Intelligent neuro-controller for navigation of mobile robot

Abstract

This paper deals with the reactive control of an autonomous robot which move safely in a crowded real world unknown environment and to reach specified target by avoiding static as well as dynamic obstacle. The inputs to the proposed neurocontroller consist of left, right, and front obstacle distance to its locations and target angle between a robot and a specified target being acquired by an array of sensors. A four layer neural networks is used to design and develop the neurocontroller to solve the path and time optimization problem of mobile robots which deals the with cognitive tasks such as learning, adaptation, generalization and optimization. Back propagation method is used to trained the network. This paper analyzes the kinematical modeling of mobile robots as well as the design of control systems for the autonomous motion of the robot. The training of the nets and the control performances analysis have been done in a real experimental setup. The simulation results are compared with experimental results which are satisfactory and shows a very good agreement.

A Generalized Neural Network Approach to Mobile Robot Navigation and Obstacle Avoidance

“…Our approach is inspired by the works done by Parhi and Singh [19][20][21] for neural network robot navigation. Parhi and Singh introduced a real-time obstacle avoidance approach, solving each of the target-seeking, obstacle-avoidance, and wall-following tasks with separate neural networks.…”

“…In proposed an approach for obstacle avoidance by employing a neural network model of classical and operant conditioning based on Grossberg's conditioning circuit [7,74]. Parhi and Singh introduced a real-time obstacle avoidance approach to solve each of the targetseeking, obstacle-avoidance, and wall-following tasks using separate neural networks [19][20][21]. In their approach, based on certain criteria one of the networks is selected at each time step to control the mobile robot allowing it to move safely in a crowded realworld and unknown environment and to reach a specified target while avoiding static as well as dynamic obstacles.…”

Real Time Trajectory Tracking Controller based on Lyapunov Function for Mobile Robot

“…Mainly the trajectory tracking control algorithms can be classified into on of six categories [1]: (1) backstepping [2], [3]; (2) linearization [4]; (3) sliding mode [5]; (4) fuzzy systems [6], [7]; (5) neural networks [8]; and (6) neurofuzzy systems [9].…”

A New Intelligent Motion Planning for Mobile Robot Navigation using Multiple Adaptive Neuro-Fuzzy Inference System

“…There are many fuzzy logic techniques using various implementations or in combination with other techniques [10][11][12][13][14]. Mobile robot path planning based on neural network approaches presented by many researchers [15][16][17][18]. Among the intelligent techniques ANFIS is a hybrid model which combines the adaptability capability of artificial neural network and knowledge representation of fuzzy inference system [19].…”