An immune evolutionary algorithm based pose estimation method for parallel manipulator

Authors:
Shu-Ping Zhang;Yong-Sheng Ding;Kuang-Rong Hao
Affiliations:
Donghua University, Shanghai, China;Donghua University, Shanghai, China;Donghua University, Shanghai, China
Venue:
Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation
Year:
2009

Citing 10
Cited 0

An analytic solution for the perspective 4-point problem

Computer Vision, Graphics, and Image Processing
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Robust camera parameter estimation using genetic algorithm

Pattern Recognition Letters
A Note on the Number of Solutions of the Noncoplanar P4P Problem

IEEE Transactions on Pattern Analysis and Machine Intelligence
A new method of camera pose estimation using 2D-3D corner correspondence

Pattern Recognition Letters
On the Probability of the Number of Solutions for the P4P Problem

Journal of Mathematical Imaging and Vision
A Minimal Solution to the Generalised 3-Point Pose Problem

Journal of Mathematical Imaging and Vision
Pose determination and plane measurement using a trapezium

Pattern Recognition Letters
Single view based pose estimation from circle or parallel lines

Pattern Recognition Letters
Recognition and pose estimation of unoccluded three-dimensional objects from a two-dimensional perspective view by banks of neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Based on immune systems, a new immune evolutionary algorithm (IEA) is presented to develop a pose estimation method for a parallel manipulator in the paper. Four vertices of a parallelogram device on a parallel manipulator's end-effector are used as the object model. And the problem of pose identification is transformed to obtain the optimal depth estimations of the object model. In IEA, depth estimations of the object model are taken as an antigen. Then the optimal solutions are searched by clone selection and variation operator. In theory, this method enriches the pose estimation methods from four points correspondences. In addition, it provides guidance for practical applications of a parallel manipulator. Experiments results demonstrate that our algorithm works speedily and robustly.