[BibTex]

[BibTex]


no image
Reinforcement learning of motor skills in high dimensions: A path integral approach

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

In Robotics and Automation (ICRA), 2010 IEEE International Conference on, pages: 2397-2403, May 2010, clmc (inproceedings)

Abstract
Reinforcement learning (RL) is one of the most general approaches to learning control. Its applicability to complex motor systems, however, has been largely impossible so far due to the computational difficulties that reinforcement learning encounters in high dimensional continuous state-action spaces. In this paper, we derive a novel approach to RL for parameterized control policies based on the framework of stochastic optimal control with path integrals. While solidly grounded in optimal control theory and estimation theory, the update equations for learning are surprisingly simple and have no danger of numerical instabilities as neither matrix inversions nor gradient learning rates are required. Empirical evaluations demonstrate significant performance improvements over gradient-based policy learning and scalability to high-dimensional control problems. Finally, a learning experiment on a robot dog illustrates the functionality of our algorithm in a real-world scenario. We believe that our new algorithm, Policy Improvement with Path Integrals (PI2), offers currently one of the most efficient, numerically robust, and easy to implement algorithms for RL in robotics.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Inverse dynamics control of floating base systems using orthogonal decomposition

Mistry, M., Buchli, J., Schaal, S.

In Robotics and Automation (ICRA), 2010 IEEE International Conference on, pages: 3406-3412, May 2010, clmc (inproceedings)

Abstract
Model-based control methods can be used to enable fast, dexterous, and compliant motion of robots without sacrificing control accuracy. However, implementing such techniques on floating base robots, e.g., humanoids and legged systems, is non-trivial due to under-actuation, dynamically changing constraints from the environment, and potentially closed loop kinematics. In this paper, we show how to compute the analytically correct inverse dynamics torques for model-based control of sufficiently constrained floating base rigid-body systems, such as humanoid robots with one or two feet in contact with the environment. While our previous inverse dynamics approach relied on an estimation of contact forces to compute an approximate inverse dynamics solution, here we present an analytically correct solution by using an orthogonal decomposition to project the robot dynamics onto a reduced dimensional space, independent of contact forces. We demonstrate the feasibility and robustness of our approach on a simulated floating base bipedal humanoid robot and an actual robot dog locomoting over rough terrain.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Fast, robust quadruped locomotion over challenging terrain

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

In Robotics and Automation (ICRA), 2010 IEEE International Conference on, pages: 2665-2670, May 2010, clmc (inproceedings)

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 terrain of varying difficulty levels. We demonstrate the generalization ability of this controller by presenting test results from an independent external test team on terrains that have never been shown to us.

am

link (url) [BibTex]

link (url) [BibTex]


no image
Automatic Filter Design for Synthesis of Haptic Textures from Recorded Acceleration Data

Romano, J. M., Yoshioka, T., Kuchenbecker, K. J.

In Proc. IEEE International Conference on Robotics and Automation, pages: 1815-1821, Anchorage, Alaska, USA, May 2010, Oral presentation given by Romano (inproceedings)

hi

[BibTex]

[BibTex]


no image
Control of a High Fidelity Ungrounded Torque Feedback Device: The iTorqU 2.1

Winfree, K. N., Romano, J. M., Gewirtz, J., Kuchenbecker, K. J.

In Proc. IEEE International Conference on Robotics and Automation, pages: 1347-1352, Anchorage, Alaska, May 2010, Oral presentation given by Winfree (inproceedings)

hi

[BibTex]

[BibTex]


no image
High Frequency Acceleration Feedback Significantly Increases the Realism of Haptically Rendered Textured Surfaces

McMahan, W., Romano, J. M., Rahuman, A. M. A., Kuchenbecker, K. J.

In Proc. IEEE Haptics Symposium, pages: 141-148, Waltham, Massachusetts, March 2010, Oral presentation given by McMahan (inproceedings)

hi

[BibTex]

[BibTex]


no image
Spatially distributed tactile feedback for kinesthetic motion guidance

Kapur, P., Jensen, M., Buxbaum, L. J., Jax, S. A., Kuchenbecker, K. J.

In Proc. IEEE Haptics Symposium, pages: 519-526, Waltham, Massachusetts, USA, March 2010, Poster presentation given by Kapur. {F}inalist for Best Poster Award (inproceedings)

hi

[BibTex]

[BibTex]


no image
Accelerometer-based Tilt Estimation of a Rigid Body with only Rotational Degrees of Freedom

Trimpe, S., D’Andrea, R.

In Proceedings of the IEEE International Conference on Robotics and Automation, 2010 (inproceedings)

am ics

PDF DOI [BibTex]

PDF DOI [BibTex]


no image
Dimensional Reduction of High-Frequency Accelerations for Haptic Rendering

Landin, N., Romano, J. M., McMahan, W., Kuchenbecker, K. J.

In Haptics: Generating and Perceiving Tangible Sensations: Part II (Proceedings of EuroHaptics), 6192, pages: 79-86, Lecture Notes in Computer Science, Springer, Amsterdam, Netherlands, 2010, Poster presentation given by Landin (inproceedings)

hi

[BibTex]

[BibTex]


no image
VerroTouch: A Vibrotactile Feedback System for Minimally Invasive Robotic Surgery

Kuchenbecker, K. J., Gewirtz, J., McMahan, W., Standish, D., Bohren, J., Martin, P., Wedmid, A., Mendoza, P. J., Lee, D. I.

In Proc. 28th World Congress of Endourology, 2010, PS8-14. Poster presentation given by Wedmid (inproceedings)

hi

[BibTex]

[BibTex]


no image
Are reaching movements planned in kinematic or dynamic coordinates?

Ellmer, A., Schaal, S.

In Abstracts of Neural Control of Movement Conference (NCM 2010), Naples, Florida, 2010, 2010, clmc (inproceedings)

Abstract
Whether human reaching movements are planned and optimized in kinematic (task space) or dynamic (joint or muscle space) coordinates is still an issue of debate. The first hypothesis implies that a planner produces a desired end-effector position at each point in time during the reaching movement, whereas the latter hypothesis includes the dynamics of the muscular-skeletal control system to produce a continuous end-effector trajectory. Previous work by Wolpert et al (1995) showed that when subjects were led to believe that their straight reaching paths corresponded to curved paths as shown on a computer screen, participants adapted the true path of their hand such that they would visually perceive a straight line in visual space, despite that they actually produced a curved path. These results were interpreted as supporting the stance that reaching trajectories are planned in kinematic coordinates. However, this experiment could only demonstrate that adaptation to altered paths, i.e. the position of the end-effector, did occur, but not that the precise timing of end-effector position was equally planned, i.e., the trajectory. Our current experiment aims at filling this gap by explicitly testing whether position over time, i.e. velocity, is a property of reaching movements that is planned in kinematic coordinates. In the current experiment, the velocity profiles of cursor movements corresponding to the participant's hand motions were skewed either to the left or to the right; the path itself was left unaltered. We developed an adaptation paradigm, where the skew of the velocity profile was introduced gradually and participants reported no awareness of any manipulation. Preliminary results indicate that the true hand motion of participants did not alter, i.e. there was no adaptation so as to counterbalance the introduced skew. However, for some participants, peak hand velocities were lowered for higher skews, which suggests that participants interpreted the manipulation as mere noise due to variance in their own movement. In summary, for a visuomotor transformation task, the hypothesis of a planned continuous end-effector trajectory predicts adaptation to a modified velocity profile. The current experiment found no systematic adaptation under such transformation, but did demonstrate an effect that is more in accordance that subjects could not perceive the manipulation and rather interpreted as an increase of noise.

am

[BibTex]

[BibTex]


no image
Optimality in Neuromuscular Systems

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

In 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2010, clmc (inproceedings)

Abstract
Abstract? We provide an overview of optimal control meth- ods to nonlinear neuromuscular systems and discuss their lim- itations. Moreover we extend current optimal control methods to their application to neuromuscular models with realistically numerous musculotendons; as most prior work is limited to torque-driven systems. Recent work on computational motor control has explored the used of control theory and esti- mation as a conceptual tool to understand the underlying computational principles of neuromuscular systems. After all, successful biological systems regularly meet conditions for stability, robustness and performance for multiple classes of complex tasks. Among a variety of proposed control theory frameworks to explain this, stochastic optimal control has become a dominant framework to the point of being a standard computational technique to reproduce kinematic trajectories of reaching movements (see [12]) In particular, we demonstrate the application of optimal control to a neuromuscular model of the index finger with all seven musculotendons producing a tapping task. Our simu- lations include 1) a muscle model that includes force- length and force-velocity characteristics; 2) an anatomically plausible biomechanical model of the index finger that includes a tendi- nous network for the extensor mechanism and 3) a contact model that is based on a nonlinear spring-damper attached at the end effector of the index finger. We demonstrate that it is feasible to apply optimal control to systems with realistically large state vectors and conclude that, while optimal control is an adequate formalism to create computational models of neuro- musculoskeletal systems, there remain important challenges and limitations that need to be considered and overcome such as contact transitions, curse of dimensionality, and constraints on states and controls.

am

PDF [BibTex]

PDF [BibTex]


no image
Learning Policy Improvements with Path Integrals

Theodorou, E. A., Buchli, J., Schaal, S.

In International Conference on Artificial Intelligence and Statistics (AISTATS 2010), 2010, clmc (inproceedings)

Abstract
With the goal to generate more scalable algo- rithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classi- cal techniques from optimal control and dy- namic programming with modern learning techniques from statistical estimation the- ory. In this vein, this paper suggests the framework of stochastic optimal control with path integrals to derive a novel approach to RL with parametrized policies. While solidly grounded in value function estimation and optimal control based on the stochastic Hamilton-Jacobi-Bellman (HJB) equations, policy improvements can be transformed into an approximation problem of a path inte- gral which has no open parameters other than the exploration noise. The resulting algorithm can be conceived of as model- based, semi-model-based, or even model free, depending on how the learning problem is structured. Our new algorithm demon- strates interesting similarities with previous RL research in the framework of proba- bility matching and provides intuition why the slightly heuristically motivated proba- bility matching approach can actually per- form well. Empirical evaluations demon- strate significant performance improvements over gradient-based policy learning and scal- ability to high-dimensional control problems. We believe that Policy Improvement with Path Integrals (PI2) offers currently one of the most efficient, numerically robust, and easy to implement algorithms for RL based on trajectory roll-outs.

am

PDF [BibTex]

PDF [BibTex]


no image
Learning optimal control solutions: a path integral approach

Theodorou, E., Schaal, S.

In Abstracts of Neural Control of Movement Conference (NCM 2010), Naples, Florida, 2010, 2010, clmc (inproceedings)

Abstract
Investigating principles of human motor control in the framework of optimal control has had a long tradition in neural control of movement, and has recently experienced a new surge of investigations. Ideally, optimal control problems are addresses as a reinforcement learning (RL) problem, which would allow to investigate both the process of acquiring an optimal control solution as well as the solution itself. Unfortunately, the applicability of RL to complex neural and biomechanics systems has been largely impossible so far due to the computational difficulties that arise in high dimensional continuous state-action spaces. As a way out, research has focussed on computing optimal control solutions based on iterative optimal control methods that are based on linear and quadratic approximations of dynamical models and cost functions. These methods require perfect knowledge of the dynamics and cost functions while they are based on gradient and Newton optimization schemes. Their applicability is also restricted to low dimensional problems due to problematic convergence in high dimensions. Moreover, the process of computing the optimal solution is removed from the learning process that might be plausible in biology. In this work, we present a new reinforcement learning method for learning optimal control solutions or motor control. This method, based on the framework of stochastic optimal control with path integrals, has a very solid theoretical foundation, while resulting in surprisingly simple learning algorithms. It is also possible to apply this approach without knowledge of the system model, and to use a wide variety of complex nonlinear cost functions for optimization. We illustrate the theoretical properties of this approach and its applicability to learning motor control tasks for reaching movements and locomotion studies. We discuss its applicability to learning desired trajectories, variable stiffness control (co-contraction), and parameterized control policies. We also investigate the applicability to signal dependent noise control systems. We believe that the suggested method offers one of the easiest to use approaches to learning optimal control suggested in the literature so far, which makes it ideally suited for computational investigations of biological motor control.

am

[BibTex]

[BibTex]