@inproceedings{StiSma2010, Author = {Stillfried, Georg and Smagt, Patrick van der}, Title = {Movement model of a human hand based on magnetic resonance imaging ({MRI})}, Year = {2010}, Booktitle = {International Conference on Applied Bionics and Biomechanics (ICABB)}, Keywords = {movement brml} } @inproceedings{HopLakUrbSma2010, Author = {H{\"o}ppner, Hannes and Lakatos, Dominic and Urbanek, Holger and Smagt, Patrick van der}, Title = {The Arm-Perturbator: Design of a Wearable Perturbation Device to measure Limb Impedance}, Year = {2010}, Booktitle = {International Conference on Applied Bionics and Biomechanics (ICABB)}, Keywords = {movement brml} } @inproceedings{StrSaaPotSma2010, Author = {Strohmayr, Michael and Saal, Hannes and Potdar, Abhijit and Smagt, Patrick van der}, Title = {The {DLR} Touch Sensor {I}: A Flexible Tactile Sensor for Robotic Hands based on a Crossed-Wire Approach}, Year = {2010}, Pages = {897-903}, Booktitle = {Proc. IEEE/RSJ International Conference on Intelligent Robots and Systems}, Doi = {10.1109/IROS.2010.5650191}, Keywords = {brml} } @inproceedings{MaiSma2008, Author = {Maier, Sebastian and Smagt, Patrick van der}, Title = {Surface {EMG} suffices to classify the motion of each finger independently}, Year = {2008}, Booktitle = {Proceedings of MOVIC. 9th International Conference on Motion and Vibration Control}, Keywords = {BMI brml} } @inbook{ArbMetSma2008, Author = {Arbib, Michael and Metta, Giorgio and Smagt, Patrick van der}, Title = {Neurorobotics: From Vision to Action}, Year = {2008}, Pages = {1453--1480}, Editor = {B. Siciliano and O. Khatib}, Publisher = {Springer Verlag}, Booktitle = {Springer Handbook of Robotics}, chapter = {62}, Keywords = {brml movement} } @inproceedings{BitSma2006, Author = {Bitzer, Sebastian and Smagt, Patrick van der}, Title = {Learning {EMG} control of a robotic hand: towards active prostheses}, Year = {2006}, Pages = {2819-2823}, Booktitle = {Proceedings 2006 IEEE International Conference on Robotics and Automation}, Doi = {10.1109/ROBOT.2006.1642128}, Keywords = {BMI movement brml} } @article{CasSma2009, Author = {Castellini, Claudio and Smagt, Patrick van der}, Title = {Surface {EMG} in Advanced Hand Prosthetics}, Journal = {Biological Cybernetics}, Year = {2009}, Volume = {100}, Number = {1}, Pages = {35--47}, Doi = {10.1007/s00422-008-0278-1}, Keywords = {BMI movement brml} } @inproceedings{CasSmaSan2008, Author = {Castellini, Claudio and Smagt, Patrick van der and Sandini, Giulio and Hirzinger, Gerd}, Title = {Surface {EMG} for Force Control of Mechanical Hands}, Year = {2008}, Pages = {725--730}, Booktitle = {Proceedings - IEEE International Conference on Robotics and Automation}, Doi = {10.1109/ROBOT.2008.4543291}, Keywords = {BMI brml} } @inproceedings{FisSmaHir1998, Author = {Fischer, Max and Smagt, Patrick van der and Hirzinger, Gerd}, Title = {Learning Techniques in a Dataglove Based Telemanipulation System for the {DLR} Hand}, Year = {1998}, Pages = {1603--1608}, Booktitle = {Transactions of the IEEE International Conference on Robotics and Automation}, Keywords = {brml movement} } @article{GreSma2008, Author = {Grebenstein, Markus and Smagt, Patrick van der}, Title = {Antagonism for a highly anthropomorphic hand-arm system}, Journal = {Advanced Robotics}, Year = {2008}, Volume = {22}, Number = {1}, Pages = {39-55}, Doi = {10.1163/156855308X291836}, Keywords = {movement brml} } @incollection{GroKrSma1991, Author = {Groen, Frans and Kr{\"o}se, Ben and Smagt, Patrick van der}, Title = {Parallel Distributed Processing in Autonomous Robot Systems}, Year = {1991}, Pages = {24--25}, Month = {May}, Publisher = {The Dutch Foundation for Neural Networks}, Address = {Nijmegen, The Netherlands}, Booktitle = {Proceedings of the 1991 Symposium on Neural Networks}, Keywords = {brml machine-learning} } @incollection{GroKrSma1993, Author = {Groen, Frans and Kr{\"o}se, Ben and Smagt, Patrick van der and Bartholomeus, M. G. P. and Noest, A. J.}, Title = {Neural Networks for robot eye-hand coordination}, Year = {1993}, Pages = {211-218}, Month = {Sep.}, Editor = {S. Gielen and B. Kappen}, Publisher = {Springer Verlag}, Address = {London}, Booktitle = {Artificial neural networks}, Keywords = {brml machine-learning} } @article{GruSmaZee2009, Author = {Gruijl, Jornt de and Smagt, Patrick van der and Zeeuw, Chris de}, Title = {Anticipatory grip force control using a cerebellar model}, Journal = {Neuroscience}, Year = {2009}, Volume = {162}, Number = {3}, Pages = {777-786}, PMID = {19249337}, Doi = {10.1016/j.neuroscience.2009.02.041}, Keywords = {brml movement} } @article{HesSarSma1994, Author = {Hesselroth, Ted and Sarkar, Kakali and Smagt, Patrick van der and Schulten, Klaus}, Title = {Neural network control of a pneumatic robot arm}, Journal = {IEEE Transactions on Systems, Man, and Cybernetics}, Year = {1994}, Volume = {24}, Number = {1}, Pages = {28--38}, Month = {January}, Doi = {10.1109/21.259683}, Keywords = {brml machine-learning movement}, Abstract = {A neural map algorithm has been employed to control a five-joint pneumatic robot arm and gripper through feedback from two video cameras. The pneumatically driven robot arm (SoftArm) employed in this investigation shares essential mechanical characteristics with skeletal muscle systems. To control the position of the arm, 200 neurons formed a network representing the three-dimensional workspace embedded in a four-dimensional system of coordinates from the two cameras, and learned a three-dimensional set of pressures corresponding to the end effector positions, as well as a set of 3x4 Jacobian matrices for interpolating between these positions. The gripper orientation was achieved through adaptation of a 1x4 Jacobian matrix for a fourth joint. Because of the properties of the rubber-tube actuators of the SoftArm, the position as a function of supplied pressure is nonlinear, nonseparable, and exhibits hysteresis. Nevertheless, through the neural network learning algorithm the position could be controlled to an accuracy of about one pixel (3 mm) after two hundred learning steps and the orientation could be controlled to two pixels after eight hundred learning steps. This was achieved through employment of a linear correction algorithm using the Jacobian matrices mentioned above. Applications of repeated corrections in each positioning and grasping step leads to a very robust control algorithm since the Jacobians learned by the network have to satisfy the weak requirement that the Jacobian yields a reduction of the distance between gripper and target.} } @incollection{JanSmaGro1992, Author = {Jansen, Arjan and Smagt, Patrick van der and Groen, Frans}, Title = {High-precision robot control: The nested network}, Year = {1992}, Pages = {583-586}, Month = {Sep.}, Editor = {I. Aleksander and J. Taylor}, Publisher = {North-Holland/Elsevier Science Publishers}, Address = {Amsterdam, The Netherlands}, Booktitle = {Artificial Neural Networks 2}, Keywords = {machine-learning brml}, Abstract = {Traditional robot control is based on precise models of sensors and manipulators. Increasing complexity of required tasks, sensors, and manipulators result in models which are extremely complex to build at the required precision. In the realm of pick-and-place problems, we aim at designing highly adaptive controllers which require minimum knowledge of the manipulator and its sensors. In this area, several models have proven successful in one area or another. The use of a single feed-forward network trained with conjugate gradient back-propagation gives fast and highly adaptive approximation, but needs up to ten feedback steps to get high-precision results. Kohonen networks give a precision up to 0.5cm.~with only two steps, but need thousands of iterations to attain reasonable results. In this paper we introduce the nested network method based on search trees which adapts in real-time and reaches a grasping precision of up to 1mm.~in only three steps.} } @incollection{JanSmaGro1995, Author = {Jansen, Arjan and Smagt, Patrick van der and Groen, Frans}, Title = {Nested Networks for Robot Control}, Year = {1995}, Pages = {221--239}, Editor = {A. F. Murray}, Publisher = {Kluwer Academic Publishers}, Address = {Dordrecht, the Netherlands}, Booktitle = {Applications of Neural Networks}, Url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.37.7858}, Keywords = {brml machine-learning}, Abstract = {We present a method for accurate representation of high-dimensional unknown functions from random samples drawn from its input space. The method builds representations of the function by recursively splitting the input space in smaller subspaces. The representations of the function at all levels (i.e., depths in the tree) are retained during the learning process, such that a good generalisation is available as well as more accurate representations in some subareas. Therefore, fast and accurate learning are combined in this method.} } @book{KrSma1994, Author = {Kr{\"o}se, Ben and Smagt, Patrick van der}, Title = {An Introduction to Neural Networks}, Year = {1994}, Publisher = {University of Amsterdam}, Address = {Amsterdam, The Netherlands}, Howpublished = {lecture book}, Keywords = {brml machine-learning} } @incollection{KrSmaGro1993, Author = {Kr{\"o}se, Ben and Smagt, Patrick van der and Groen, Frans}, Title = {A one-eyed self-learning robot manipulator}, Year = {1993}, Pages = {19-28}, Editor = {G. Bekey and K. Goldberg}, Publisher = {Kluwer Academic Publishers, Dordrecht}, Booktitle = {Neural networks in robotics}, Keywords = {movement brml machine-learning}, Abstract = {A self-learning, adaptive control system for a robot arm using a vision system in a feedback loop is described. The task of the control system is to position the end-effector as accurate as possible directly above a target object, so that it can be grasped. The camera of the vision system is positioned in the end-effector and the visual information is used directly to control the robot. Two strategies are presented to solve the problem of obtaining 3D information from a single camera: a) using the size of the target object and b) using information from a sequence of images from the moving camera. In both cases a neural network is trained to perform the desired mapping.} } @inproceedings{PanEibGre2008, Author = {Panzer, Heiko and Eiberger, Oliver and Grebenstein, Markus and Wolf, Sebastian and Schaefer, Peter and Smagt, Patrick van der}, Title = {Human motion range data optimizes anthropomorphic robotic hand-arm system design}, Year = {2008}, Booktitle = {Proc. 9th International Conference on Motion and Vibration Control (MOVIC)}, Keywords = {movement brml} } @article{PetSma2002, Author = {Peters, Jan and Smagt, Patrick van der}, Title = {Searching a Scalable Approach to Cerebellar Based Control}, Journal = {Applied Intelligence}, Year = {2002}, Volume = {17}, Number = {1}, Pages = {11-33}, Doi = {10.1023/A:1015775631060}, Keywords = {brml movement} } @incollection{Sma1997, Author = {Smagt, Patrick van der}, Title = {Teaching a robot to see how it moves}, Year = {1997}, Pages = {195--219}, Editor = {Antony Browne}, Publisher = {Institute of Physics Publishing}, Booktitle = {Neural Network Perspectives on Cognition and Adaptive Robotics}, Keywords = {brml movement} } @article{Sma1998, Author = {Smagt, Patrick van der}, Title = {Cerebellar Control of Robot Arms}, Journal = {Connection Science}, Year = {1998}, Volume = {10}, Pages = {301--320}, Editor = {Noel Sharkey}, Doi = {10.1080/095400998116468}, Keywords = {movement brml}, Abstract = {Decades of research into the structure and function of the cerebellum have led to a clear understanding of many of its cells, as well as how learning takes place. Furthermore, there are many theories on what signals the cerebellum operates on, and how it works in concert with other parts of the nervous system. Nevertheless, the application of computational cerebellar models to the control of robot dynamics remains in its infant state. To date, a few applications have been realized, yet limited to the control of traditional robot structures which, strictly speaking, do not require adaptive control for the tasks that are performed since their dynamic structures are relatively simple. The currently emerging family of light-weight robots~\cite{Hir96} poses a new challenge to robot control: due to their complex dynamics traditional methods, depending on a full analysis of the dynamics of the system, are no longer applicable since the joints influence each other dynamics during movement. Can artificial cerebellar models compete here? In this overview paper we present a succinct introduction of the cerebellum, and discuss where it could be applied to tackle problems in robotics. Without conclusively answering the above question, an overview of several applications of cerebellar models to robot control is given.} } @article{Sma2000, Author = {Smagt, Patrick van der}, Title = {Benchmarking Cerebellar Control}, Journal = {Robotics and Autonomous Systems}, Year = {2000}, Volume = {32}, Pages = {237--251}, Doi = {10.1016/S0921-8890(00)00090-7}, Keywords = {movement brml} } @phdthesis{Sma1995, Author = {Smagt, Patrick van der}, Title = {Visual Robot Arm Guidance using Neural Networks}, Year = {1995}, Month = {March}, School = {Dept of Computer Systems, University of Amsterdam}, Keywords = {brml movement machine-learning} } @article{Sma1994, Author = {Smagt, Patrick van der}, Title = {Minimisation methods for training feed-forward networks}, Journal = {Neural Networks}, Year = {1994}, Volume = {7}, Number = {1}, Pages = {1--11}, Keywords = {brml machine-learning}, Abstract = {Minimisation methods for training feed-forward networks with back-propagation are compared. Feed-forward neural network training is a special case of function minimisation, where no explicit model of the data is assumed. Therefore, and due to the high dimensionality of the data, linearisation of the training problem through use of orthogonal basis functions is not desirable. The focus is on function minimisation on any basis. Quasi-Newton and conjugate gradient methods are reviewed, and the latter are shown to be a special case of error back-propagation with momentum term. Three feed-forward learning problems are tested with five methods. It is shown that, due to the fixed stepsize, standard error back-propagation performs well in avoiding local minima. However, by using not only the local gradient but also the second derivative of the error function a much shorter training time is required. Conjugate gradient with Powell restarts shows to be the superior method.} } @article{Sma1994a, Author = {Smagt, Patrick van der}, Title = {Simderella: a robot simulator for neuro-controller design}, Journal = {Neurocomputing}, Year = {1994}, Volume = {6}, Number = {2}, Pages = {281--285}, Publisher = {Elsevier Science Publishers}, Keywords = {brml}, Abstract = {Simderella is a general purpose Public Domain simulator of robot manipulator kinematics. It was developed over the course of several years to aid my research in neural networks for robot arm control. Simderella is intended to be a tool for speeding development of controllers for robot arms. Computational efficiency is essential for controllers, and can be best evaluated by separating controller and simulator processes. Such a separation facilitates code modularity and code migration to extant platforms connected to real robot arms. The operation of the separate processes is synchronised by message passing. Under Unix, sockets are the most widely supported method for interprocess communication. For example, shell pipes are implemented using sockets. The three programs which constitute Simderella: connel, simmel, and bemmel, communicate over sockets. Connel is the controller, and should be programmed by the neural network experimenter. Simmel is the actual robot simulator, and calculates (among other things) the forward kinematics. Bemmel is an X-window based program for robot visualisation.} } @incollection{Sma1990, Author = {Smagt, Patrick van der}, Title = {A Comparative Study of Neural Network Algorithms Applied to Optical Character Recognition}, Year = {1990}, Pages = {1037--1044}, Month = {July}, Publisher = {the Association for Computing Machinery, Inc.}, Address = {New York}, Booktitle = {Proceedings of the Third International Conference on Industrial and Engineering Applications of Artificial Intelligence and Expert Systems}, Keywords = {brml machine-learning} } @article{SmaBul2002, Author = {Smagt, Patrick van der and Bullock, Daniel}, Title = {Guest editorial for Special Issue on Scalable Applications of Neural Networks to Robotics}, Journal = {Applied Intelligence}, Year = {2002}, Volume = {17}, Pages = {7--10}, Doi = {10.1023/A:1015762314222}, Keywords = {brml} } @techreport{SmaBul1997, Author = {Smagt, Patrick van der and Bullock, Daniel}, Title = {Can Artificial Cerebellar Models Compete to Control Robots?}, Year = {1997}, Institution = {DLR Oberpfaffenhofen}, Keywords = {brml} } @inproceedings{SmaDevGro1995, Author = {Smagt, Patrick van der and Dev, Anuj and Groen, Frans}, Title = {A visually guided robot and a neural network join to grasp slanted objects}, Year = {1995}, Pages = {144-150}, Month = {Sep.}, Editor = {B. Kappen and S. Gielen}, Publisher = {Foundation for Neural Networks, Nijmegen}, Address = {Nijmegen, Netherlands}, Booktitle = {Proceedings of the 3rd SNN Symposium on Neural Networks}, Keywords = {brml}, Abstract = {In this paper we introduce a method for model-free monocular visual guidance of a robot arm. The robot arm, with a single camera in its end-effector, should be positioned above a target, with a changing pan and tilt, which is placed against a textured background. It is shown that a trajectory can be planned in visual space by using components of the optic flow, and this trajectory can be translated to joint torques by a self-learning neural network. No model of the robot, camera, or environment is used. The method reaches a high grasping accuracy after only a few trials.} } @incollection{SmaGro1997, Author = {Smagt, Patrick van der and Groen, Frans}, Title = {Visual Feedback in Motion}, Year = {1997}, Pages = {37--73}, Editor = {O. Omidvar and P. van der Smagt}, Publisher = {Academic Press}, Address = {Boston, Massachusetts}, Booktitle = {Neural Systems for Robotics}, Keywords = {brml} } @inproceedings{SmaGro1995, Author = {Smagt, Patrick van der and Groen, Frans}, Title = {Approximation with neural networks: Between local and global approximation}, Year = {1995}, Pages = {II:1060-II:1064}, Note = {(invited paper)}, Booktitle = {Proceedings of the 1995 International Conference on Neural Networks}, Keywords = {brml machine-learning}, Abstract = {We investigate neural network based approximation methods. These methods depend on the locality of the basis functions. After discussing local and global basis functions, we propose a a multi-resolution hierarchical method. The various resolutions are stored at various levels in a tree. At the root of the tree, a global approximation is kept; the leafs store the learning samples themselves. Intermediate nodes store intermediate representations. In order to find an optimal partitioning of the input space, self-organising maps (SOM's) are used. The proposed method has implementational problems reminiscent of those encountered in many-particle simulations. We will investigate the parallel implementation of this method, using parallel hierarchical methods for many-particle simulations as a starting point.} } @inproceedings{SmaGroGro1994, Author = {Smagt, Patrick van der and Groen, Frans and Groenewoud, Ferry van het}, Title = {Robotic Hand-Eye Coordination using Multi-Resolution Linear Perceptron Representation}, Year = {1994}, Pages = {85--92}, Editor = {H. M. Groenboom and H. W. Klijn Hesselink and M. M. Lankhorst}, Booktitle = {Proceedings of the 1994 Groningen Student Conference on Computer Science}, Keywords = {brml machine-learning}, Abstract = {We present a method for accurate representation of high-dimensional unknown functions from random samples drawn from its input space. The method builds representations of the function by recursively splitting the input space in smaller subspaces; these representations are essentially coded as nodes in a tree. The representations of the function at all levels (i.e., depths in the tree) are retained during the learning process, such that a good generalisation is available as well as more accurate representations in some subareas. Therefore, fast and accurate learning are combined in this method. An essential property of the method is its adaptivity through continuous learning. In particular, approximations at different levels of the tree are trained on sets of learning samples which have different temporal histories.} } @inproceedings{SmaGroGro1994a, Author = {Smagt, Patrick van der and Groen, Frans and Groenewoud, Ferry van het}, Title = {The locally linear nested network for robot manipulation}, Year = {1994}, Pages = {2787--2792}, Booktitle = {Proceedings of the IEEE International Conference on Neural Networks}, Keywords = {brml machine-learning}, Abstract = {We present a method for accurate representation of high-dimensional unknown functions from random samples drawn from its input space. The method builds representations of the function by recursively splitting the input space in smaller subspaces, while in each of these subspaces a linear approximation is computed. The representations of the function at all levels (i.e., depths in the tree) are retained during the learning process, such that a good generalisation is available as well as more accurate representations in some subareas. Therefore, fast and accurate learning are combined in this method. The method, which is applied to hand-eye coordination of a robot arm, is shown to be superior to other neural networks.} } @inproceedings{SmaGroKr1995, Author = {Smagt, Patrick van der and Groen, Frans and Kr{\"o}se, Ben}, Title = {A Monocular Robot Arm can be Neurally Positioned}, Year = {1995}, Pages = {123--130}, Editor = {U. Rembold and R. Dillmann and L. O. Hertzberger and T. Kanade}, Publisher = {IOS Press}, Booktitle = {Proceedings of the 1995 International Conference on Intelligent Autonomous Systems}, Keywords = {brml}, Abstract = {In this paper we introduce a method for model-free monocular visual guidance of a robot arm. The robot arm, with a single camera in its end-effector, should be positioned above a visually observed target. It is shown that a trajectory can be planned in visual space by using components of the optic flow, and this trajectory can be translated to joint torques by a self-learning neural network. No model of the robot, camera, or environment is used. The method reaches a high grasping accuracy after only a few trials.} } @article{SmaGroSch1996, Author = {Smagt, Patrick van der and Groen, Frans and Schulten, Klaus}, Title = {Analysis and control of a rubbertuator arm}, Journal = {Biological Cybernetics}, Year = {1996}, Volume = {75}, Number = {5}, Pages = {433--440}, Url = {http://www.robotic.dlr.de/fileadmin/robotic/smagt/publications/SmaGroSch1996.pdf}, Abstract = {The control of light-weight compliant robot arms is cumbersome due to the fact that their Coriolis forces are large, and the forces exerted by the relatively weak actuators may change in time due to external (e.g., temperature) influences. We describe and analyse the behaviour of a light-weight robot arm, the SoftArm robot. It is found that the hysteretic force-position relationship of the arm can be explained from its structure. This knowledge is used in the construction of a neural-network based controller. Experiments show that the network is able to accurately control the robot arm after a training session of only a few minutes.} } @techreport{SmaGroKr1993, Author = {Smagt, Patrick van der and Groen, Frans and Kr{\"o}se, Ben}, Title = {Robot hand-eye coordination using neural networks}, Year = {1993}, Number = {CS-93-10}, Month = {Oct.}, Institution = {Dept. of Comp. Sys, University of Amsterdam}, Keywords = {brml}, Abstract = {This paper focuses on static hand-eye coordination. The key issue that will be addressed is the construction of a controller that eliminates the need for calibration. Instead, the system should be self-learning and must be able to adapt itself to changes in the environment. In this application, only positional information in the system will be used; hence the above reference `static.' Three coordinate domains are used to describe the system: the Cartesian world-domain, the vision domain, and the robot domain. The task that is set out to be solved is the following. A robot manipulator has to be positioned directly above a pre-specified target, such that it can be grasped. The target is specified in terms of visual parameters. Only the (x,y,z) position of the end-effector relative to the target is taken into account; this suffices for many pick-and-place problems encountered in industry. (In a number of cases, also the rotation of the hand is of importance, but this rotation can be executed separate from the 3D positioning problem.) Thus the remaining problem is 3 degrees-of-freedom (DoF).} } @inproceedings{SmaHir1998, Author = {Smagt, Patrick van der and Hirzinger, Gerd}, Title = {Why Feed-Forward Networks are in a Bad Shape}, Year = {1998}, Pages = {159--164}, Editor = {L. Niklasson and M. Bod{\'e}n and T. Ziemke}, Publisher = {Springer}, Booktitle = {Proceedings of the 8th International Conference on Artificial Neural Networks}, Keywords = {brml machine-learning}, Abstract = {It has often been noted that the learning problem in feed-forward neural networks is very badly conditioned. Although, generally, the special form of the transfer function is usually taken to be the cause of this condition, we show that it is caused by the manner in which neurons are connected. By analyzing the expected values of the Hessian in a feed-forward network it is shown that, even in a network where all the learning samples are well chosen and the transfer function is not in its saturated state, the system has a non-optimal condition. We subsequently propose a change in the feed-forward network structure which alleviates this problem. We finally demonstrate the positive influence of this approach.} } @incollection{SmaHir1998a, Author = {Smagt, Patrick van der and Hirzinger, Gerd}, Title = {Solving the Ill-Conditioning in Neural Network Learning}, Year = {1998}, Pages = {193--206}, Editor = {J. Orr and K. M{\"u}ller}, Publisher = {Springer Lecture Notes in Computer Science 1524}, Booktitle = {Neural Networks: Tricks of the Trade}, Keywords = {brml machine-learning} } @inproceedings{SmaHir2006, Author = {Smagt, Patrick van der and Hirzinger, Gerd}, Title = {{NEUROBOTICS}: The fusion of neuroscience and robotics}, Year = {2006}, Booktitle = {Proceedings ISR-2006, Joint Conference on Robotics / ROBOTIK} } @inproceedings{SmaHir2000, Author = {Smagt, Patrick van der and Hirzinger, Gerd}, Title = {The cerebellum as computed torque model}, Year = {2000}, Pages = {760--763}, Publisher = {IEEE}, Booktitle = {Fourth International Conference on knowledge-Based Intelligent Engineering Systems \& Applied Technologies}, Keywords = {brml} } @incollection{SmaJanGro1992, Author = {Smagt, Patrick van der and Jansen, A. and Groen, Frans}, Title = {Interpolative robot control with the nested network approach}, Year = {1992}, Pages = {475-480}, Month = {Aug.}, Publisher = {IEEE}, Address = {Glasgow, Scotland, U.K.}, Booktitle = {IEEE Int. Symposium on Intelligent Control}, Keywords = {brml machine-learning}, Abstract = {In the realm of pick-and-place problems, we aim at designing highly adaptive controllers which require minimum knowledge of the manipulator and its sensors. In this area, several models have proven more or less successful in one area or another. Non-neural parameter estimation techniques have been investigated, but real-time computational requirements grow out of bound when the number of state variables increases. The use of a single feed-forward network trained with conjugate gradient back-propagation gives fast and highly adaptive approximation, but needs up to ten feedback steps to get high-precision results. Kohonen networks give a precision up to 0.5cm.~with only two steps, but need thousands of iterations to attain reasonable results. Instead, we introduce the nested network method based on search trees which adapts in real-time and reaches a grasping precision of up to 1mm.~in only three steps.} } @inproceedings{SmaKr1995, Author = {Smagt, Patrick van der and Kr{\"o}se, Ben}, Title = {Using Many-Particle Decomposition to get a Parallel Self-Organising Map}, Year = {1995}, Pages = {241-249}, Editor = {J. van Vliet}, Booktitle = {Proceedings of the 1995 Conference on Computer Science in the Netherlands}, Keywords = {brml machine-learning}, Abstract = {We propose a method for decreasing the computational complexity of self-organising maps. The method uses a partitioning of the neurons into disjoint clusters. Teaching of the neurons occurs on a cluster-basis instead of on a neuron-basis. For teaching an N-neuron network with N' samples, the computational complexity decreases from O(NN') to O(N log N'). Furthermore, we introduce a measure for the amount of order in a self-organising map, and show that the introduced algorithm behaves as well as the original algorithm.} } @incollection{SmaKrGro1992, Author = {Smagt, Patrick van der and Kr{\"o}se, Ben and Groen, Frans}, Title = {A Cyclops Learns to Grasp}, Year = {1992}, Pages = {88}, Publisher = {The Dutch Foundation for Neural Networks}, Address = {Nijmegen, The Netherlands}, Booktitle = {Proceedings of the Second Symposium on Neural Networks}, Keywords = {brml} } @incollection{SmaKr1991, Author = {Smagt, Patrick van der and Kr{\"o}se, Ben}, Title = {A Real-Time Learning Neural Robot Controller}, Year = {1991}, Pages = {351--356}, Month = {June}, Editor = {T. Kohonen and K. M\"akisara and O. Simula and J. Kangas}, Publisher = {North-Holland/Elsevier Science Publishers}, Booktitle = {Proceedings of the 1991 International Conference on Artificial Neural Networks}, Keywords = {brml}, Abstract = {A neurally based adaptive controller for a 6 degrees of freedom (DOF) robot manipulator with only rotary joints and a hand-held camera is described. The task of the system is to place the manipulator directly above an object that is observed by the camera (i.e., 2D hand-eye coordination). The requirement of adaptivity results in a system which does not make use of any inverse kinematics formulas or other detailed knowledge of the plant; instead, it should be self-supervising and adapt on-line. The proposed neural system will directly translate the preprocessed sensory data to joint displacements. It controls the plant in a feedback loop. The robot arm may make a sequence of moves before the target is reached, when in the meantime the network learns from experience. The network is shown to adapt quickly (in only tens of trials) and form a correct mapping from input to output domain.} } @incollection{SmaKrGro1992a, Author = {Smagt, Patrick van der and Kr{\"o}se, Ben and Groen, Frans}, Title = {A self-learning controller for monocular grasping}, Year = {1992}, Pages = {177-182}, Month = {Jun.}, Publisher = {IEEE}, Address = {Raleigh, N. C.}, Booktitle = {Proceedings of the 1992 IEEE/RSJ International Conference on Intelligent Robots and Systems}, Keywords = {brml}, Abstract = {A method is presented to learn 3D grasping of objects with unknown dimensions using a monocular eye-in-hand manipulator. From a sequence of images a motion profile is generated to approach the object of unknown size. It is shown that monocular visual information suffices to control the deceleration of the robot manipulator. A strategy for generating learning samples is presented, and simulation results demonstrate the effectiveness of the method.} } @incollection{SmaSch1993, Author = {Smagt, Patrick van der and Schulten, Klaus}, Title = {Control of pneumatic robot arm dynamics by a neural network}, Year = {1993}, Pages = {III/180-III/183}, Publisher = {Lawrence Erlbaum Associates, Inc., Hillsdale, NJ}, Address = {Portland, OR, USA}, Booktitle = {World congress on neural networks}, Url = {http://www.robotic.dlr.de/fileadmin/robotic/smagt/publications/SmaSch1993.pdf}, Keywords = {brml machine-learning}, Abstract = {The trajectory control of a pneumatically driven robot arm resembling a skeletal muscle system is studied. The arm dynamics have been shown to be hysteretic and significantly changing in time due to external influences (Hesselroth et al., IEEE Systems, Man and Cybernetics V24N1, pp. 28-38, 1994) thus requiring an adaptive controller. A highly adaptive feedback algorithm is suggested and shown to control accurately trajectory following tasks.} } @inproceedings{SmaSti2008, Author = {Smagt, Patrick van der and Stillfried, Georg}, Title = {Using {MRT} data to compute a hand kinematic model}, Year = {2008}, Booktitle = {Proc. 9th International Conference on Motion and Vibration Control (MOVIC)}, Keywords = {movement brml} } @inproceedings{UrbAlbSma2004, Author = {Urbanek, Holger and Albu-Sch{\"a}ffer, Alin and Smagt, Patrick van der}, Title = {Learning from demonstration: Repetitive movements for autonomous service robotics}, Year = {2004}, Volume = {4}, Pages = {3495-3500}, Booktitle = {2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, Doi = {10.1109/IROS.2004.1389957}, Keywords = {brml} } @book{OmiSma1997, Author = {Omidvar, Omid and Smagt, Patrick van der}, Title = {Neural Systems for Robotics}, Year = {1997}, Publisher = {Academic Press}, Address = {Boston, Massachusetts}, Isbn = {0125262809}, Booktitle = {Neural Systems for Robotics}, Keywords = {brml} } @inproceedings{CasSma2011, Author = {Castellini, Claudio and Smagt, Patrick van der}, Title = {Preliminary evidence of dynamic muscular synergies in human grasping}, Year = {2011}, Pages = {28-33}, Booktitle = {Proceedings of ICAR - International Conference on Advanced Robotics}, Doi = {10.1109/ICAR.2011.6088612}, Keywords = {movement brml} } @inproceedings{HoeLakUrbCasSma2011, Author = {H{\"o}ppner, Hannes and Lakatos, Dominic and Urbanek, Holger and Castellini, Claudio and van der Smagt, Patrick}, Title = {The Grasp Perturbator: Calibrating human grasp stiffness during a graded force task}, Year = {2011}, Pages = {3312-3316 }, Booktitle = {Proc. ICRA---International Conference on Robotics and Automation}, Doi = {10.1109/ICRA.2011.5980217}, Keywords = {movement brml} } @inproceedings{LakPetSma2011, Author = {Lakatos, Dominic and Petit, Florian and van der Smagt, Patrick}, Title = {Conditioning vs. Excitation Time for Estimating Impedance Parameters of the Human Arm}, Year = {2011}, Pages = {636-642}, Booktitle = {Proceedings of the 11th IEEE-RAS International Conference on Humanoid Robots}, Doi = {10.1109/Humanoids.2011.6100872}, Keywords = {movement brml} } @inproceedings{VogCasSma2011, Author = {Vogel, J{\"o}rn and Castellini, Claudio and Smagt, Patrick van der}, Title = {{EMG}-Based Teleoperation and Manipulation with the {DLR LWR-III}}, Year = {2011}, Pages = {672-678}, Booktitle = {Proc. IROS---International Conference on Intelligent Robots and Systems}, Doi = {10.1109/IROS.2011.6048345}, Keywords = {BMI brml movement} } @article{Sma2009, Author = {Smagt, Patrick van der and Grebenstein, Markus and Urbanek, Holger and Fligge, Nadine and Strohmayr, Michael and Stillfried, Georg and Parrish, Jonathon and Gustus, Agneta}, Title = {Robotics of human movements}, Journal = {Journal of physiology, Paris}, Year = {2009}, Volume = {103}, Number = {3-5}, Pages = {119-132}, PMID = {19686847}, Doi = {10.1016/j.jphysparis.2009.07.009}, Keywords = {movement brml} } @inproceedings{VogHadSim2010, Author = {Vogel, J{\"o}rn and Haddadin, Sami and Simeral, John D and Stavisky, Sergej D and Bacher, Dirk and Hochberg, Leigh R and Donoghue, John P and van der Smagt, Patrick}, Title = {Continuous Control of the {DLR} Light-weight Robot III by a human with tetraplegia using the {BrainGate2} Neural Interface System}, Year = {2010}, Booktitle = {International Symposium on Experimental Robotics (ISER)}, Url = {http://iser2010.grasp.upenn.edu/sites/iser2010/files/papers/ISER2010_0089_14e7fa3c7a71dfeeb4893068d51f1501.pdf}, Keywords = {BMI brml} } @inproceedings{Liu2010, Author = {Liu, Jing and Simeral, John D. and Stavisky, Sergey D. and Bacher, Daniel and Vogel, Joern and Haddadin, Sami and Smagt, Patrick van der and Hochberg, Leigh R. and Donoghue, John P.}, Title = {Control of a robotic arm using intracortical motor signal by an individual with tetraplegia in the {BrainGate2} trial}, Year = {2010}, Booktitle = {40th Annual Meeting in Neuroscience (SFN2010)}, Keywords = {BMI brml} } @article{RueOseSma2012, Author = {R{\"u}ckstie{\ss}, Thomas and Osendorfer, Christian and van der Smagt, Patrick}, Title = {Minimizing Data Consumption with Sequential Online Feature Selection}, Journal = {International Journal of Machine Learning and Cybernetics}, Year = {2013}, Volume = {4}, Number = {3}, Pages = {235-243}, Doi = {10.1007/s13042-012-0092-x}, Keywords = {classification,feature selection,reinforcement learning machine-learning brml} } @incollection{Sma2011, Author = {Smagt, Patrick van der}, Title = {Neue Entwicklungen in der Rehabilitation von Handfunktionsst\"{o}rungen: Humanrobotik}, Year = {2011}, Pages = {433-451}, Editor = {Dennis A. Novak}, Publisher = {Springer}, Booktitle = {Handfunktionsst{\"o}rungen in der Neurologie: Klinik und Rehabilitation}, Doi = {10.1007/978-3-642-17257-1_14}, Url = {http://www.springerlink.com/content/n548422365893224/}, Keywords = {brml movement} } @incollection{BayOseSma2011, Author = {Bayer, Justin and Osendorfer, Christian and Smagt, Patrick van der }, Title = {Learning sequence neighbourhood metrics}, Year = {2012}, Volume = {7552}, Pages = {531-538}, Editor = {Villa, Alessandro and Duch, Włodzisław and {\'E}rdi, P{\'e}ter and Masulli, Francesco and Palm, G{\"u}nther}, Publisher = {Springer Berlin Heidelberg}, Series = {Lecture Notes in Computer Science}, Booktitle = {Artificial Neural Networks and Machine Learning – ICANN 2012}, Doi = {10.1007/978-3-642-33269-2_67}, Keywords = {brml machine-learning} } @inproceedings{Ose2011, Author = {Osendorfer, Christian and Schl{\"u}ter, Jan and Schmidhuber, J{\"u}rgen and Smagt, Patrick van der}, Title = {Unsupervised learning of low-level audio features for music similarity estimation}, Year = {2011}, Booktitle = {Workshop on Learning Architectures, Representations, and Optimization for Speech and Visual Information Processing, ICML 2011}, Keywords = {brml machine-learning} } @incollection{RueOseSma2011, Author = {R{\"u}ckstiess, Thomas and Osendorfer, Christian and Smagt, Patrick van der}, Title = {Sequential feature selection for classification}, Year = {2011}, Volume = {7106}, Editor = {Dianhui Wang and Mark Reynolds}, Publisher = {Springer Berlin Heidelberg}, Series = {Lecture Notes in Computer Science}, Booktitle = {AI 2011: Advances in Artificial Intelligence}, Doi = {10.1007/978-3-642-25832-9_14}, Keywords = {brml machine-learning} } @inproceedings{FliMcISma2012, Author = {Nadine Fligge and Joe McIntyre and Patrick van der Smagt}, Title = {Minimum jerk for human catching movements in 3D}, Year = {2012}, Pages = {581--586}, Booktitle = {Proc. IEEE International Conference on Biomedical Robotics and Biomechatronics}, Doi = {10.1109/BioRob.2012.6290265}, Keywords = {brml movement} } @inproceedings{GieGusSma2012, Author = {Dominikus Gierlach and Agneta Gustus and Patrick van der Smagt}, Title = {Generating marker stars for 6D optical tracking}, Year = {2012}, Pages = {147--152}, Booktitle = {IEEE International Conference on Biomedical Robotics and Biomechatronics}, Doi = {10.1109/BioRob.2012.6290261}, Keywords = {brml movement} } @inproceedings{CorCorZolSicSma2012, Author = {Francesca Cordella and Francesco Di Corato and Loredana Zollo and Bruno Siciliano and Patrick van der Smagt}, Title = {Patient performace evaluation using kinect and Monte Carlo-based finger tracking}, Year = {2012}, Pages = {1967--1972}, Booktitle = {IEEE International Conference on Biomedical Robotics and Biomechatronics}, Doi = {10.1109/BioRob.2012.6290794}, Keywords = {movement brml } } @inproceedings{ninapro2012, Author = {Atzori, M. and Gijsberts, A. and Heynen, S. and Mittaz-Hager, A.-G. and Deriaz, O. and van der Smagt, P. and Castellini, C. and Caputo, B. and Müller, H.}, Title = {Building the NINAPRO Database: A Resource for the Biorobotics Community}, Year = {2012}, Pages = {1258--1265}, Booktitle = {IEEE International Conference on Biomedical Robotics and Biomechatronics}, Doi = {10.1109/BioRob.2012.6290287}, Keywords = {brml } } @article{, Author = {Leigh R. Hochberg and Daniel Bacher and Beata Jarosiewicz and Nicolas Y. Masse and John D. Simeral and Joern Vogel and Sami Haddadin and Jie Liu and Sydney S. Cash and Patrick van der Smagt and John P. Donoghue}, Title = {Reach and grasp by people with tetraplegia using a neurally controlled robotic arm}, Journal = {Nature}, Year = {2012}, Volume = {485}, Pages = {372-377}, Doi = {10.1038/nature11076}, Keywords = {movement brml BMI} } @inproceedings{Bra2012, Author = {D. J. Braun and F. Petit and S. Haddadin and P. van der Smagt and A. Albu-Schäffer and S. Vijayakumar}, Title = {Optimal Torque and Stiffness Control in Compliantly Actuated Robots}, Year = {2012}, Pages = {2801--2808}, Booktitle = {Proc. 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems}, Doi = {10.1109/IROS.2012.6385991}, Keywords = {brml movement} } @article{GusStiVisJorSma2012, Author = {Agneta Gustus and Georg Stillfried and Judith Visser and Henrik Jorntell and Patrick van der Smagt}, Title = {Human hand modelling: kinematics, dynamics, applications}, Journal = {Biological Cybernetics}, Year = {2012}, Volume = {106}, Number = {11-12}, Pages = {741-755}, Doi = {10.1007/s00422-012-0532-4}, Keywords = {brml movement} } @article{FliUrbSma2013, Author = {N. Fligge and H. Urbanek and P. van der Smagt}, Title = {Relation between object properties and EMG during reaching to grasp}, Journal = {Journal of Electromyography and Kinesiology}, Year = {2013}, Volume = {23}, Number = {2}, Pages = {402-410}, Doi = {10.1016/j.jelekin.2012.10.010}, Keywords = {brml movement} } @article{CasSma2013, Author = {Claudio Castellini and Patrick van der Smagt}, Title = {Evidence of muscle synergies during human grasping}, Journal = {Biological Cybernetics}, Year = {2013}, Volume = {107}, Number = {2}, Pages = {233-245}, Doi = {10.1007/s00422-013-0548-4}, Keywords = {brml bmi} } @article{Bra2013, Author = {David J. Braun and Florian Petit and Felix Huber and Sami Haddadin and Patrick van der Smagt and Alin Albu-Schaffer and Sethu Vijayakumar}, Title = {Robots Driven by Compliant Actuators: Optimal Control under Actuation Constraints}, Journal = {IEEE Transactions on Robotics}, Year = {2013}, Volume = {99}, Number = {5}, Pages = {1--17}, Doi = {10.1109/TRO.2013.2271099}, Keywords = {brml movement} } @incollection{, Author = {Christian Osendorfer and Justin Bayer and Sebastian Urban and Patrick van der Smagt}, Title = {Convolutional Neural Networks learn compact local image descriptors}, Year = {2013}, Volume = {8228}, Pages = {624-630}, Publisher = {Springer-Verlag}, Series = {Lecture Notes in Computer Science}, Booktitle = {Neural Information Processing}, Doi = {10.1007/978-3-642-42051-1_77}, Url = {http://arxiv.org/abs/1304.7948}, Keywords = {brml machine-learning} } @incollection{, Author = {Justin Bayer and Christian Osendorfer and Sebastian Urban and Patrick van der Smagt}, Title = {Training Neural Networks with Implicit Variance}, Year = {2013}, Volume = {8227}, Pages = {132-139}, Series = {Lecture Notes in Computer Science }, Booktitle = {Neural Information Processing}, Doi = {10.1007/978-3-642-42042-9_17}, Keywords = {brml machine-learning} } @inproceedings{, Author = {Sebastian Urban and Justin Bayer and Christian Osendorfer and Göran Wesling and Benoni B. Edin and Patrick van der Smagt}, Title = {Computing grip force and torque from finger nail images using Gaussian processes}, Year = {2013}, Pages = {4034--4039}, Booktitle = {Proc. 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)}, Doi = {10.1109/IROS.2013.6696933}, Keywords = {brml machine-learning movement} } @inproceedings{VogBaySma2013, Author = {Joern Vogel and Justin Bayer and Patrick van der Smagt}, Title = {Continuous robot control using surface electromyography of atrophic muscles}, Year = {2013}, Pages = {845--850}, Booktitle = {Proc. 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems}, Doi = {10.1109/IROS.2013.6696449}, Keywords = {brml BMI} } @incollection{VogSma2014, Author = {Jörn Vogel and Sami Haddadin and John D Simeral and Sergey D Stavisky and Daniel Bacher and Leigh R Hochberg and John P Donoghue and Patrick van der Smagt }, Title = {Continuous Control of the DLR Light-weight Robot III by a human with tetraplegia using the BrainGate2 Neural Interface System}, Year = {2014}, Volume = {79}, Pages = {125-136}, Editor = {Oussama Khatib and Vijay Kumar and Gaurav Sukhatme}, Publisher = {Springer Berlin Heidelberg}, Series = {Springer Tracts in Advanced Robotics}, Booktitle = {Experimental Robotics}, Doi = {10.1007/978-3-642-28572-1_9}, Keywords = {brml bmi} } @incollection{LakRueBayVogSma2013, Author = {Dominic Lakatos and Daniel Rüschen and Justin Bayer and Jörn Vogel and Patrick van der Smagt}, Title = {Identification of Human Limb Stiffness in 5 DoF and Estimation via EMG}, Year = {2013}, Volume = {88}, Pages = {89-99}, Editor = {Desai, Jaydev P. and Dudek, Gregory and Khatib, Oussama and Kumar, Vijay}, Publisher = {Springer International Publishing}, Series = {Springer Tracts in Advanced Robotics}, Isbn = {978-3-319-00064-0}, Booktitle = {Experimental Robotics}, Doi = {10.1007/978-3-319-00065-7_7}, Keywords = {brml movement bmi} } @article{HopMciSma2013, Author = {Hannes Höppner and Joseph McIntyre and Patrick van der Smagt}, Title = {Task Dependency of Grip Stiffness---A Study of Human Grip Force and Grip Stiffness Dependency during Two Different Tasks with Same Grip Forces}, Journal = {PLOS ONE}, Year = {2013}, Volume = {8}, Number = {12}, Pages = {e80889}, Doi = {10.1371/journal.pone.0080889}, Url = {http://blog.brml.org/new-paper-on-grip-stiffness/}, Keywords = {brml movement} } @incollection{StiSma2014, Author = {Georg Stillfried and Ulrich Hillenbrand and Marcus Settles and Patrick van der Smagt}, Title = {MRI-based skeletal hand movement model}, Year = {2014}, Volume = {95}, Pages = {49-75}, Editor = {Ravi Balasubramanian and Veronica J. Santos}, Publisher = {Springer-Verlag}, Series = {Springer Tracts in Advanced Robotics}, Isbn = {978-3-319-03017-3}, Booktitle = {The Human Hand as an Inspiration for Robot Hand Development}, Doi = {10.1007/978-3-319-03017-3_3}, Url = {blog.brml.org/human-hand-biomechanics}, Keywords = {brml movement} } @inproceedings{Sma1996, Author = {Smagt, Patrick van der}, Title = {A robot arm is neurally controlled using monocular feedback}, Year = {1996}, Pages = {9/1--9/3}, Publisher = {IEEE}, Booktitle = {Self Learning Robots, IEE Colloquium on}, Doi = {10.1049/ic:19960151}, Keywords = {brml} } @inproceedings{HoeWieSma2014, Author = {Hannes Höppner and Wolfgang Wiedmeyer and Patrick van der Smagt}, Title = {A new biarticular joint mechanism to extend stiffness ranges}, Year = {2014}, Booktitle = {Robotics and Automation (ICRA), 2014 IEEE International Conference on}, Doi = {10.1109/ICRA.2014.6907349}, Keywords = {brml movement} } @inproceedings{CheSma2014, Author = {Nutan Chen and Sebastian Urban and Christian Osendorfer and Justin Bayer and Patrick van der Smagt}, Title = {Estimating finger grip force from an image of the hand using Convolutional Neural Networks and Gaussian Processes}, Year = {2014}, Booktitle = {Robotics and Automation (ICRA), 2014 IEEE International Conference on}, Doi = {10.1109/ICRA.2014.6907310}, Keywords = {brml machine-learning movement} } @incollection{OseSoySma2014, Author = {Christian Osendorfer and Hubert Soyer and Patrick van der Smagt}, Title = {Image Super-Resolution with Fast Approximate Convolutional Sparse Coding}, Year = {2014}, Volume = {8836}, Note = {(ICONIP 2014 Best Paper Award)}, Publisher = {Springer International Publishing}, Series = {Lecture Notes in Computer Science}, Booktitle = {Neural Information Processing}, Doi = {10.1007/978-3-319-12643-2_31}, Keywords = {brml machine-learning} } @inproceedings{Bay2014, Author = {Justin Bayer and Christian Osendorfer and Daniela Korhammer and Nutan Chen and Sebastian Urban and Patrick van der Smagt}, Title = {On Fast Dropout and its Applicability to Recurrent Networks}, Year = {2014}, Booktitle = {Proceedings of the International Conference on Learning Representations}, Url = {http://arxiv.org/abs/1311.0701}, Keywords = {brml machine-learning} } @inproceedings{Hornung2014, Author = {Hornung, Rachel and Urbanek, Holger and Klodmann, Julian and Osendorfer, Christian and van der Smagt, Patrick}, Title = {Model-free robot anomaly detection}, Year = {2014}, Booktitle = {Proc. IEEE/RSJ International Conference on Robotics and Systems (IROS)}, Doi = {10.1109/IROS.2014.6943078}, Keywords = {brml machine-learning} } @inproceedings{Bayer2014, Author = {Justin Bayer and Christian Osendorfer}, Title = {Learning Stochastic Recurrent Networks}, Year = {2014}, Booktitle = {Workshop on Advances in Variational Inference, Neural Information Processing Systems 2014}, Url = {http://arxiv.org/abs/1411.7610}, Keywords = {brml machine-learning} } @article{VogSma2015, Author = {J. Vogel and S. Haddadin and B. Jarosiewicz and J. D. Simeral and D. Bacher and M. M. Hochberg and J. P. Donoghue and P. van der Smagt}, Title = {An assistive decision-and-control architecture for force-sensitive hand--arm systems driven by human--machine interfaces}, Journal = {The International Journal of Robotics Research (IJRR)}, Year = {2015}, Doi = {10.1177/0278364914561535}, Keywords = {brml BMI} } @inproceedings{Flownet2015, Author = {P. Fischer and A. Dosovitskiy and E Ilg and P Haeusser and C Hazirbas and V. Golkov and P. van der Smagt and D. Cremers and T. Brox}, Title = {FlowNet: Learning Optical Flow with Convolutional Networks}, Year = {2015}, Booktitle = {Proc. ICCV}, Url = {http://arxiv.org/abs/1504.06852}, Keywords = {brml machine-learning} } @inproceedings{UrbSma2015, Author = {Sebastian Urban and Patrick van der Smagt}, Title = {A Neural Transfer Function for a Smooth and Differentiable Transition Between Additive and Multiplicative Interactions}, Year = {2015}, Booktitle = {arXiv}, Url = {http://arxiv.org/abs/1503.05724}, Keywords = {brml machine-learning} } @inproceedings{HoeGreSma2015, Author = {Hannes H{\"o}ppner and Markus Grebenstein and Patrick van der Smagt}, Title = {Two-dimensional orthoglide mechanism for revealing areflexive human arm mechanical properties}, Year = {2015}, Booktitle = {Proc. IEEE International Conference on Intelligent Robots and Systems (IROS 2015)}, Keywords = {brml movement} } @inproceedings{ChenSma2015, Author = {Nutan Chen and Sebastian Urban and Justin Bayer and Patrick van der Smagt}, Title = {Measuring Fingertip Forces from Camera Images for Random Finger Poses}, Year = {2015}, Booktitle = {Proc. IEEE International Conference on Robotics and System (IROS)}, Keywords = {brml movement} } @inproceedings{MilLudSmaLor2015, Author = {Zoltán A. Milacskí and Marvin Ludersdorfer and Patrick van der Smagt and Andräs Lörincz}, Title = {Robust Detection of Anomalies via Sparse Methods}, Year = {2015}, Booktitle = {Proc. ICONIP}, Keywords = {brml machine-learning robotics} } @article{UrbLudSma2015, Author = {Sebastian Urban and Marvin Ludersdorfer and Patrick van der Smagt}, Title = {Sensor Calibration and Hysteresis Compensation with Heteroscedastic Gaussian Processes}, Journal = {IEEE Sensors}, Year = {2015}, Volume = {15}, Number = {11}, Pages = {6498--6506}, Month = {November}, Doi = {10.1109/JSEN.2015.2455814}, Keywords = {brml machine-learning robotics} } @inproceedings{BayKarKorSma2015, Author = {Justin Bayer and Maximilian Karl and Daniela Korhammer and Patrick van der Smagt}, Title = {Fast Adaptive Weight Noise}, Year = {2015}, Booktitle = {arXiv}, Url = {http://arxiv.org/abs/1507.05331}, Keywords = {brml machine-learning} } @inproceedings{CheBaySurSma2015, Author = {Nutan Chen and Justin Bayer and Sebastian Urban and Patrick van der Smagt}, Title = {Efficient movement representation by embedding Dynamic Movement Primitives in Deep Autoencoders}, Year = {2015}, Booktitle = {Proc. 2015 IEEE-RAS International Conference on Humanoid Robots}, Keywords = {brml machine-learning movement} } @inproceedings{SolBayLudSma2016, Author = {Maximilian S{\"o}lch and Justin Bayer and Marvin Ludersdorfer and Patrick van der Smagt}, Title = {Variational Inference for On-line Anomaly Detection in High-Dimensional Time Series}, Year = {2016}, Booktitle = {International Conference on Learning Representations (ICLR)}, Url = {http://arxiv.org/abs/1602.07109}, Keywords = {brml movement machine-learning} } @article{UrbSma2016, Author = {Holger Urbanek and Patrick van der Smagt }, Title = {{iEMG}: Imaging Electromyography}, Journal = {Journal of Electromyography and Kinesiology}, Year = {2016}, Volume = {27}, Pages = {1--9}, Doi = {10.1016/j.jelekin.2016.01.001}, Keywords = {brml BMI } } @inproceedings{KoeSmaUrb2016, Author = {Wiebke Koepp and Patrick van der Smagt and Sebastian Urban}, Title = {A Differentiable Transition Between Additive and Multiplicative Neurons}, Year = {2016}, Booktitle = {International Conference on Learning Representations (ICLR)}, Url = {http://arxiv.org/abs/1604.03736}, Keywords = {brml machine-learning} } @article{KarSoeBaySma, Author = {Maximilian Karl and Maximilian Soelch and Justin Bayer and Patrick van der Smagt}, Title = {Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data}, Journal = {arxiv}, Year = {2016}, Url = {http://arxiv.org/abs/1605.06432}, Keywords = {brml machine-learning movement DVBF} } @journal{KarBaySma2015, Author = {Maximilian Karl and Justin Bayer and Patrick van der Smagt}, Title = {Efficient Empowerment}, Journal = {arXiv}, Year = {2015}, Url = {http://arxiv.org/abs/1509.08455}, Keywords = {brml machine-learning} } @inproceedings{Hoof2016, Author = {Herke van Hoof and Nutan Chen and Maximilian Karl and Patrick van der Smagt and Jan Peters}, Title = {Stable Reinforcement Learning with Autoencoders for Tactile and Visual Data}, Year = {2016}, Booktitle = {Proc. IEEE International Conference on Intelligent Robots and Systems (IROS)}, Keywords = {brml, movement, machine-learning} } @article{GusSma2016, Author = {Agneta Gustus and Patrick van der Smagt}, Title = {Evaluation of joint type modelling in the human hand}, Journal = {Journal of Biomechanics}, Year = {2016}, Volume = {49}, Number = {13}, Pages = {3097–3100}, Doi = {10.1016/j.jbiomech.2016.07.018}, Keywords = {brml} } @inproceedings{CheKarsma2016, Author = {Nutan Chen and Maximilian Karl and Patrick van der Smagt}, Title = {Dynamic Movement Primitives in Latent Space of Time-Dependent Variational Autoencoders}, Year = {2016}, Booktitle = {Proc. 16th IEEE-RAS International Conference on Humanoid Robots}, Keywords = {brml machine-learning dvbf movement} } @article{, Author = {Christopher Wolf and Maximilian Karl and Patrick van der Smagt}, Title = {Variational Inference with Hamiltonian Monte Carlo}, Journal = {arXiv}, Year = {2016}, Url = {https://arxiv.org/abs/1609.08203}, Keywords = {brml, machine-learning} } @article{KayJenSma2017, Author = {Baris Kayalibay and Grady Jensen and Patrick van der Smagt}, Title = {CNN-based Segmentation of Medical Imaging Data}, Journal = {arXiv}, Year = {2017}, Url = {https://arxiv.org/abs/1701.03056}, Keywords = {brml machine-learning} } @inproceedings{KarSoeBaySma2017, Author = {Maximilian Karl and Maximilian Soelch and Justin Bayer and Patrick van der Smagt}, Title = {Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Data}, Year = {2017}, Booktitle = {International Conference on Learning Representations (ICLR)}, Url = {https://openreview.net/pdf?id=HyTqHL5xg}, Keywords = {brml machine-learning} } @inproceedings{ZhaHaiSma2017, Author = {Rui Zhao and Ali Haider and Patrick van der Smagt}, Title = {Two-Stream RNN/CNN for Action Recognition in 3D Videos}, Year = {2017}, Booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017)}, Keywords = {brml machine-learning movement} } @article{Sta2017, Author = {Benedikt Staffler and Manuel Berning and Kevin M Boergens and Anjali Gour and Patrick van der Smagt and Moritz Helmstaedter}, Title = {SynEM, automated synapse detection for connectomics}, Journal = {eLife}, Year = {2017}, Volume = {2017;6:e26414}, Doi = {10.7554/eLife.26414}, Url = {https://elifesciences.org/articles/26414}, Keywords = {brml machine-learning} } @article{UrbBasSma2017, Author = {Sebastian Urban and Marcus Basalla and Patrick van der Smagt}, Title = {Gaussian Process Neurons Learn Stochastic Activation Functions}, Journal = {arXiv}, Year = {2017}, Url = {https://arxiv.org/abs/1711.11059}, Keywords = {brml machine-learning} } @article{UrbSma2017, Author = {Sebastian Urban and Patrick van der Smagt}, Title = {Automatic Differentiation for Tensor Algebras}, Journal = {arXiv}, Year = {2017}, Url = {https://arxiv.org/abs/1711.01348}, Keywords = {brml machine-learning} } @article{KueSmaall, Author = {Markus K{\"u}hne and Johannes Potzy and R Garcia-Rochin and Patrick van der Smagt and Angelika Peer}, Title = {Design and Evaluation of a Haptic Interface With Octopod Kinematics}, Journal = {IEEE/ASME Transactions on Mechatronics}, Year = {2017}, Volume = {22}, Number = {5}, Pages = {2091-2101}, Doi = {10.1109/TMECH.2017.2742581}, Keywords = {brml} } @inproceedings{GanSma2017, Author = {Joern Vogel and N Takemura and Hannes H{\"o}ppner and Patrick van der Smagt and Gowrishankar Ganesh}, Title = {Hitting the sweet spot: Automatic optimization of energy transfer during tool-held hits}, Year = {2017}, Pages = {1549-1556 }, Booktitle = {IEEE International Conference on Robotics and Automation (ICRA)}, Doi = {10.1109/ICRA.2017.7989185}, Keywords = {movement brml} } @COMMENT{Bibtex file generated on 2018-10-9 with typo3 si_bibtex plugin. Data from https://brml.org/publications/publications/ }