Action Decision Strategy of Simulation Robot Fish Based on Ant Colony Algorithm

Xu Qiong Yang; Xue Le Jia; Yan Song  Deng

doi:10.4028/www.scientific.net/AMM.341-342.949

Paper Titles

Optimization of Hybrid Electric Bus Control Strategy with Hybrid Optimization Algorithm
p.924

On Non-Linearities Separate Modeling Method and State Feedback Control
p.931

Path Planning of Multi-Robot Fish Based on Cooperative Game Model
p.940

Backstepping Based Adaptive Control of Magnetic Levitation System
p.945

Action Decision Strategy of Simulation Robot Fish Based on Ant Colony Algorithm
p.949

Comprehensive CEP Evaluation Method for Calculating Positioning Precision of Navigation Systems
p.955

The Application Research of Coal Seam CO Source Identification Based on the D-S Evidence Conflict
p.961

Vibration Analysis and Control of an Active Power-Train Mount System
p.966

Used Surface Plasma Wave Measure the Thickness and the Negative Permittivity of Nanometal Film
p.971

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 341-342Action Decision Strategy of Simulation Robot Fish...

Action Decision Strategy of Simulation Robot Fish Based on Ant Colony Algorithm

Abstract:

In order to achieve the quick and accurate adjustment of the robot fish, there are two plans, which are based on ant-colony-algorithm movement strategy. These plans are aimed at 2D robot fish in the ant colony algorithm, and the key judgment of the robot fish relies on the branches of physic matters, together with the best match of the fish in its current speed. However, according to the dynamic algorithm project, the feedback of dynamic variable movement can process adjustment automatically. In every period, these two examples by which the 2D Simulation results show the robot fish can be adjusted on the policy path. To achieve optimal combination of speed and direction, the shortest time has a strong ability to adapt effectively to meet the simulation of robot fish or action of the action decision-making.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 341-342)

Pages:

949-954

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.341-342.949

Citation:

Cite this paper

Online since:

July 2013

Authors:

Xu Qiong Yang, Xue Le Jia, Yan Song Deng

Keywords:

Action Decision-Making, Ant Colony Algorithm (ACA), Branch Boundaries, Dynamic Programming, Simulation Robot Fish

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Wang Pengfei, Tian red for multi-robot path planning, an improved ant colony algorithm . Computer Knowledge and Technology, 2008, 4(2): 54-55.

Google Scholar

[2] Dorigo, Maniezzo, Colomi. AntSystem: optimization by a colony of cooperating agents. IEEE Tran saction son SMC, 1996, 26(1): 8-14.

Google Scholar

[3] Auzinger D, Djumlija G Application of advanced aechnology packages for improved strip profile and flatness in hot-strip-mills. Iron and steel, 2004, 39(11): 132-133.

DOI: 10.1051/metal:2003111

Google Scholar

[4] Yue Fuzhan, Cui Pingyuan. Planetary Robot Path Planning Based on Improved Ant Colony Algorithm. Control and Decision, 2006, 21 (12): 1437-1440.

Google Scholar

[5] Du Zhijun, Chen Shanshan, Li Bobo robotic fish speed control algorithm . Academic discussion, Hownet space 2009, the volume (8).

Google Scholar

[6] Chai Zhongming, Yu Mei, Liu Shu. Genetic algorithm for path planning of robotic fish based on. Automation panorama, 2010, 29 (11): 92-96.

Google Scholar

[7] Wu Qidi, Wang Lei. Ant colony algorithm and its application. Shanghai: Shanghai Education Press, 2004: 3-129.

Google Scholar