This paper introduces modified backpropagation algorithms for training multilayer feedforward neural networks with hard-limiting neurons. Transforming neuron activation functions are used in all the hidden layers, whi...
详细信息
This paper introduces modified backpropagation algorithms for training multilayer feedforward neural networks with hard-limiting neurons. Transforming neuron activation functions are used in all the hidden layers, which are the modified continuous sigmoidal functions with an adaptive steepness factors. In the training process, this steepness factor varies from a small positive value to infinite with the decrease of the sum square error. Thus, a multilayer feedforward neural network can be trained with the resultant architecture 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. Extensive numerical simulations are presented to show the feasibility of the proposed algorithm. In addition, the numerical properties of the proposed algorithm are discussed and comparisons of the proposed algorithm with other algorithms are made.< >
Given two objects, A and B, such that A intersection B not= theta , the authors define a measure to characterize the penetration between A and B. They present fast algorithms for computing the measure for planar and p...
详细信息
Given two objects, A and B, such that A intersection B not= theta , the authors define a measure to characterize the penetration between A and B. They present fast algorithms for computing the measure for planar and polyhedral objects and demonstrate how the measure can be used in collision detection for path planning.< >
A system for exhaustively inspecting a workpiece, not merely certain features, is presented. The system is based on comparing a volumetric representation of a reference object to a volumetric representation of an actu...
详细信息
Faat procedures for computing fuzzy prozimity meaaurea between a multifingered robot hand and an object to be grasped are presented in this paper. The computation useful in graap planning and in analyzing the local be...
详细信息
This paper presents an approach for designing robust tracking controller for lumped mass model of a vibrating link (VL) robot manipulator. The control methodology is intuitively simple since it is based on concepts wh...
详细信息
In this paper, we present a complete and exact algorithm for planning a geometrically feasible path for a polyhedral subassembly (robot) translating amongst polyhedral obstacles. Our algorithm can be used to determine...
详细信息
In traditional geometric modeling, it is common to assume that models of objects created are complete and correct. Unfortunately in real life robots and other autonomous machines may have only uncertain knowledge of o...
详细信息
A novel approach to inspection is presented based on comparing a volumetric representation of a reference object to a volumetric representation of an actual object iteratively created from sensor data. The use of volu...
详细信息
作者:
Stewart, C.V.Department of Computer Science
New York State Center for Advanced Technology in Automation and Robotics Rensselaer Polytechnic Institute TroyNY12180-3590 United States
Probability density functions (PDFs) are derived for many of the geometric measurements upon which stereo matching techniques are based, including orientation differences between matching line segments or curves, the ...
详细信息
作者:
S.S. KrishnanA.C. SandersonElectrical
Computer and Systems Engineering Department Center for Advanced Technology in Automation and Robotics Rensselaer Polytechnic Institute Troy NY USA
The feasible path problem is solved for planning a collision-free path to translate an arbitrary polyhedral robot from an initial position to some goal position in a polyhedral environment. The shortest path problem e...
详细信息
The feasible path problem is solved for planning a collision-free path to translate an arbitrary polyhedral robot from an initial position to some goal position in a polyhedral environment. The shortest path problem entails finding the shortest feasible path. The authors present two versions of the window corner (WC) algorithm, which is a novel solution to the problems for the case of single and multistep translational paths for two dimensions, and then summarize the extension to the three-dimensional WC algorithm, for feasible paths. The concept of window corners in the polyhedral cone representation (PCR) is introduced, which reduces the search space. The PCR cones store constraints between boundary elements. The PCO representation has O(m) vertices compared to O(m/sup 2/) in a C-space representation. The WC algorithm was tested and an example from assembly path planning is presented.< >
暂无评论