检索结果-内蒙古大学图书馆

Annual Conference on Neural Information Processing Systems

作者： Sergey Levine Vladlen Koltun Stanford University Stanford University and Adobe Research

ISBN: (纸本)9781632660244

In order to learn effective control policies for dynamical systems, policy search methods must be able to discover successful executions of the desired task. While random exploration can work well in simple domains, complex and high-dimensional tasks present a serious challenge, particularly when combined with high-dimensional policies that make parameter-space exploration infeasible. We present a method that uses trajectory optimization as a powerful exploration strategy that guides the policy search. A variational decomposition of a maximum likelihood policy objective allows us to use standard trajectory optimization algorithms such as differential dynamic programming, interleaved with standard supervised learning for the policy itself. We demonstrate that the resulting algorithm can outperform prior methods on two challenging locomotion tasks.

关键词： trajectory optimization Policies exploration strategy dynamic programming optimization algorithms standard trajectory

来源：评论

学校读者我要写书评

暂无评论

Street-Specific Handover optimization for Vehicular Terminals in Future Cellular Networks

Street-Specific Handover Optimization for Vehicular Terminal...

引用

IEEE Vehicular Technology Conference

作者： Zhe Ren Peter Fertl Qi Liao Federico Penna Slawomir Stańczak BMW Forschung und Technik Hanauerstrasse 46 Munich Germany Fraunhofer Institute for Telecommunications Heinrich Hertz Institute Einsteinufer 37 Berlin

ISBN: (纸本)9781467363365

Modern vehicles will have strong requirements with regard to seamless mobility support in future cellular systems, in order to enable advanced cooperative driver assistance and infotainment systems that guarantee traffic safety and efficiency. In this work, we introduce street-specific handover parameters for vehicular terminals. In particular, we propose an adaptive optimization algorithm that exploits vehicle context information in order to tune the handover parameters. Simulation results confirm that the proposed concept has the potential to improve handover performance significantly.

关键词： assistance infotainment safety safety Cellular networks cellular system optimization algorithms Consumer safety vehicle Device Terminal adaptive optimization Traffic safety

来源：评论

学校读者我要写书评

暂无评论

POPULATION MODEL-BASED optimization WITH SEQUENTIAL MONTE CARLO 13

POPULATION MODEL-BASED OPTIMIZATION WITH SEQUENTIAL MONTE CA...

引用

Simulation Conference

作者： Xi Chen Enlu Zhou University of Illinois at Urbana-Champaign Urbana IL

ISBN: (纸本)9781479920778

Model-based optimization algorithms are effective for solving optimization problems with little structure. The algorithms iteratively find candidate solutions by generating samples from a parameterized probabilistic model on the solution space. In order to better capture the multi-modality of the objective function than the traditional model-based methods which use only a single model, we propose a framework of using a population of models with an adaptive mechanism to propagate the population over iterations. The adaptive mechanism is derived from estimating the optimal parameter of the probabilistic model in a Bayesian manner, and thus provides a proper way to determine the diversity in the population of the models. We develop two practical algorithms under this framework by applying sequential Monte Carlo methods, provide some theoretical justification on the convergence of the proposed methods, and carry out numerical experiments to illustrate their performance.

关键词： population model Probabilistic Model Solution space multimodality Frameworks optimization algorithms Monte Carlo technique Sequential Objective function Hypoderma optimal parameter

来源：评论

学校读者我要写书评

暂无评论

NeuroEvolutionary Meta-optimization

NeuroEvolutionary Meta-Optimization

引用

International Joint Conference on Neural Networks

作者： Andreas Lang Kenneth O. Stanley Department of Computer Science of the University of Geneva Department of Electrical Engineering and Computer Science of the University of Central Florida

ISBN: (纸本)9781467361279

This paper introduces a meta-optimization algorithm called NeuroEvolutionary Meta-optimization (NEMO) that evolves an algorithm targeted at optimizing only within a specific problem class. More specifically, a form of neural network is evolved that acts as the controller of a kind of optimization algorithm that can potentially exploit problem class-specific structure. NEMO is demonstrated on several benchmark problems that confirm its ability to succeed on problems within the class on which it is trained. The key implication is that it is indeed possible to evolve this kind of meta-optimizer with a neural network-like structure, opening up a promising research direction in automatically evolving such class-specific optimizers.

关键词： NEMO optimizing only several benchmark problems IKBKG gene Benchmark testing Neural network optimization algorithms Controllers

来源：评论

学校读者我要写书评

暂无评论

SIMPLE ITERATION-OPTIMAL DISTRIBUTED optimization

SIMPLE ITERATION-OPTIMAL DISTRIBUTED OPTIMIZATION

引用

European Signal Processing Conference

作者： Konstantinos I. Tsianos Michael G. Rabbat Department of Electrical and Computer Engineering McGill University Montréal Québec Canada

ISBN: (纸本)9781479936878

We propose a consensus-based distributed optimization algorithm for minimizing separable convex objectives. Each node only knows one component of the objective function, and so the nodes must coordinate in order to find a global minimizer. The proposed algorithm has an error rate which is no more than (1/) after T iterations, matching the best possible rate. To achieve this, the algorithm requires multiple rounds of consensus per iteration, where the number of consensus rounds depends on the structure of the underlying communication topology through the spectral gap. Consequently, the amount of computation required by the proposed approach is less that of distributed optimization methods in the literature, while the total amount of communication is not increased.

关键词： Distributed optimization consensus optimization method optimization algorithms iterative methods Error analysis LITAF gene optimization methods Communication Research Objective function Rounding off

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of Energy optimization Algorithm for Mobile Robots in Three-dimension Motion Using Predictive Control

Experimental Evaluation of Energy Optimization Algorithm for...

引用

Mediterranean Conference on Control & Automation

作者： Mostafa I. Yacoub D. S. Necsulescu Jurek Z. Sasiadek University of Ottawa Carleton University

ISBN: (纸本)9781479909964

Torque saturation of DC motors of the wheels of mobile robots is one of the main difficulties during climbing hills. A two-DC motor-driven wheels mobile robot is used in the present work to attempt crossing a ditch-like hindrance using predictive control. The proposed predictive control algorithm is compared with the PID control and the open-loop control. Experimental examination of energy optimization algorithm for mobile robots is presented. The experimental results showed a good agreement with the simulation results confirming the capability of the predictive control to avoid torque saturation and indicating a noticeable reduction in the energy consumption. Additionally, a theoretical parametric study of the predictive control is presented. The effects of the road slope and the prediction horizon length on the consumed energy are evaluated. The analytical study showed that the energy consumption is reduced by increasing the prediction horizon until it reaches a limit at which no more energy reduction is obtained. This limit is proportional to the width of the ditch in front of the mobile robot.

关键词： Mobile robots Predictive control energy consumption Simulation results optimization algorithms DC motors Wheels Energy conservation ditch

来源：评论

学校读者我要写书评

暂无评论

A rapid path planning adaptive optimization algorithm based on fuzzy neural network for multi-robot systems

A rapid path planning adaptive optimization algorithm based ...

引用

International Conference on Cyberspace Technology (CCT 2013)

作者： Huan Zhang Zhiguo Shi Xiancui Wei School of Computer and Communication Engineering University of Sci.&Tech. Beijing 100083 China

ISBN: (纸本)9781632660015

A rapid path planning adaptive optimization algorithm based on fuzzy neural network is proposed for mobile robot in a static unknown environment. In order to solve the limitations of the subjective experience in the fuzzy control and design problems of path planning, conventional neural network is given fuzzy input signals and fuzzy weights by using the membership function and the error cost function of fuzzy control theory. Neural network is constructed from fuzzy rules to accelerate the convergence of FNN, so that the collision-free motion is achieved by combining with the formation control method for mobile robot. Finally, the experiment results show that the robot path planning based on FNN algorithm is faster than other algorithms to finish the task as well as a better controllability and adaptability by the platform of Player/Stage.

关键词： Fuzzy neural network multi-robot system path planning Fuzzy neural networks Path planning multi-robot systems optimization algorithms adaptive optimization Control Methods Cost functions Membership functions Fuzzy control fuzzy control theory Fuzzy Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Design of Underactuated Steerable Electrode Arrays for Optimal Insertions

引用

JOURNAL OF MECHANISMS AND ROBOTICS-TRANSACTIONS OF THE ASME 2013年第1期5卷 011008-011008页

作者： Zhang, Jian Simaan, Nabil Vanderbilt Univ Dept Mech Engn ARMA Lab Nashville TN 37235 USA

This paper addresses the design of wire actuated steerable electrode arrays for optimal insertions in cochlear implant surgery. These underactuated electrode arrays are treated as continuum robots which have an embedded actuation strand inside their flexible medium. By pulling on the actuation strand, an electrode array assumes a minimum-energy shape. The problems of designing optimal actuation strand placement are addressed in this paper. Based on the elastic modeling of the steerable electrode arrays proposed in this paper, an analytical solution of the strand placement is solved to minimize the shape discrepancy between a bent electrode array and a given target curve defined by the anatomy. Using the solved strand placement inside the steerable electrode array, an optimized insertion path planning with robotic assistance is proposed to execute the insertion process. Later, an optimization algorithm is presented to minimize the shape discrepancy between an inserted electrode array and a given target curve during the whole insertion process. Simulations show a steerable electrode array bending using the elastic model and robot insertion path planning with optimized strand placement. Two experiments have been conducted to validate the elastic model and algorithms. [DOI: 10.1115/1.4007005]

关键词： Modeling Shapes optimization algorithms Electrodes Robots

来源：评论

学校读者我要写书评

暂无评论

Model Reduction Using Proper Orthogonal Decomposition and Predictive Control of Distributed Reactor System

引用

JOURNAL OF CONTROL SCIENCE AND ENGINEERING 2013年第unknown期2013卷 763165.1-763165.19页

作者： Marquez, Alejandro Espinosa Oviedo, Jairo Jose Odloak, Darci Univ Nacl Colombia Fac Minas Medellin 050041 Colombia Univ Sao Paulo Chem Engn Dept BR-05508900 Sao Paulo SP Brazil

This paper studies the application of proper orthogonal decomposition (POD) to reduce the order of distributed reactor models with axial and radial diffusion and the implementation of model predictive control (MPC) based on discrete-time linear time invariant (LTI) reduced-ordermodels. In this paper, the control objective is to keep the operation of the reactor at a desired operating condition in spite of the disturbances in the feed flow. This operating condition is determined by means of an optimization algorithm that provides the optimal temperature and concentration profiles for the system. Around these optimal profiles, the nonlinear partial differential equations (PDEs), that model the reactor are linearized, and afterwards the linear PDEs are discretized in space giving as a result a high-order linear model. POD and Galerkin projection are used to derive the low-order linear model that captures the dominant dynamics of the PDEs, which are subsequently used for controller design. An MPC formulation is constructed on the basis of the low-order linear model. The proposed approach is tested through simulation, and it is shown that the results are good with regard to keep the operation of the reactor.

关键词： low-order Reactors optimum temperature Maximum Allowable Concentration Pods linear models Orthogonal Predictive control REACTOR OPERATION optimization algorithms Surgery Reduced order model Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of 2D and 3D Lung Nodules in Chest Spiral CT Scans

引用

INTERNATIONAL JOURNAL OF BIOMEDICAL IMAGING 2013年第1期2013卷 517632页

作者： El-Baz, Ayman Elnakib, Ahmed Abou El-Ghar, Mohamed Gimel'farb, Georgy Falk, Robert Farag, Aly Univ Louisville Dept Bioengn Bioimaging Lab Louisville KY 40292 USA Univ Mansoura Urol & Nephrol Dept Mansoura 35516 Egypt Univ Auckland Dept Comp Sci Auckland 1142 New Zealand Jewish Hosp Med Imaging Div Louisville KY 40202 USA Univ Louisville Elect & Comp Engn Dept Louisville KY 40292 USA

Automatic detection of lung nodules is an important problem in computer analysis of chest radiographs. In this paper, we propose a novel algorithm for isolating lung abnormalities (nodules) from spiral chest low-dose CT (LDCT) scans. The proposed algorithm consists of three main steps. The first step isolates the lung nodules, arteries, veins, bronchi, and bronchioles from the surrounding anatomical structures. The second step detects lung nodules using deformable 3D and 2D templates describing typical geometry and gray-level distribution within the nodules of the same type. The detection combines the normalized cross-correlation template matching and a genetic optimization algorithm. The final step eliminates the false positive nodules (FPNs) using three features that robustly define the true lung nodules. Experiments with 200 CT data sets show that the proposed approach provided comparable results with respect to the experts.

关键词： Computer aided analysis Dataset gray level distribution Lung nodules Spiral Computed Tomography optimization algorithms automatic detection Bronchioles

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：