Parallel Bacterial Potential Field Algorithm for Path Planning in Mobile Robots: A GPU Implementation
Path planning is a fundamental task in autonomous mobile robot navigation and one of the most computationally intensive tasks. In this work, a parallel version of the bacterial potential field (BPF) method for path planning in mobile robots is presented. The BPF is a hybrid algorithm, which makes use of a bacterial evolutionary algorithm (BEA) with the artificial potential field (APF) method, to take advantage of intelligent and classical methods. The parallel bacterial potential field (parallel-BPF) algorithm is implemented on a graphics processing unit (GPU) to speed up the path planning computation in mobile robot navigation. Simulation results to validate the analysis and implementation are provided; the experiments were specially designed to show the effectiveness and the efficiency of the parallel-BPF algorithm.
KeywordsBacterial potential field Path planning Mobile robots GPU
We thank Instituto Politécnico Nacional (IPN), the Comisión de Operación y Fomento de Actividades Academicas of IPN (COFAA), and the Mexican National Council of Science and Technology (CONACYT) for supporting our research activities.
- 5.Y. Chen, J. Yu, X. Su, G. Luo, Path planning for multi-UAV formation. J. Intell. Rob. Syst. 77(1), 229–246 (2015)Google Scholar
- 8.N.E. Nawa, T. Hashiyama, T. Furuhashi, Y. Uchikawa, A study on fuzzy rules discovery using pseudo-bacterial genetic algorithm with adaptive operator. Paper presented at the IEEE international conference on evolutionary computation, Indianapolis, IN, 13–16 Apr 1997 (1997)Google Scholar
- 9.J. Botzheim, L.T. Kóczy, Model identification by bacterial optimization. National Scientific Research Fund, Budapest, Hungary. https://pdfs.semanticscholar.org/b717/7925a514452b03d9802a7a6390b1910db30a.pdf. Accessed 05 Apr 2017 (2004)
- 10.M.F. Rad, F. Akbari, A.J. Bakht, Implementation of common genetic and bacteriological algorithms in optimization testing data in mutation testing. Paper presented at the 2010 international conference on computational intelligence and software engineering, Wuhan, 10–12 Dec 2010 (2010)Google Scholar
- 12.J. Botzheim, L. Gál, L.T. Kóczy, Fuzzy rule base model identification by bacterial memetic algorithms, in Recent Advances in Decision Making, vol. 222, ed. by E. Rakus-Andersson, R.R. Yager, N. Ichalkarange, L.C. Jain (Springer, Berlin, 2009), pp. 21–43Google Scholar
- 13.J. Botzheim, Y. Toda, N. Kubota, Path planning for mobile robots by bacterial memetic algorithm. Paper presented at the 2011 IEEE workshop on robotic intelligence in informationally structured space, Paris, 11–15 Apr 2011 (2011)Google Scholar
- 15.Q. Zhang, D. Chen, T. Chen, An obstacle avoidance method of soccer robot based on evolutionary artificial potential field. Procedia 16, 1792–1798 (2012). Paper presented at the 2012 international conference on future energy, environment, and materialsGoogle Scholar