Publications
Results
- Showing results for:
- Reset all filters
Search results
-
Journal articleJamisola RS, Kormushev P, Roberts RG, et al., 2016,
Task-Space Modular Dynamics for Dual-Arms Expressed through a Relative Jacobian
, Journal of Intelligent & Robotic Systems, Pages: 1-14, ISSN: 1573-0409 -
Conference paperFlaxman S, Sejdinovic D, Cunningham JP, et al., 2016,
Bayesian Learning of Kernel Embeddings
, UAI'16Kernel methods are one of the mainstays of machine learning, but the problemof kernel learning remains challenging, with only a few heuristics and verylittle theory. This is of particular importance in methods based on estimationof kernel mean embeddings of probability measures. For characteristic kernels,which include most commonly used ones, the kernel mean embedding uniquelydetermines its probability measure, so it can be used to design a powerfulstatistical testing framework, which includes nonparametric two-sample andindependence tests. In practice, however, the performance of these tests can bevery sensitive to the choice of kernel and its lengthscale parameters. Toaddress this central issue, we propose a new probabilistic model for kernelmean embeddings, the Bayesian Kernel Embedding model, combining a Gaussianprocess prior over the Reproducing Kernel Hilbert Space containing the meanembedding with a conjugate likelihood function, thus yielding a closed formposterior over the mean embedding. The posterior mean of our model is closelyrelated to recently proposed shrinkage estimators for kernel mean embeddings,while the posterior uncertainty is a new, interesting feature with variouspossible applications. Critically for the purposes of kernel learning, ourmodel gives a simple, closed form marginal pseudolikelihood of the observeddata given the kernel hyperparameters. This marginal pseudolikelihood caneither be optimized to inform the hyperparameter choice or fully Bayesianinference can be used.
-
Journal articleMa ZB, Yang Y, Liu YX, et al., 2016,
Recurrently decomposable 2-D convolvers for FPGA-based digital image processing
, IEEE Transactions on Circuits and Systems, Vol: 63, Pages: 979-983, ISSN: 1549-7747Two-dimensional (2-D) convolution is a widely used operation in image processing and computer vision, characterized by intensive computation and frequent memory accesses. Previous efforts to improve the performance of field-programmable gate array (FPGA) convolvers focused on the design of buffering schemes and on minimizing the use of multipliers. A recently proposed recurrently decomposable (RD) filter design method can reduce the computational complexity of 2-D convolutions by splitting the convolution between an image and a large mask into a sequence of convolutions using several smaller masks. This brief explores how to efficiently implement RD based 2-D convolvers using FPGA. Three FPGA architectures are proposed based on RD filters, each with a different buffering scheme. The conclusion is that RD based architectures achieve higher area efficiency than other previously reported state-of-the-art methods, especially for larger convolution masks. An area efficiency metric is also suggested, which allows the most appropriate architecture to be selected.
-
Book chapterAhmadzadeh SR, Kormushev P, 2016,
Visuospatial Skill Learning
, Handling Uncertainty and Networked Structure in Robot Control, Editors: Busoniu, Tamás, Publisher: Springer International Publishing, Pages: 75-99, ISBN: 978-3-319-26327-4 -
Book chapterKormushev P, Ahmadzadeh SR, 2016,
Robot Learning for Persistent Autonomy
, Handling Uncertainty and Networked Structure in Robot Control, Editors: Busoniu, Tamás, Publisher: Springer International Publishing, Pages: 3-28, ISBN: 978-3-319-26327-4 -
Conference paperMaurelli F, Lane D, Kormushev P, et al., 2016,
The PANDORA project: a success story in AUV autonomy
, OCEANS Conference 2016, Publisher: IEEE, ISSN: 0197-7385This paper presents some of the results of the EU-funded project PANDORA - Persistent Autonomy Through Learning Adaptation Observation and Re-planning. The project was three and a half years long and involved several organisations across Europe. The application domain is underwater inspection and intervention, a topic particularly interesting for the oil and gas sector, whose representatives constituted the Industrial Advisory Board. Field trials were performed at The Underwater Centre, in Loch Linnhe, Scotland, and in harbour conditions close to Girona, Spain.
-
Journal articleFilippi S, Barnes CP, Kirk PDW, et al., 2016,
Robustness of MEK-ERK Dynamics and Origins of Cell-to-Cell Variability in MAPK Signaling
, CellReports -
Conference paperEleftheriadis S, Rudovic O, Deisenroth MP, et al., 2016,
Variational Gaussian Process Auto-Encoder for Ordinal Prediction of Facial Action Units.
, Pages: 154-170 -
Conference paperPantic M, Evers V, Deisenroth M, et al., 2016,
Social and Affective Robotics Tutorial
, 24th ACM Multimedia Conference (MM), Publisher: ASSOC COMPUTING MACHINERY, Pages: 1477-1478- Author Web Link
- Cite
- Citations: 3
-
Conference paperCalandra R, Ivaldi S, Deisenroth MP, et al., 2015,
Learning Torque Control in Presence of Contacts using Tactile Sensing from Robot Skin
, 2015 IEEE-RAS International Conference on Humanoid Robots, Publisher: IEEEWhole-body control in unknown environments ischallenging: Unforeseen contacts with obstacles can lead topoor tracking performance and potential physical damages ofthe robot. Hence, a whole-body control approach for futurehumanoid robots in (partially) unknown environments needsto take contact sensing into account, e.g., by means of artificialskin. However, translating contacts from skin measurementsinto physically well-understood quantities can be problematicas the exact position and strength of the contact needs to beconverted into torques. In this paper, we suggest an alternativeapproach that directly learns the mapping from both skinand the joint state to torques. We propose to learn suchan inverse dynamics models with contacts using a mixtureof-contactsapproach that exploits the linear superimpositionof contact forces. The learned model can, making use ofuncalibrated tactile sensors, accurately predict the torquesneeded to compensate for the contact. As a result, tracking oftrajectories with obstacles and tactile contact can be executedmore accurately. We demonstrate on the humanoid robot iCubthat our approach improve the tracking error in presence ofdynamic contacts.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.