Advertisement

Optimal Path Selection for Mobile Robot Navigation Using Genetic Algorithm in an Indoor Environment

  • D. Tamilselvi
  • S. Mercy Shalinie
  • A. Fathima Thasneem
  • S. Gomathi Sundari
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7135)

Abstract

The proposed Navigation Strategy using GA (Genetic Algorithm) finds an optimal path in the simulated grid environment. GA finds a path that connects the robot’s starting and target positions via predefined points. Each point in the environmental model is called a genome and the path connecting the Start and Target is called a Chromosome. According to the problem formulation, the length of the chromosomes (number of genomes) is dynamic and the genome is not just a simple digit. In this case, every genome represents a node in the 2D grid environment. After the application of crossover and mutation concepts the resultant chromosome (path) is subjected to an optimization process which gives an optimal path as a result. The problem is that there are chances for the fittest chromosome to be lost while performing the reproduction operations. This problem is solved by using the concept of elitism to maintain the population richness. The efficiency of the algorithm is analyzed with respect to the execution time and path cost to reach the destination. An optimal path is achieved in both static and dynamic environment.

Keywords

Mobile Robot Path Planning Genetic Algorithm OptimalPath Navigation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Tu, J., Yang, S.X.: Genetic algorithm based path planning for a mobile robot. In: IEEE International Conference on Robotics and Automation, vol. 1, pp. 1221–1226 (2003)Google Scholar
  2. 2.
    Sedighi, K.H., Ashenayi, K., Manikas, T.W., Wainwright, R.L., Tai, H.M.: Autonomous local path planning for a mobile robot using a genetic algorithm. Congress on Evolutionary Computation 2, 1338–1452 (2004)Google Scholar
  3. 3.
    AL-Taharwa, I., Sheta, A., Al-Weshah, M.: A Mobile Robot Path Planning Using Genetic Algorithm in Static Environment. Journal of Computer Science 4(4), 341–344 (2008)CrossRefGoogle Scholar
  4. 4.
    Arkin, A.: Using Genetic Algorithm to learn Reactive Control Parameters for Autonomous Mobile Robot Navigation. Adaptive Behaviour 2(3), 277–304 (1994)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Zhang, Y., Zhang, L., Zhang, X.: Mobile Robot Path Planning Base on the Hybrid Genetic Algorithm in Unknown Environment. In: Eighth International Conference on Intelligent Systems Design and Applications, ISDA 2008, vol. 2, pp. 661–665 (2008)Google Scholar
  6. 6.
    Ye, C., Webb, P.: A Sub Goal Seeking Approach for Reactive Navigation in Complex Unknown Environments. Robotics and Autonomous Systems 57(9), 877–888 (2009)CrossRefGoogle Scholar
  7. 7.
    Changan, L., Xiaohu, Y., Chunyang, L., Guodong, L.: Dynamic Path Planning for Mobile Robot Based on Improved Genetic Algorithm. Chinese Journal of Electronics 19(2), 2010–2014 (2010)Google Scholar
  8. 8.
    Hwang, Ahuja, Y.K.: Gross Motion Planning-A Survey. ACM Computing Surveys 24(3), 219–291 (1992)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • D. Tamilselvi
    • 1
  • S. Mercy Shalinie
    • 1
  • A. Fathima Thasneem
    • 1
  • S. Gomathi Sundari
    • 1
  1. 1.CSE Dept.Thiagarajar College of EngineeringMaduraiIndia

Personalised recommendations