Mobile Robot Path Planning Based on Ant Colony Optimization

Abstract:

Global path planning is quoted in this paper. The stoical and global environment has been given to us, which is abstracted with grid method before we build the workspace model of the robot. With the adoption of the ant colony algorithm, the robot tries to find a path which is optimal or optimal-approximate path from the starting point to the destination. The robot with the built-in infrared sensors navigates autonomously to avoid collision the optimal path which has been built, and moves to the object. Based on the MATLAB platform, the simulation results indicate that the algorithm is rapid, simple, efficient and high-performance. Majority of traditional algorithms of the path planning have disadvantages, for instance, the method of artificial potential field is falling into the problem of local minimum value easily. ACO avoids these drawbacks, therefore the convergence period can be extended, and optimal path can be planned rapidly.

• Periodical: Applied Mechanics and Materials (Volumes 687-691)
• Pages: 706-709
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.687-691.706
• Online since: November 2014
• Authors: Bao Feng Zhang*, Ya Chun Wang, Xiao Ling Zhang
• Keywords: Ant Colony Optimization, Global Path Planning, Grid Method, Robot

References

[1] Dorigo M, Bonabeau E, etal. Ant algorithms and stigmergy [J]. Future Generation Computer Systems, 2000, 16: 851-871.

DOI: 10.1016/s0167-739x(00)00042-x

[2] Deneubourg J L, Aron S, etal. The self- organizing exploratory pattern of the argentine ant[J]. Journal of Insect Behavior, 1990, 3: 159-168.

DOI: 10.1007/bf01417909

[3] Goss S, Aron S, etal. Self-organizing shortcuts in the Argentine Ant[J]. Naturwissens-ehaften, 1989, 76: 579-581.

DOI: 10.1007/bf00462870

[4] Shiyong L, Yongqiang C, Yan L. Ant colony algorithm and its application [M]. Harbin Industry Press, 2004. 18-21.

[5] Lige D, Cile SL. Ant colony optimization[M]. Jun Z, Xiaomin H, Xuyao L, etc. Tsinghua University press, 2007. 1-5.

[6] Guimei X, Jianchao Z. A roulette wheel selection stochastic particle swarm optimization algorithm based on genetic algorithm [J]. Computer engineering and Science, 2007, 29 (6): 52.