A Mobile Robot Path Planning Using Genetic Algorithm in Static Environment
A Mobile Robot Path Planning Using Genetic Algorithm in Static Environment
A Mobile Robot Path Planning Using Genetic Algorithm in Static Environment
Corresponding Author: Ismail AL-Taharwa, Department of Information Technology, Faculty of Science and Information Technology, Al-Balqa Applied University, Al-Salt, Jordan
341
J. Computer Sci., 4 (4): 341-344, 2008 Proposed algorithms: To use GAs for solving the path planning problem, we considered number of steps. These steps are: First: Convert the search environment to a grid graph (i.e., node). Thus, the robot shall move in a step fashion on the proposed grid as they appear in the real environment Second: Specify the staring and ending point where the path need to be established Third: Defining the static obstacles locations on each node of the grid shortest path helps computing the total number of steps the mobile robot need to take to reach the ending point. Consequently, the fitness value for a complete solution will be computed as: pi = d0 + d1 ++ dm d0 = d1 = d2 = dm = The distance between cstart, c1 The distance between c1, c2 The distance between c2, c3 The distance between c1, cend
Path planning technique: In this study, we present the main steps for the proposed path planning techniques. Initialization: Create an initial population with a predefined population size. The population contains number of individuals (i.e., chromosomes). Each individual represents a solution for the problem under study. In our case, each solution is in fact a path between the start and end point in the search space. The initial population with size n can be presented as: Initial Population = <p1, p2,,pn> Each structure pi is simply an integer string of length L, in general. Each structure pi represents a vector of node numbers in the grid which can take values of 1, 2, , L (i.e., search space). Normally, GAs individuals can contain any point value between the starting and ending point. Thus, the individual generated by GAs is in the form of: <c1, c2,,cl > where, l is the number of visited node in the search space. The starting and ending point will not be shown in this individual. This is why we need to make some modification to the individual structure so that we can add the starting and ending point. The modified individual representation will be: <cstart, c1, c2,,sl, cend> Fitness function: Fitness function represents an important part of any evolutionary process using GAs. Appropriate selection of the fitness function will lead the search towards the optimal solution. The optimal path, in our case, is the shortest path between the starting and ending point. Thus, the fitness function is responsible on finding this path. The 342
Fitness computation: To compute the fitness function for an individual, we should have the coordinates of each point in the individual (i.e., column and row for each cl from a lookup table). Thus, we can compute the distance between any two points in the search space (i.e., environment of the robot). Assume we have two points in the search space xcurrent, xnext. The distance between the two points can be computed using the following equation:
D = x next,col x current ,col + x next, row x current,row
Absolute value is important since distance is a quantity value. Experiments: In this study, we present our development experiments in with two types of environment (i.e., obstacle free and obstacle environment). Obstacle free environment: We used Genetic Algorithms to search a space of 1010 and 100100 nodes to find an optimal path for a mobile robot to move from a start to end points. In our experiment we used an individual structure of 7 elements and 18 elements, respectively. This means that the mobile robot could visit the same point number of times. This is why GAs has to pick up the best path which avoids this type of problems. We ran GAs with various population sizes 10, 20 and 50, respectively. The goal is to investigate about the behavior of GAs in each case. This will also help in showing that GAs will converge to the optimal solution (i.e., optimal path) in each run. In Table 1 and 2, we show the computed results using GAs with various population sizes, the best fitness value achieved after each run and the generation number where this value was found.
Generation no. 80 30 20
Fig. 1: Convergence process for GAs with a 100100 grid with obstacle free environment In Fig. 1, we show the convergence process for the GA in the case of the second experiment (100100 nodes). It is shown that with various population sizes, GA selected the optimal path in all cases. The best fitness value found equal to 198. Obstacle avoidance: In this study we propose three different environments with various obstacles locations. They include: Indoor environment Moderate scattered environment Complex scattered environment
Fig. 3: moderate scattered environment In Fig. 2, 3 and 4 we also show three best paths developed with various colours (i.e., red, pink and blue). It was found that increasing the number of generation helps finding the shortest path with less number of generations. Although, we know that the larger the number of individual in the population (i.e., large population size) is the larger number of computation. 343
The three environments are shown in Fig. 2, 3 and 4, respectively. In Table 3, 4 and 5, we show the best discovered paths using GAs with the three explored environment.
J. Computer Sci., 4 (4): 341-344, 2008 6. B. Graf, J. M. Hostalet Wandosell, Flexible path planning for nonholonomic mobile robots,. In Proc. 4th European workshop on advanced Mobile Robots (EUROBOT01)., Fraunhofer Inst. Manufact. Eng. Automat. (IPS). Lund, Sweden, Sept. 19-21, 2001, pp. 199-206. J. C. Latombe, Robot Motion Planning. 1st ed, Boston, UK, MA: Kluwer Academic Publishers (Published by Springer), 1991, ISBN: 0-79239129-2. T. Lozano-Perez and M. Wesely, (1979, October). An algorithm for planning collision-Free paths among polyhedral obstacles. Commun. of the ACM [Online], 22(10), pp. 560-570. D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning. 1st ed. ISBN: 0-201-15767-5, Boston, MA: Addison-Wesley Longman publishing Co., Inc., 1989. C. E. Thomas, M. A. C. Pacheco, M.M. and B.R. Vellasco, Mobile Robot Path Planning Using Genetic Algorithms,. In foundations and tools for neural modeling, vol. 1606/1999, Springer Berlin/ Heidelberg, ISBN: 3-540-66069-0, 1999, pp. 671679. J. Brank, Evolutionary approaches to dynamic optimization problems-introduction and recent trends, [Online] In Proc. GECCO Workshop on Evol. Algorithms for Dynamic Optimization Problems, Chicago, USA, 2003, pp. 2 J. Lu and D. Yang, Path planning based on double-layer genetic algorithm, in 3rd Int. Conf. on Natural Computation (ICNC 2007) [Online], Hangzhou, Haikou, China, Aug. 24-27, 2007, Vol. 4, pp: 357-361. A. Ramirez-Serrano and M. Boumedine, Real time navigation in unknown environments using fuzzy logic and ultrasonic sensing, in Proc. 1996 IEEE Int. Symp. In Intell. Control, Dearborn, MI, ISBN: 0-7803-2978-3, Y de Estudios supeiores de Monterrey, 15-18 Sept, 1996, pp: 26-30, DOI: 10.1109/ISIC.1996.556172. I.K. Jung, K.B. Hong, S.K. Hong and S.C. Hong, Path planning of mobile robot using neural network, in Proc. IEEE Int. Symp. on Ind. Electron,. Sch. Elect. Eng., 1999 ISIE Bled Slovenia, Vol. 3, 12-16 July, 1999, pp. 979-983, DOI: 10.1109/ISIE,1999.796750. J.J. Grefenstette, A Users guide to GENESIS, Technical Report, CS-84-11, Department of Computer Science, Vanderbilt University, Nashville, TN.
7.
8.
Fig. 4: Complex scattered environment CONCLUSIONS In this study we presented the idea of using Genetic Algorithm approach to solve the mobile robot path planning problem in static environment with predictable terrain. We proposed a simplified fitness function which utilizes the path length. We explored the performance of the evolutionary process with varies population size. Our preliminary experiments show that the proposed approach is effective and efficient in handling different types of tasks in static environments. REFERENCES 1. A. Elshamli, H. A. Abdullah and S. Areibi, Genetic algorithm for dynamic path planning. In: Proc. Canadian Conf. Elect. and Comput. Eng., Niagara Falls, Vol.2, May 2-5, 2004, pp: 677-680, ISBN: 0-7803-8253-6/04/$/7.00 2004 IEEE. Y. Davidor, Robot programming with a genetic algorithm,. In Proc. 1999 IEEE Int. Conf. Comput. Syst. and Software Eng., Tel Aviv, Israel, pp: 186-191. K. H. Sedighi, K. Ashenayi, T. W. Manikas, R. L. Wainwright, and H. M. Tai, Autonomous Local Path Planning for a Mobile Robot Using a Genetic Algorithm, in Congr. Evol. Comput. 2004. CEC2004., Vol. 2, pp. 1338-1345. A. Sheta and H. Turabieh, (2006, January). A comparison between genetic algorithms and sequential quadratic programming in solving constrained optimization problems.The Int. J. of Artificial Intell. and Mach. Learning 6(1), pp. 67-74. A. Ramirez-Serrano, H. Liu and G. C. Pettinaro. (2008). Mobile robot localization in quazi-dynamic environments. Int. J. on Ind. Robot, pp.246-258. 344
9.
10.
11.
12.
2.
13.
3.
14.
4.
15.
5.