Selection method of multi — objective problems using genetic algorithm in motion plan of AUV

Abstract

To research the effect of the selection method of multi — objects genetic algorithm problem on optimizing result, this method is analyzed theoretically and discussed by using an autonomous underwater vehicle (AUV) as an object. A changing weight value method is put forward and a selection formula is modified. Some experiments were implemented on an AUV, TwinBurger. The results shows that this method is effective and feasible.

Keywords

AUV / multi — objective optimization / genetic algorithm / selection method

References

[1] Ura T, Takagawa S. The survey of underwater robot[M]. 1996, Tokyo: Sizando publishing House

[2] Zhang Mingjun, Tamaki. Motion optimization of autonomous underwater vehiecles by genetic algorithm [J]. Journal of Society of Naval Architects of Japan, 1997, 182: 491-499 (in Japanese)

[3] Zhang Mingjun, Han Jinhua. Operating method of multi — objective problems genetic algorithm in motion plan of AUV[J]. Journal of Harbin Engineering University, 2000, 21(2): 23-27

[4] FUJII T, URA T. A study on intelligent behaviors of autonomous underwater robots[J]. Journal of Society of Naval Architects of Japan, 1993, 174 (in Japanese).

[5] ISHII K, URA T, FUJII T. A feed forward neural network for identification and adaptive of autonomous under-water vehicles[A]. Proc IEEE ICNN’ 94[C]. Orlando FL, 1994.

[6] Tamaki Hisashi. Generation of a set of pareto — optimal solutions by genetic algorithm[J]. T SICE, 1995, 31(8): 1185-1192