检索结果-内蒙古大学图书馆

IEEE International Conference on robotics and automation (ICRA)

作者： L. Singh A. Silverthorne S. Gottschlich H. Stephanou New York State Center for Advanced Technology in Robotics and Automation Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute Troy NY USA

There are numerous applications in which robots are needed to assist rather than replace human operators. These applications typically involve either work in a dangerous environment or performing tasks that are physically impossible for humans to accomplish by themselves. Robots used in this mode do not need to be autonomous because they can essentially be controlled by the operator. Nonetheless, it is difficult for an operator to flawlessly control a robot with a large number of degrees of freedom. Therefore, an intelligent control system is needed to correct and improve the operator's input to the robot. In this paper the authors discuss a central component in this control system known as the variably-autonomous trajectory generator (VATG). The VATG combines input from the operator with input from one or more autonomous control modules (CM) to generate the robot trajectory. The amount of impact the autonomous CMs will have on the overall trajectory will depend on a number of factors such as the task being performed and the sensing modalities available, hence the authors refer to this type of control as being variably-autonomous.< >

关键词： Robot sensing systems robotics and automation Humans Control systems Application software Wrist Tactile sensors Force sensors Grasping Systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

Training hard-limiting neurons using back-propagation algorithm by updating steepness factors

Training hard-limiting neurons using back-propagation algori...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Xiangui Yu N.K. Loh W.C. Miller Department of Electrical Engineering University of Windsor Windsor ONT Canada Center for Robotics and Advanced Automation Dodge Hall of Engineering Oakland University Rochester MI USA

This paper presents one kind of modified backpropagation algorithm for training the multilayer feedforward neural networks with hard-limiting neurons. Adaptive steepness factors in the analog sigmoidal neuron activation functions are updated in the training process. With the decrease of the sum-square error, these steepness factors are varied from a small positive value to infinite. It makes the sigmoidal neuron transferred to hard-limiting one after the training process complete. Thus, a multilayer feedforward neural network can be trained with the resultant architecture is only composed of hard-limiting neurons. The learning algorithm is similar to the conventional backpropagation algorithm, only the derivatives of the hidden neural activation functions are modified according to the proposed idea. Extensive numerical simulations are presented to show the feasibility of the proposed algorithm. In addition, the numerical properties of the proposed algorithm are also discussed in detail. Comparisons of the proposed algorithm with algorithms are given, and some useful conclusions are drawn.< >

关键词： Neurons Backpropagation algorithms Multi-layer neural network Neural networks Feedforward neural networks Very large scale integration robotics and automation Multilayer perceptrons Numerical simulation Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

AN IMPROVED DIGIT-REVERSAL PERMUTATION ALGORITHM

引用

SIGNAL PROCESSING 1993年第3期32卷 409-415页

作者： YU, XG LOH, NK MILLER, WC Department of Electrical Engineering University of Windsor Windsor Ontario Canada N9B 3P4 Center for Robotics and Advanced Automation Dodge Hall of Engineering Oakland University Rochester MI48309-4401 USA

This paper introduces a new structure to compute the digit-reversal permutation in the radix-B fast Fourier or Hartley transform. By studying the property of base-B numbers, we find that any base-B number, k, can be represented as the sum of three numbers: one base-B number, i;digital reverse of another base-B number, j;and a constant, z, in which the two base-B numbers i and j are no greater than square-root N, where N is the number of data points to be transformed. Then, the digital reverse of k is just the sum of j and the digital reverse of i plus the constant z. Using this property we have developed a new algorithm to compute the digital reverse of any index very efficiently. Since it uses fewer arithmetic operations, the new algorithm is faster than other algorithms known to the authors and the program storage requirements are no greater than Evans' and Walker's algorithms.

关键词： FAST FOURIER TRANSFORM FAST HARTLEY TRANSFORM DIGIT-REVERSAL PERMUTATION BIT-REVERSE ALGORITHM

来源：评论

学校读者我要写书评

暂无评论

Dynamic Modelling and Tracking Control of Nonholonomic Wheeled Vehicles

引用

IFAC Proceedings Volumes 1993年第2期26卷 61-64页

作者： G.J. Pappas K.J. Kyriakopoulos New York State Center for Advanced Technology in Automation and Robotics & Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute Troy NY 12180-3590 USA

Nonholonomic vehicles are shown to be kinematically equivalent to unicycles. A dynamic model for mobile vehicles moving on planar surfaces under nonholonomic constraints is derived. The model is decomposed into a kinematic and a dynamic subsystem. The kinematic subsystem is shown to be globally stabilizable by using continuous control laws on reference trajectories that are nonstationary and continuously differentiable with respect to time. The continuity of the kinematic control inputs allows the extension of the vehicle control at the dynamic level. Stability of the overall closed loop system is examined using singular perturbation theory. Simulations verify all theoretical derivations.

关键词： Nonholonomic Control Vehicle Control Mobile Robots

来源：评论

学校读者我要写书评

暂无评论

Registration of dissimilar featureless models for inspection

Registration of dissimilar featureless models for inspection

引用

IEEE International Conference on robotics and automation (ICRA)

作者： G.H. Tarbox S.N. Gottschlich L.A. Gerhardt New York State Center for Advanced Technology in Automation and Robotics and Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute Troy NY USA

General-purpose CAD-based inspection of a manufactured workpiece often involves comparing a part model created using intensity or range images of the part to a toleranced reference model of the part. Before this comparison can be made, however, the sensed object model must be registered to the reference object model. Most registration approaches assume that it is possible to identify and match features in the models and that the object models represent very similar geometries. A registration approach that deals with featureless dissimilar models is presented, and experimental results are demonstrated. Although the need for such an approach was motivated by needs in inspection, the approach is very general and can be used in a variety of other applications.< >

关键词： Inspection Casting robotics and automation Solid modeling Data structures Systems engineering and theory Geometry Valves Manufacturing processes Surface morphology

来源：评论

学校读者我要写书评

暂无评论

Nonholonomic path planning with inequality constraints

Nonholonomic path planning with inequality constraints

引用

IEEE Conference on Decision and Control

作者： A.W. Divelbiss J. Wen New York State Center for Advanced Technology in Robotics and Automation Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute Troy NY USA

A class of Newton-type algorithms is effective in solving the kinematic path planning problem for a system with nonholonomic equality constraints. A key result in this approach has been the generic full rank condition of a certain gradient operator. We have extended this method to path planning problems with inequality constraints and shown its efficacy in solving some challenging problems, but a similar genericity result is not currently available. In this paper, we present some extension of our algorithm for nonholonomic path planning with equality and inequality constraints and show the generic full rank condition for a special case. Simulation examples involving a steerable tractor-trailer vehicle and experiment results of a quarter-scale car with a trailer are presented.< >

关键词： Path planning Control systems Nonlinear control systems Controllability robotics and automation Systems engineering and theory Kinematics Space vehicles Velocity control Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Shape matching from grasp using a minimal representation size criterion

Shape matching from grasp using a minimal representation siz...

引用

IEEE International Conference on robotics and automation (ICRA)

作者： R. Joshi A.C. Sanderson New York Center for Advanced Technology in Automation and Robotics USA Electrical Computer and Systems engineering Department Rensselaer Polytechnic Institute Troy NY USA

A robust polynomial-time algorithm for model-based pose estimation from tactile grasp data is presented. A minimal representation criterion is used to formulate the matching problem as a global optimization. The hypothesize-and-test paradigm is invoked to search for the optimal solution. A three-on-three match of model features to data features is used to reduce the transform search space to polynomial size. A polynomial-time assignment algorithm is used to compute the optimal correspondence for each hypothesized pose. The strength of the algorithm lies in its ability to perform with noisy or incomplete data and with missing or spurious features. It is capable of rejecting outliers and finding partial matches, and it produces sensible results even in the presence of large noise. The algorithm has been implemented and tested on actual data.< >

关键词： Shape Polynomials robotics and automation Testing Robustness Kinematics Least squares approximation Fingers Data engineering Systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

Automatic synthesis and verification of compliance mappings

Automatic synthesis and verification of compliance mappings

引用

IEEE International Conference on robotics and automation (ICRA)

作者： S. Vougioukas S. Gottschlich New York State Center for Advanced Technology in Robotics and Automation USA Electrical Computer and Systems Engineering Department Rensselaer Polytechnic Institute NY USA

When the uncertainty is large compared to clearances between objects, some form of compliance is required for a robot to manipulate these objects. Such situations include, but are not restricted to, assembly operations. Compliance can be thought of as a task-dependent mapping from sensed forces to corrective motions which bring the robot closer to its goal. A methodology for the automated synthesis of this mapping is described. The possible erroneous configurations of the robot together with their resulting contact forces are computed, and a corrective motion is identified for each configuration. The validity of the mapping is checked to ensure that the sensed forces will provide unambiguous information during the actual execution of the planned compliant motion.< >

关键词： robotics and automation Robot sensing systems Uncertainty Robotic assembly Path planning Motion planning Damping Systems engineering and theory technology planning Sensor systems

来源：评论

学校读者我要写书评

暂无评论

The design and training of an intelligent sensor implementation

The design and training of an intelligent sensor implementat...

引用

Canadian Conference on electrical and Computer Engineering (CCECE)

作者： Xiangui Yu N.K. Loh G.A. Jullien W.C. Miller Department of Electrical Engineering University of Windsor Windsor ONT Canada Center for Robotics and Advanced Automation Dodge Hall of Engineering Oakland University Rochester MI USA

The design and VLSI implementation of an intelligent sensor that can be used for process control applications requiring image capture or non-contact measurement is presented in this paper. The sensor architecture is based on an analog VLSI realization of an artificial neural network with an integrated photosensitive array. A 10/spl times/10 array of photosensitive cells has been designed as the input nodes to a two-layer feedforward neural network. Four groups each with 25 photosensors are fully connected to 4 neurons respectively in the hidden layer. The 16 hidden neurons are fully connected to 5 neurons in the output layer. A development program has been written that determines the optimal set of weights using the modified backpropagation algorithm. The neural network has been trained to recognize 18 different types of patterns. The final implementation of this intelligent sensor has the dimensions of 4500/spl times/4820 design scale microns and contains approximately 1630 analog devices fabricated using a 3/spl mu/ single-polysilicon, double-metal, p-well CMOS process.< >

关键词： Intelligent sensors Sensor arrays Neurons Very large scale integration Artificial neural networks Neural networks Process control Feedforward neural networks Backpropagation algorithms Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Comparisons of four learning algorithms for training the multilayer feedforward neural networks with hard-limiting neurons

Comparisons of four learning algorithms for training the mul...

引用

Canadian Conference on electrical and Computer Engineering (CCECE)

In this paper, two kinds of learning algorithms that have been developed for training multilayer feedforward neural networks with hard-limiting neurons are reviewed. For the modified backpropagation algorithms, their numerical performances of convergence speed and training efficiency are compared; for the architecture generating methods, the architecture sizes of the neural networks generated are compared and their generalization ability are discussed. For any given application problem, some criteria for selecting a suitable training algorithm are also discussed.< >

关键词： Multi-layer neural network Neural networks Feedforward neural networks Neurons Backpropagation algorithms Artificial neural networks robotics and automation Electronic mail Convergence of numerical methods Multilayer perceptrons

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：