## GENETIC ALGORITHM BASED ROBOT MASSAGE

### BibTeX

@MISC{Alavandar_geneticalgorithm,

author = {Srinivasan Alavandar},

title = {GENETIC ALGORITHM BASED ROBOT MASSAGE},

year = {}

}

### OpenURL

### Abstract

In this paper, a new robot massage experimental setup for leg using genetic algorithm based camera calibration is presented. Teach Mover, a five axis articulated robot is used to press the muscle from ankle to knee. The real leg massage problem is approximated by a frustum shaped model, which can be easily extended to real leg massage. Three different sensors that are encoders; mounted at each joint of the robot with six degrees of freedom, a calibrated camera and a grip switch; mounted at the wrist of the manipulator were used. Camera calibration is done with the help of an algorithm proposed by Qiang Ji et. al [1] to estimate internal and external camera parameters using seven control points. The distance between camera and the robot is assumed to be fixed. By estimating the position and orientation of the object, which is the frustum model, the linear trajectory is found which the robot follows. The result shows the feasibility of the use of above-mentioned approach. The algorithm works satisfactorily for wide range of varying parameters i.e. the position and orientation of the model.

### Citations

2031 | Genetic algorithms in search, optimization and machine learning - Goldberg - 1989 |

1644 | An introduction to genetic algorithms - Mitchell - 1997 |

1126 |
A versatile camera calibration technique for high-accuracy 3d machine vision metrology using off-the-shelf TV cameras and lenses
- Tsai
- 1987
(Show Context)
Citation Context ...lgorithm. It was also observed that the scale factors were the most affected one if the control points approximately lie in a single plane. This observation is inline with that of the one reported in =-=[2]-=-. In fact, [2] has removed the scale factors from single plane calibration and advises to calibrate scale factors only in multi plane techniques. Thus, the camera was positioned in such a way that the... |

656 | A Tutorial on Visual Servo Control - Hutchinson, Hager, et al. - 1996 |

82 | A Comparison of Selection Schemes Used in Genetic Algorithms - Blickle, Thiele - 1995 |

58 | Visual control of robot manipulators - a review - Corke - 1993 |

35 | Camera Calibration and 3D Reconstruction from Single Images Using - Wilczkowiak, Boyer, et al. |

33 | The Role of Mutation and Recombination in Evolutionary Algorithms - Spears - 1998 |

14 | Analysis of Selection, Mutation and Recombination in Genetic Algorithms
- Mühlenbein, Schlierkamp-Voosen
- 1993
(Show Context)
Citation Context ...es given in [1] and here is different. This is because; here the pose of the object is estimated with that of the camera. The algorithm uses linear ranking selection and Roulette wheel selection. See =-=[10]-=- and [11] for an in-depth analysis of these selection schemes. The linear ranking selection scheme sorts in the best individual and gives mo re chromosomes for the successful one during selection proc... |

13 |
New exact and approximate solutions of the three-point perspective problem
- DeMenthon, Davis
- 1989
(Show Context)
Citation Context ... orthonormality constraint of the rotation matrix and solve the pose of the object as a linear system [2]. The rotation matrix is then made orthonormal after the solution is found. Analytic solutions =-=[3]-=- are closed form solutions that exist for a small number of points and are sensitive to the accuracy of the feature point extraction. In nonlinear methods, the pose of the object is iteratively improv... |

9 | Comparison of selection methods for evolutionary optimization
- Zhang, Kim
(Show Context)
Citation Context ...in [1] and here is different. This is because; here the pose of the object is estimated with that of the camera. The algorithm uses linear ranking selection and Roulette wheel selection. See [10] and =-=[11]-=- for an in-depth analysis of these selection schemes. The linear ranking selection scheme sorts in the best individual and gives mo re chromosomes for the successful one during selection process. 3.1.... |

6 | Genetic Algorithms in Search and Optimization: The Technique and Applications
- Deb
- 1998
(Show Context)
Citation Context ...for a small number of points and are sensitive to the accuracy of the feature point extraction. In nonlinear methods, the pose of the object is iteratively improved while the system remains nonlinear =-=[4]-=-. Here the nonlinear approach is followed. 2. STATEMENT OF THE PROBLEM The problem under consideration is massaging automatically the leg of the patient in order to reduce the pain using the TeachMove... |

4 |
Real coded genetic algorithms, virtual alphabets and blocking
- Goldberg
- 1991
(Show Context)
Citation Context ...Most of the theoretical work supports for encoding the bits in binary and the industry supports for the real valued ones. This discrepancy was solved by Goldberg although not in favor of both of them =-=[9]-=-. Here the algorithm is encoded as the function of pan angle w, tilt angleφ, and swing angle k of the object as follows: X X Y Y r11 = cos φ cos φ r21 = sin ω sin φ cos k + cos ω sin k r31 = − cos ω s... |

1 | Cohen and Marc Herniiou et al. “Camera calibration with distortion models and accuracy evaluation - Weng, Paul - 1992 |

1 | cohen and Marc Herniiou , “Camera calibration with distortion models and accuracy estimation - weng, Paul - 1992 |

1 | Zvi S.Roth, “Camera-aided robot calibration - Zhuang - 1996 |