Multiobjective hybrid evolutionary path planning with adaptive pareto ranking of variable-length chromosomes

This paper presents a novel approach to multiobjective evolutionary robot path planning. The paths are designed for bi-dimensional continuous working scenes with disjoint, nonconvex obstacles. A new ranking procedure ensures a self-adapted progressive articulation between decision and search, performed in relation to the landscape of the objective space. The ranks are assigned by means of dominance analysis, while making use of adaptive grouping of individuals and adaptive control of diversity. The algorithm also accepts variable-length chromosomes and uses a new compatible crossover, which avoids the production of offspring longer than their parents. The unfeasible paths are repaired and shortened by means of a new corrective algorithm. This correction works only once on a specific chromosome and its main role is to guide the genetic search towards the feasible regions of the search space. The experiments demonstrate the effectiveness of the suggested techniques on several working scenes with different maps of obstacles.

[1]  Lavinia Ferariu,et al.  Multiobjective design of evolutionary hybrid neural networks , 2011, The 17th International Conference on Automation and Computing.

[2]  Oscar Castillo,et al.  Multiple Objective Genetic Algorithms for Path-planning Optimization in Autonomous Mobile Robots , 2006, Soft Comput..

[3]  Fumitoshi Matsuno,et al.  Path planning for an autonomous mobile robot considering a region with a velocity constraint in a real environment , 2012, Artificial Life and Robotics.

[4]  Marina L. Gavrilova,et al.  Generalized Voronoi Diagram: A Geometry-Based Approach to Computational Intelligence , 2008, Generalized Voronoi Diagram.

[5]  Marina L. Gavrilova,et al.  Density-Based Clustering Based on Topological Properties of the Data Set , 2008, Generalized Voronoi Diagram.

[6]  Ferariu Lavinia,et al.  Multi-objective genetic algorithm with clustering-based ranking and direct control of diversity , 2013, 2013 17th International Conference on System Theory, Control and Computing (ICSTCC).

[7]  Atsuyuki Okabe,et al.  Spatial Tessellations: Concepts and Applications of Voronoi Diagrams , 1992, Wiley Series in Probability and Mathematical Statistics.

[8]  Mansoor Davoodi Monfared,et al.  Multi-objective path planning in discrete space , 2013, Appl. Soft Comput..

[9]  Lily Rachmawati,et al.  Multiobjective Evolutionary Algorithm With Controllable Focus on the Knees of the Pareto Front , 2009, IEEE Transactions on Evolutionary Computation.

[10]  Atsuyuki Okabe,et al.  Spatial Tessellations: Concepts and Applications of Voronoi Diagrams, Second Edition , 2000, Wiley Series in Probability and Mathematical Statistics.

[11]  Faruk Polat,et al.  Limited-Damage A*: A path search algorithm that considers damage as a feasibility criterion , 2011, Knowl. Based Syst..

[12]  Kalyanmoy Deb,et al.  Multi-objective optimal path planning using elitist non-dominated sorting genetic algorithms , 2012, Soft Computing.

[13]  Gary B. Lamont,et al.  Evolutionary Algorithms for Solving Multi-Objective Problems , 2002, Genetic Algorithms and Evolutionary Computation.

[14]  Joshua D. Knowles,et al.  Modes of Problem Solving with Multiple Objectives: Implications for Interpreting the Pareto Set and for Decision Making , 2008, Multiobjective Problem Solving from Nature.

[15]  Gang Chen,et al.  Preserving and Exploiting Genetic Diversity in Evolutionary Programming Algorithms , 2009, IEEE Transactions on Evolutionary Computation.

[16]  Gary B. Lamont,et al.  Evolutionary algorithms for solving multi-objective problems, Second Edition , 2007, Genetic and evolutionary computation series.