Volume IV, Issue IX, September 2015 IJLTEMAS ISSN 2278 - 2540 www.ijltemas.in Page 21 Mobile Robot Localization Using Multi-Objective Optimization Sabita Mali Department of Electronics and communication Engg., ITER,SOA University, Bhubaneswar, Orissa Abstract - The Swarm Intelligence-based Reinforcement Learning (SWIRL) method is proposed in this paper to efficiently generate Artificial Neural Network(ANN) based solutions to various problems. An aritificial neural networks learning method for mobile robot localization, which combines the two popular swarm inspired methods in computational intelligence areas: Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO) to train the ANN models. The most used artificial neural networks(ANNs) models is the well-known multi-layer perceptron (MLP). Training neural networks is a complex task for reinforcement learning methods .The training process of MLPs for pattern classification problems consists of two tasks , the first one is the selection of an appropriate architecture for the problem , and the second is the adjustment of the connection weights of the network. Recently artificial neural networks based methods are applied to robotic systems. An ANN was trained to estimate a robot’s position relative to a particular local object and to correct the pose estimates from odometry using ultrasonic sensors. Keywords: ANN, ACO,PSO,MLP,SWIRL I. INTRODUCTION wo well-known approaches among many successful bio-inspired swarm intelligence based computational paradigms are known as Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO). The ACO algorithm is essentially a system that simulates the natural behavior of ants, including mechanisms of cooperation and adaptation. The involved agents are steered toward local and global optimization through a mechanism of feedback of simulated pheromones and pheromone intensity processing. Particle Swarm Optimization(PSO) is a biologically-inspired algorithm motivated by a social analogy, such as flocking, herding, and schooling behavior in animal populations. Both algorithms have been applied to solve problems in various areas, such as clustering, data mining, dynamic task allocation, and optimization. The basic idea of the SWIRL method is that ACO is used to optimize the topology structure of the ANNs, while PSO is used to adjust the ANN connection weights within a given topology structure. This is designed to split the problem such that ACO and PSO can both operate in the environment they are most suited for. ACO is ideally applied to finding paths through graphs. One can treat the ANN’s neurons as vertices and its connections as directed edges, thereby transforming the topology design into a graph problem. PSO is best used to find the global maximum or minimum in a real- valued search space. Considering each connection weight plus one associated fitness score as orthogonal dimensions in a hyperspace, each possible weight configuration is merely a point in that hyperspace. Finding the optimal weights is thus reduced to finding the global maximum of the fitness function in that hyperspace. II. OVERVIEW OF NEURAL NETWORK IN ROBOTICS An Artificial Neural Network (ANN) is an information processing paradigm which is composed of a large number of highly interconnected processing elements (neurons) and the weighted connections between them which is shown in fig 1. Learning in biological systems involve adjustments to the synaptic connections that exist between the neurons. Fig. 1 Diagram of an Artificial Neural Network An individual neuron cannot accomplish much, but the cumulative effect of many neurons connected together is effectively unlimited in complexity. A multilayer perceptron is a feed forward neural network with one or more hidden layers . The network consists of an input layer of source neurons ,at least one middle or hidden layer of computational neurons, and an output layer of computational neurons. A hidden layer “hides” it’s desired output .Neurons in the hidden layer can not be observed through the input/output behavior of the network We report on the objective of the motion planning problem well known in robotics. Given an object with an initial location and orientation, a goal location and orientation, and a set of obstacles located in workspace, the problem is to find a continuous path from the initial position to the goal position, which avoids collisions with obstacles along the way. In other words, the motion planning problem is divided into two sub-problems, called ‘Findspace’ and ‘Findpath’ problem. The findspace problem is used in construction the configuration space of a given object and some obstacles. The findpath problem T