检索结果-内蒙古大学图书馆

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Aymeric Orhan Dorian Verdel Olivier Bruneau Franck Geffard Bastien Berret CEA List Université Paris-Saclay Palaiseau France Department of Bioengineering Human Robotics Group Imperial College of Science Technology and Medicine London United-Kingdom LURPA Mechanical Engineering Department ENS Paris-Saclay Université Paris-Saclay Gif-sur-Yvette France CIAMS Sport Sciences Department Univcrsité Paris-Saclay Orsay France CIAMS Université d'Orléans Orléans France

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Accurately predicting human movement trajectories is of critical interest in multiple fields, including human-exoskeleton interaction. In general, such predictions can be obtained from model-based approaches (e.g., optimal control theory) or from data-driven approaches (e.g., learning from human demonstrations). Data-driven methods generally require numerous demonstrations but avoid the computational burden of model-based methods. In this paper, we introduce a hybrid method mixing the strengths of these two approaches to enable the prediction of human trajectories in a receding-horizon fashion when the number of actual demonstrations is very limited. First, we propose to use the stochastic optimal feedforward-feedback control framework to generate a large set of humanlike trajectories, including their variability. Second, we used the probabilistic movement primitives (ProMPs) frame-work to learn the distribution of these synthetic trajectories and make online predictions about the upcoming human trajectories from the observation of past movement data. Here, we evaluated our hybrid method on an existing data set composed of arm reaching movements in a parasagittal plane. Overall, our method proves to be advantageous when generalization is needed and demonstrations are lacking, such as in novel targets scenarios. The introduced method shows promise to efficiently predict realistic human trajectories on a given time horizon, even when limited or no human demonstration is available for the task at hand.

关键词： Computational modeling Optimal control Stochastic processes Training data Predictive models Motors Cost function Real-time systems Trajectory Robots

来源：评论

学校读者我要写书评

暂无评论

2022 Roadmap on Neuromorphic Computing and Engineering

arXiv

引用

arXiv 2021年

作者： Christensen, Dennis Valbjørn Dittmann, Regina Linares-Barranco, Bernabé Sebastian, Abu Le Gallo, Manuel Redaelli, Andrea Slesazeck, Stefan Mikolajick, Thomas Spiga, Sabina Menzel, Stephan Valov, Ilia Milano, Gianluca Ricciardi, Carlo Liang, Shi-Jun Miao, Feng Lanza, Mario Quill, Tyler J. Keene, Scott T. Salleo, Alberto Grollier, Julie Marković, Danijela Mizrahi, Alice Yao, Peng Yang, J. Joshua Indiveri, Giacomo Strachan, John Paul Datta, Suman Vianello, Elisa Valentian, Alexandre Feldmann, Johannes Li, Xuan Pernice, Wolfram H.P. Bhaskaran, Harish Furber, Steve Neftci, Emre Scherr, Franz Maass, Wolfgang Ramaswamy, Srikanth Tapson, Jonathan Panda, Priyadarshini Kim, Youngeun Tanaka, Gouhei Thorpe, Simon Bartolozzi, Chiara Cleland, Thomas A. Posch, Christoph Liu, Shih-Chii Panuccio, Gabriella Mahmud, Mufti Mazumder, Arnab Neelim Hosseini, Morteza Mohsenin, Tinoosh Donati, Elisa Tolu, Silvia Galeazzi, Roberto Christensen, Martin Ejsing Holm, Sune Ielmini, Daniele Pryds, N. Department of Energy Conversion and Storage Technical University of Denmark Kgs. LyngbyDK-2800 Denmark Peter Gruenberg Institute 7 Forschungszentrum Juelich GmbH Juelich52425 Germany JARA-FIT RWTH Aachen University Aachen52056 Germany CSIC Universidad de Sevilla Seville41092 Spain IBM Research Zurich Switzerland STMicroelectronics Agrate Italy Dresden01187 Germany Institute of Semiconductors and Microsystems TU Dresden Dresden Germany CNR-IMM Unit of Agrate Brianza via C. Olivetti 2 MB Agrate Brianza Italy Juelich Germany Torino Italy Department of Applied Science and Technology Politecnico di Torino Torino Italy National Laboratory of Solid State Microstructures School of Physics Collaborative Innovation Center of Advanced Microstructures Nanjing University Nanjing China Thuwal23955-6900 Saudi Arabia Department of Materials Science and Engineering Stanford University StanfordCA94305 United States Department of Engineering University of Cambridge CambridgeCB2 1PZ United Kingdom Unité Mixte de Physique CNRS Thales Université Paris-Saclay Palaiseau91767 France Electrical and Computer Engineering Department University of Southern California Los AngelesCA United States Institute of Neuroinformatics University of Zurich ETH Zurich Switzerland Hewlett Packard Laboratories Hewlett Packard Enterprise San JoseCA United States Department of Electrical Engineering University of Notre Dame Notre DameIN United States CEA LETI Université Grenoble Alpes Grenoble France CEA LIST Université Grenoble Alpes Grenoble France Department of Materials University of Oxford Parks Road OxfordOX1 3PH United Kingdom Institute of Physics University of Münster Heisenbergstr. 11 Heisenbergstr Münster48149 Germany Center for Soft Nanoscience University of Münster Münster48149 Germany The University of Manchester United Kingdom Department of Cognitive Sciences University of California Irvine IrvineCA United States Institute of Theoretica

Modern computation based on the von Neumann architecture is today a mature cutting-edge science. In the Von Neumann architecture, processing and memory units are implemented as separate blocks interchanging data intensively and continuously. This data transfer is responsible for a large part of the power consumption. The next generation computer technology is expected to solve problems at the exascale with 1018 calculations each second. Even though these future computers will be incredibly powerful, if they are based on von Neumann type architectures, they will consume between 20 and 30 megawatts of power and will not have intrinsic physically built-in capabilities to learn or deal with complex data as our brain does. These needs can be addressed by neuromorphic computing systems which are inspired by the biological concepts of the human brain. This new generation of computers has the potential to be used for the storage and processing of large amounts of digital information with much lower power consumption than conventional processors. Among their potential future applications, an important niche is moving the control from data centers to edge devices. The aim of this Roadmap is to present a snapshot of the present state of neuromorphic technology and provide an opinion on the challenges and opportunities that the future holds in the major areas of neuromorphic technology, namely materials, devices, neuromorphic circuits, neuromorphic algorithms, applications, and ethics. The Roadmap is a collection of perspectives where leading researchers in the neuromorphic community provide their own view about the current state and the future challenges for each research area. We hope that this Roadmap will be a useful resource by providing a concise yet comprehensive introduction to readers outside this field, for those who are just entering the field, as well as providing future perspectives for those who are well established in the neuromorphic computing community. © 2021,

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Robot Assistance Selection for Large Object Manipulation with a Human

Robot Assistance Selection for Large Object Manipulation wit...

引用

IEEE International Conference on Systems, Man, and Cybernetics

作者： Julie Dumora Franck Geffard Catherine Bidard Nikos A. Aspragathos Philippe Fraisse CEA LIST Interactive Robotics Laboratory Gif-sur-Yvette France Mechanical Engineering and Aeronautics Department University of Patras Greece LIRMM University of Montpellier 2/CNRS France

ISBN: (纸本)9781479906505

In this paper, we propose a method that allows a human to perform complex manipulation tasks jointly with a robotic partner. To that end, the robot has a library of assistances that it can provide for helping the human partner during a priori unknown collaborative tasks. According to the haptic cues naturally transmitted by the human partner, the robot selects on-line the suitable assistance for the current intended collaborative motion. Based on the naive bayes classifier and the Matthew Correlation Coefficient, the parameters of the decisionmaking are automatically tuned. An experiment on a real arm manipulator is provided to validate the proposed approach.

关键词： large object comanipulation human intent detection assistive control Object Manipulation Bayesian classifier Human Robot decision making Libraries Religious Missions AUTOMATIC

来源：评论

学校读者我要写书评

暂无评论

Some Remarks on Smith predictor-based control with distance feedback for a 3-DOF haptic system with distributed delays

Some Remarks on Smith predictor-based control with distance ...

引用

11th Workshop on Time-Delay Systems, TDS 2013

作者： Liacu, Bogdan MorǍrescu, Irinel-Constantin Niculescu, Silviu-Iulian Andriot, Claude Dumur, Didier Colledani, Frédéric Boucher, Patrick CNRS-SUPELEC 3 Rue Joliot Curie 91192 Gif-sur-Yvette France Université de Loraine CRAN UMR-CNRS 7039 2 Avenue de la forêt de Haye 54516 Vandoeuvre-lès-Nancy Cedex France CEA LIST Interactive Robotics Laboratory Fontenay aux Roses F-92265 France SUPELEC E3S Control Department 3 Rue Joliot Curie 91192 Gif sur Yvette cedex France

ISBN: (纸本)9783902823267

This paper focuses on the construction of a Smith predictor for network-based haptic systems. Roughly speaking, the idea is to use a predictor just on the haptic side in order to compensate the viscosity effect and to provide an accurate feeling in the case of contacts. A new approach is presented by using the available information on the distance from the virtual reality simulator and introducing it in the predictor in order to maintain the similarity between the "real" and the "predicted model". In order to validate the approach, experimental results are presented for constant and random varying delays (normal distributed and gamma with gap distributed), for a simple virtual environment and for a virtual box. © 2013 IFAC.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A frequency-domain approach for flexible-joint robot modeling and identification

A frequency-domain approach for flexible-joint robot modelin...

引用

Universite Libre de Bruxelles

作者： Makarov, Maria Grossard, Mathieu Rodríguez-Ayerbe, Pedro Dumur, Didier CEA LIST Interactive Robotics Laboratory Fontenay aux Roses F-92265 France Control Department Gif sur Yvette Cedex F-91192 France

ISBN: (纸本)9783902823069

This paper proposes a control-oriented modeling and identification framework for flexible-joint robot arms using motor-side measurements only. From the perspective of model-based control strategies including an inner feedback linearization loop, the proposed method allows an explicit treatment of the vibrational behavior induced by the flexibilities. A theoretical model of the partially decoupled system is derived and a frequency-domain identification procedure allowing an estimation of the flexible parameters is detailed. The obtained description of the system is experimentally validated on the cea lightweight robot arm ASSIST. © 2012 IFAC.

关键词： Flexible manipulators

来源：评论

学校读者我要写书评

暂无评论

High dexterity docking of an UUV by fast determination of the Area Manipulability Measure of the ARM using ANN

High dexterity docking of an UUV by fast determination of th...

引用

10th IFAC Symposium on Robot Control, SYROCO 2012

作者： Sotiropoulos, Panagiotis Aspragkathos, Nikolaos Geffard, Franck Mechanical Engineering and Aeronautics Department University of Patras Patras 26500 Greece CEA LIST Interactive Robotics Laboratory Fontenay-aux-Roses F-92265 France

ISBN: (纸本)9783902823113

The scope of this paper is to contribute towards the advancements in the autonomy and in the optimal planning of the intervention mission of an Unmanned Underwater Vehicle (UUV). Particularly, an approach is proposed for the automatic and fast determination of a high dexterity docking location. A feed forward back propagation Artificial Neural Network (ANN) is trained to calculate directly a dexterity index for the manipulator of the UUV defined in the task area and called Area Manipulability Measure (AMM). The main advantage of this procedure is the very fast determination of the AMM using the ANN compared with the very long analytical calculation of the AMM, which is used only for the training. A common intervention mission is presented and a Genetic Algorithm (GA) is implemented to search for the optimum docking pose taking into consideration the Area Manipulability Measure derived by the ANN, the distance between the current pose of the vehicle and the docking target, as well as the geometric restrictions imposed by the layout of the underwater installation. © 2012 IFAC.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Frequency-Domain Approach for Flexible-Joint Robot Modeling and Identification

引用

IFAC Proceedings Volumes 2012年第16期45卷 583-588页

作者： Maria Makarov Mathieu Grossard Pedro Rodríguez-Ayerbe Didier Dumur CEA LIST Interactive Robotics Laboratory Fontenay aux Roses F-92265 France SUPELEC Systems Sciences (E3S) Control Department Gif sur Yvette Cedex F-91192 France

关键词： robotic manipulators flexible arms feedback linearization control-oriented models

来源：评论

学校读者我要写书评

暂无评论

High Dexterity Docking of an UUV by Fast Determination of the Area Manipulability Measure of the Arm Using ANN

引用

IFAC Proceedings Volumes 2012年第22期45卷 198-203页

作者： Panagiotis Sotiropoulos Nikolaos Aspragkathos Franck Geffard Mechanical Engineering and Aeronautics Department University of Patras Patras 26500 Greece (Tel: +30 ***) Mechanical Engineering and Aeronautics Department University of Patras Patras 26500 Greece CEA LIST Interactive Robotics Laboratory Fontenay-aux-Roses F-92265 France

关键词： Autonomous mobile robots Neural Networks Manipulation Genetic algorithms Inverse kinematic problem

来源：评论

学校读者我要写书评

暂无评论

Active damping strategy for robust control of a flexible-joint lightweight robot

Active damping strategy for robust control of a flexible-joi...

引用

IEEE Conference on Control Technology and Applications (CCTA)

作者： Maria Makarov Mathieu Grossard Pedro Rodríguez-Ayerbe Didier Dumur CEA LIST Interactive Robotics Laboratory France and SUPELEC Systems Sciences (E3S) Fonte-nay aux Roses France CEA LIST Interactive Robotics Laboratory France SUPELEC Systems Sciences (E3S) Control Department F-91192 Gif sur Yvette Cedex France SUPELEC Systems Sciences (E3S) Control Department France

ISBN: (纸本)9781467345033

This paper proposes a practical approach for damping control of flexible-joint manipulators. High-bandwidth tracking objectives are achieved together with robustness and effective disturbance rejection using motor measurements only. An inner decoupling loop based on the rigid-body approximation is first applied to minimize the effects of robot nonlinearities. The consequences of this approximate linearization are then explicitly taken into account in the control design and analysis, and a simple decentralized linear control strategy is proposed, combining low-authority collocated damping controllers with a high-authority motion loop based on the Generalized Predictive Control. The described approach is experimentally validated on the lightweight and back-drivable cea ASSIST robot arm.

关键词： Damping Robots Joints Uncertainty Robustness Control design DC motors

来源：评论

学校读者我要写书评

暂无评论

PD control with gain-scheduling depending on the distance for a 3-dof network based haptic system

PD control with gain-scheduling depending on the distance fo...

引用

IEEE Conference on Control Technology and Applications (CCTA)

作者： Bogdan Liacu Claude Andriot Didier Dumur Silviu-Iulian Niculescu Frédéric Colledani Patrick Boucher SUPELEC Gif sur Yvette Cedex and CEA LIST Interactive Robotics Laboratory Fontenay-aux-Roses France Fontenay aux Roses CEA LIST Interactive Robotics Laboratory France SUPELEC E3S Control Department Gif sur Yvette Cedex France Laboratoire des Signaux et Systemes (LSS) CNRS-SUPELEC Gif-sur-Yvette Cedex France

ISBN: (纸本)9781467345033

This paper presents a Proportional Derivative (PD) controller with gain-scheduling depending on the distance for haptic interfaces and virtual environments subject to communication delays. It is well known that the presence of delays deteriorates the overall system performance. More precisely, depending on the proposed architecture as, for example, bilateral position-position coupling, time-delays introduce a feeling of viscosity in free motion and reduce the sense of stiffness in the case of hard contacts. Even in the presence of time-delays, the controller gains can be tuned in order to guarantee the desired behavior and performances for one case (free or restricted motion) with the price of the completely loss of the other case performances and behavior. To overcome this drawback, a gain-scheduling controller is designed, able to guarantee the desired behavior and performances for free and restricted motion. The experimental results obtained on a three-degree of freedom real-time experimental platform enforce the theoretical developments.

关键词： Haptic interfaces Switches Stability analysis PD control Virtual environments Delay Viscosity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：