Transcript PPT
Fusion of Evolutionary Algorithms and Multi-Neuron Heuristic Search for Robotic Path Planning Rahul Kala, Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior http://students.iiitm.ac.in/~ipg_200545/ [email protected], [email protected] Publication of paper:R. Kala, A. Shukla, R. Tiwari (2009) Fusion of Evolutionary Algorithms and MultiNeuron Heuristic Search for Robotic Path Planning, Proceedings of the 2009 IEEE World Congress on Nature & Biologically Inspired Computing, Coimbatote, India, pp. 684 – 689. Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation The Problem Inputs ◦ Robotic Map ◦ Location of Obstacles ◦ Static and Dynamic Output ◦ Path P such that no collision occurs Constraints ◦ Time Constraints ◦ Dimensionality of Map ◦ Static and Dynamic Environment Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation MNHS Algorithm In all we take α neurons. We have a list of heuristic costs each corresponding to node seen but waiting to be processed. We divide the cost range into α ranges equally among them. Each of these neurons is given a particular range. Each neuron selects the minimum most element of the cost range allotted to it and starts searching. At one step of each neuron processes its element by searching and expanding the element. This process is repeated. Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation Path Generation Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation Evolutionary Algorithm Individual Representation Conversion to graph Evolutionary Operators Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation Individual Representation Set of points P <P0, P1, P2, P3, …. Pn, Pn+1>. P0 is the source and Pn+1 is the goal. X axis is the straight line joining the source and the goal. The Y axis is perpendicular All points represented by the individual are sorted by their x axis values. Y Source P0 (0,0) Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior α P1 (x,y) P2 P3 P4 Goal X X’ P5 (m’,n’) MTech Thesis Fourth Evaluation Genetic Operators Crossover Mutation Rank based fitness scaling Stochastic uniform selection Diversity Preservation Selection Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation Fusion MNHS reduces number of points for EA EA gives iterative approach Select Prospective Best points by EA and Build actual solution by MNHS Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation Results Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation Publications Kala, Rahul, Shukla, Anupam, & Tiwari, Ritu (2010) Robotic Path Planning using Evolutionary Momentum based Exploration, Journal of Experimental and Theoretical Artificial Intelligence, Taylor and Francis Publishers (Impact Factor: 0.341) Kala, Rahul, Shukla, Anupam, & Tiwari, Ritu (2010) Fusion of probabilistic A* algorithm and fuzzy inference system for robotic path planning, Artificial Intelligence Review, Springer Publishers, Vol. 33, No. 4, pp 275-306 (Impact Factor: 0.119) Kala, Rahul, Shukla, Anupam, & Tiwari, Ritu (2009) Fusion of Evolutionary Algorithms and Multi-Neuron Heuristic Search for Robotic Path Planning, Proceedings of the IEEE 2009 World Congress on Nature & Biologically Inspired Computing, NABIC '09, pp 684 - 689, Coimbatore, India Kala, Rahul, Shukla, Anupam, & Tiwari, Ritu (2009), Robotic Path Planning using Multi Neuron Heuristic Search, Proceedings of the ACM 2009 International Conference on Computer Sciences and Convergence Information Technology, ICCIT 2009, pp 1318-1323, Seoul, Korea Kala, Rahul, Shukla, Anupam, Tiwari, Ritu, Roongta, Sourabh & Janghel, RR (2009) Mobile Robot Navigation Control in Moving Obstacle Environment using Genetic Algorithm, Artificial Neural Networks and A* Algorithm, Proceedings of the IEEE World Congress on Computer Science and Information Engineering, CSIE 2009, pp 705-713, Los Angeles/Anaheim, USA Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation Thank You Soft Computing and Expert System Laboratory Indian Institute of Information Technology and Management Gwalior MTech Thesis Fourth Evaluation