Multi-objective mobile robot path planning problem through learnable evolution model

ABSTRACT A new multi-objective non-Darwinian-type evolutionary computation approach based on learnable evolution model (LEM) is proposed for solving the robot path planning problem. The multi-objective property of this approach is governed by a robust strength Pareto evolutionary algorithm (SPEA) incorporated in the LEM algorithm presented here. Learnable evolution model includes a machine learning method, like the decision trees, that can detect the right directions of the evolution and leads to large improvements in the fitness of the individuals. Several new refiner operators are proposed to improve the objectives of the individuals in the evolutionary process. These objectives are: the path length, the path safety and the path smoothness. A modified integer coding path representation scheme is proposed where the edge-fixing and top-row fixing procedures are performed implicitly. This proposed robot path planning problem solving approach is assessed on eight realistic scenarios in order to verify the performance thereof. Computer simulations reveal that this proposed approach exhibits much higher hypervolume and set coverage in comparison with other similar approaches. The experimental results confirm that the proposed approach performs in the workspaces with a dense set of obstacles in a significant manner.

[1]  Kalyanmoy Deb,et al.  Multi-objective path planning using spline representation , 2011, 2011 IEEE International Conference on Robotics and Biomimetics.

[2]  Shuzhi Sam Ge,et al.  Dynamic Motion Planning for Mobile Robots Using Potential Field Method , 2002, Auton. Robots.

[3]  Jianhua Zhang,et al.  Robot path planning in uncertain environment using multi-objective particle swarm optimization , 2013, Neurocomputing.

[4]  Rafael Murrieta-Cid,et al.  A Sampling-Based Motion Planning Approach to Maintain Visibility of Unpredictable Targets , 2005, Auton. Robots.

[5]  K. S. Al-Sultan,et al.  A new potential field-based algorithm for path planning , 1996, J. Intell. Robotic Syst..

[6]  Corina Cimpanu,et al.  Pareto genetic path planning hybridized with multi-objective Dijkstra's algorithm , 2014, 2014 18th International Conference on System Theory, Control and Computing (ICSTCC).

[7]  Tiong Sieh Kiong,et al.  Cognitive Map approach for mobility path optimization using multiple objectives genetic algorithm , 2000, 2009 4th International Conference on Autonomous Robots and Agents.

[8]  Laetitia Vermeulen-Jourdan,et al.  Preliminary Investigation of the 'Learnable Evolution Model' for Faster/Better Multiobjective Water Systems Design , 2005, EMO.

[9]  Ryszard S. Michalski,et al.  Learning and Evolution: An Introduction to Non-darwinian Evolutionary Computation , 2000, ISMIS.

[10]  Dayal R. Parhi,et al.  Optimal path planning for a mobile robot using cuckoo search algorithm , 2016, J. Exp. Theor. Artif. Intell..

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

[12]  Marco Laumanns,et al.  SPEA2: Improving the strength pareto evolutionary algorithm , 2001 .

[13]  Lothar Thiele,et al.  An evolutionary algorithm for multiobjective optimization: the strength Pareto approach , 1998 .

[14]  Howie Choset,et al.  Sensor based motion planning: the hierarchical generalized Voronoi graph , 1996 .

[15]  Quanmin Zhu,et al.  Complex System Modelling and Control Through Intelligent Soft Computations , 2016, Studies in Fuzziness and Soft Computing.

[16]  D. Sheskin.  Handbook of Parametric and Nonparametric Statistical Procedures: Third Edition , 2000 .

[17]  Lothar Thiele,et al.  Multiobjective Optimization Using Evolutionary Algorithms - A Comparative Case Study , 1998, PPSN.

[18]  Stan C. A. M. Gielen,et al.  Neural Network Dynamics for Path Planning and Obstacle Avoidance , 1995, Neural Networks.

[19]  D. K. Pratihar,et al.  FUZZY-GENETIC ALGORITHMS AND TIME-OPTIMAL OBSTACLE-FREE PATH GENERATION FOR MOBILE ROBOTS , 1999 .

[20]  Zexuan Zhu,et al.  Global Path Planning of Wheeled Robots Using a Multi-Objective Memetic Algorithm , 2013, IDEAL.

[21]  Mario Cortina-Borja,et al.  Handbook of Parametric and Nonparametric Statistical Procedures, 5th edn , 2012 .

[22]  Abdolreza Mirzaei,et al.  A New Automated Design Method Based on Machine Learning for CMOS Analog Circuits , 2016 .

[23]  Tomás Lozano-Pérez,et al.  An algorithm for planning collision-free paths among polyhedral obstacles , 1979, CACM.

[24]  Hongwei Mo,et al.  Constrained Multi-objective Biogeography Optimization Algorithm for Robot Path Planning , 2013, ICSI.

[25]  Maliha S. Nash,et al.  Handbook of Parametric and Nonparametric Statistical Procedures , 2001, Technometrics.

[26]  Corina Cimpanu,et al.  Multiobjective hybrid evolutionary path planning with adaptive pareto ranking of variable-length chromosomes , 2014, 2014 IEEE 12th International Symposium on Applied Machine Intelligence and Informatics (SAMI).

[27]  Ellips Masehian,et al.  Multi-objective robot motion planning using a particle swarm optimization model , 2010, Journal of Zhejiang University SCIENCE C.

[28]  Behzad Moradi.  An Intelligent Evolutionary Computation Approach for Solving the Shortest Path Problem , 2018, J. Multiple Valued Log. Soft Comput..

[29]  Tomoyuki Hiroyasu,et al.  SPEA2+: Improving the Performance of the Strength Pareto Evolutionary Algorithm 2 , 2004, PPSN.

[30]  Nafiseh Sedaghat,et al.  Mobile robot path planning by new structured multi-objective genetic algorithm , 2011, 2011 International Conference of Soft Computing and Pattern Recognition (SoCPaR).

[31]  Miguel A. Vega-Rodríguez,et al.  Solving the multi-objective path planning problem in mobile robotics with a firefly-based approach , 2015, Soft Computing.

[32]  Dalong Wang,et al.  Ranked Pareto Particle Swarm Optimization for Mobile Robot Motion Planning , 2009 .

[33]  Otthein Herzog,et al.  Machine learning in agent-based stochastic simulation: Inferential theory and evaluation in transportation logistics , 2012, Comput. Math. Appl..

[34]  Jing-Sin Liu,et al.  High-quality path planning for autonomous mobile robots with η3-splines and parallel genetic algorithms , 2009, 2008 IEEE International Conference on Robotics and Biomimetics.

[35]  Max Q.-H. Meng,et al.  Real-time Collision-free Path Planning of Robot Manipulators using Neural Network Approaches , 2000, Auton. Robots.

[36]  Miguel A. Vega-Rodríguez,et al.  MOSFLA-MRPP: Multi-Objective Shuffled Frog-Leaping Algorithm applied to Mobile Robot Path Planning , 2015, Eng. Appl. Artif. Intell..

[37]  Kenneth A. Kaufman,et al.  Intelligent evolutionary design: A new approach to optimizing complex engineering systems and its application to designing heat exchangers , 2006, Int. J. Intell. Syst..

[38]  Janusz Wojtusiak,et al.  The LEM3 System for Multitype Evolutionary Optimization , 2009, Comput. Informatics.

[39]  Lothar Thiele,et al.  Multiobjective evolutionary algorithms: a comparative case study and the strength Pareto approach , 1999, IEEE Trans. Evol. Comput..

[40]  Gouda I. Salama,et al.  A Generic Feature Extraction Model using Learnable Evolution Models (LEM+ID3) , 2013 .

[41]  Yan-tao Tian,et al.  Multi-objective path planning for unrestricted mobile , 2009, 2009 IEEE International Conference on Automation and Logistics.

[42]  Piotr A. Domanski,et al.  An Optimized Design of Finned-Tube Evaporators Using the Learnable Evolution Model , 2004 .

[43]  H. Van Dyke Parunak,et al.  Evolving adaptive pheromone path planning mechanisms , 2002, AAMAS '02.

[44]  Jing-Sin Liu,et al.  Generating minimax-curvature and shorter η3-spline path using multi-objective variable-length genetic algorithm , 2010, 2010 International Conference on Networking, Sensing and Control (ICNSC).

[45]  Ryszard S. Michalski,et al.  LEARNABLE EVOLUTION MODEL: Evolutionary Processes Guided by Machine Learning , 2004, Machine Learning.

[46]  Miguel A. Vega-Rodríguez,et al.  Applying the MOVNS (multi-objective variable neighborhood search) algorithm to solve the path planning problem in mobile robotics , 2016, Expert Syst. Appl..

[47]  Shiyin Qin,et al.  Multi-objective Path Planning for Space Exploration Robot Based on Chaos Immune Particle Swarm Optimization Algorithm , 2011, AICI.

[48]  Jianhua Zhang,et al.  Multi-objective Particle Swarm Optimization for Robot Path Planning in Environment with Danger Sources , 2011, J. Comput..

[49]  S. Geetha,et al.  Multi objective mobile robot path planning based on hybrid algorithm , 2011, 2011 3rd International Conference on Electronics Computer Technology.

[50]  Marilena Vendittelli,et al.  Fuzzy maps: A new tool for mobile robot perception and planning , 1997, J. Field Robotics.

[51]  Saeed Farzi.  The design of self-organizing evolved polynomial neural networks based on learnable evolution model 3 , 2012, Int. Arab J. Inf. Technol..

[52]  Dunwei Gong,et al.  Robot path planning in an environment with many terrains based on interval multi-objective PSO , 2013, 2013 IEEE Congress on Evolutionary Computation.

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

[54]  Hu Jun,et al.  Multi-objective Mobile Robot Path Planning Based on Improved Genetic Algorithm , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[55]  Hesam Omranpour,et al.  Solving robot path planning problem by using a new elitist multi-objective IWD algorithm based on coefficient of variation , 2015, Soft Computing.

[56]  Ellips Masehian,et al.  A multi-objective PSO-based algorithm for robot path planning , 2010, 2010 IEEE International Conference on Industrial Technology.

[57]  Ellips Masehian,et al.  Multi-Objective PSO- and NPSO-based Algorithms for Robot Path Planning , 2010 .

[58]  Otthein Herzog,et al.  The learnable evolution model in agent-based delivery optimization , 2012, Memetic Computing.