Step-spreading map knowledge based multi-objective genetic algorithm for robot-path planning

To tackle the path planning of mobile robots, a step-spreading map (SSM) algorithm was proposed as the prior knowledge to instruct the evolutionary process of multi- objective genetic algorithm (MOGA). The time complexity of SSM is O(8 x n) and n is the scale of problem. Inspired by Pareto optimum and NSGA-II, the developed MOGA can deal the path planning with multi-objective optimization such as: minimum energy consumption, safest and shortest length of the paths, etc. To utilize the prior knowledge, the process of initialization and mutation are controlled by different rules. The effectiveness of the prior knowledge based MOGA is demonstrated by simulation studies. The Proposed MOGA worked well by using the SSM knowledge to generate Pareto Front with the initialization of population and evolution convergence. The efficiency of computational time of proposed algorithm suggests the ability to real-life applications.

[1]  David Filliat,et al.  Map-based navigation in mobile robots: II. A review of map-learning and path-planning strategies , 2003, Cognitive Systems Research.

[2]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[3]  Xin Du,et al.  Path planning method based on neural network and genetic algorithm , 2004, 2004 International Conference on Intelligent Mechatronics and Automation, 2004. Proceedings..

[4]  Carlos A. Coello Coello,et al.  A Short Tutorial on Evolutionary Multiobjective Optimization , 2001, EMO.

[5]  E. J. van Henten,et al.  Collision-free Motion Planning for a Cucumber Picking Robot , 2003 .

[6]  Nasser Sadati,et al.  Genetic algorithm in robot path planning problem in crisp and fuzzified environments , 2002, 2002 IEEE International Conference on Industrial Technology, 2002. IEEE ICIT '02..

[7]  B. Martin-del-Brio,et al.  A simple approach to robot navigation based on cooperative neural networks , 2002, IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02.

[8]  W. Gharieb,et al.  Path planning for a mobile robot using genetic algorithms , 2004, International Conference on Electrical, Electronic and Computer Engineering, 2004. ICEEC '04..

[9]  Marcus Gemeinder,et al.  GA-based path planning for mobile robot systems employing an active search algorithm , 2003, Appl. Soft Comput..

[10]  Kesheng Wang,et al.  A Problem-Specific Genetic Algorithm for Path Planning of Mobile Robot in Greenhouse , 2006, PROLAMAT.

[11]  Xuemei Liu,et al.  An Effective Algorithm of Shortest Path Planning in a Static Environment , 2006, PROLAMAT.