Intelligent neuro-controller for navigation of mobile robot

International Journal of Computer and Electrical Engineering, 2014

In this paper, design of an intelligent autonomous vehicle is presented that can navigate in noisy and unknown environments without hitting the obstacles in its way. The vehicle is made intelligent with the help of two multilayer feed forward neural network controllers namely 'Hurdle Avoidance Controller' and 'Goal Reaching Controller' with back error propagation as training algorithm. Hurdle avoidance controller ensures collision free motion of mobile robot while goal reaching controller helps the mobile robot in reaching the destination. Both these controllers are trained offline with the data obtained during experimental run of the robot and implemented with low cost AT89C52 microcontrollers. The computational burden on microcontrollers is reduced by using piecewise linearly approximated version of tangent-sigmoid activation function of neurons. The vehicle with the proposed controllers is tested in outdoor complex environments and is found to reach the set targets successfully. I. INTRODUCTION Navigation is the ability of a mobile robot to reach the set targets by avoiding obstacles in its way. Thus essential behaviors for robot navigation are obstacle avoidance and goal reaching [1], [2]. Conventional control techniques can be used to build controllers for these behaviors; however, the environment uncertainty imposes a serious problem in developing the complete mathematical model of the system resulting in limited usability of these controllers. Thus some kind of intelligent controllers are required that can cope with the changing environment conditions. Amongst the various artificial intelligence techniques available in literature, neural networks offer promising solution to robot navigation problem because of their ability to learn complex non linear relationships between input sensor values and output control variables. This ability of neural networks has attracted many researchers across the globe in developing neural network based controllers for reactive navigation of mobile robots in indoor as well as outdoor environments. In [3], a collision free path between source and destination is constructed based on

Proceeding of the Electrical Engineering Computer Science and Informatics, 2017

Mobile robot are widely applied in various aspect of human life. The main issue of this type of robot is how to navigate safely to reach the goal or finish the assigned task when applied autonomously in dynamic and uncertain environment. The application of artificial intelligence, namely neural network, can provide a "brain" for the robot to navigate safely in completing the assigned task. By applying neural network, the complexity of mobile robot control can be reduced by choosing the right model of the system, either from mathematical modeling or directly taken from the input of sensory data information. In this study, we compare the presented methods of previous researches that applies neural network to mobile robot navigation. The comparison is started by considering the right mathematical model for the robot, getting the Jacobian matrix for online training, and giving the achieved input model to the designed neural network layers in order to get the estimated position of the robot. From this literature study, it is concluded that the consideration of both kinematics and dynamics modeling of the robot will result in better performance since the exact parameters of the system are known. Index Terms-Dynamics modeling; kinematics modeling; mobile robot navigation; neural network controller.

2015

This project presents a neural network approach to the motion control of an artificial mobile robot. The robot is required to move towards its goal in a cluttered environment and simultaneously avoiding collision with obstacles of any size and being randomly distributed. We have used feed-forward back propagation algorithm to control the robot motion. Our main focus is on the steering action of the robot. The algorithm takes input as angle to target, front obstacle distance, right obstacle distance and left obstacle distance. Sensors have been used for the purpose of getting the inputs on various obstacle distances. The network provides the angle through which the robot is to be steered to avoid obstacles. The steering is achieved by controlling the speed of motors and hence of wheels to whom they are attached to. The viability of the algorithm has been demonstrated through various simulations. The real-world experimental outcomes prove the efficacy of the algorithm to navigate the ...

Solid State Phenomena, 2013

When mobile robots are used among people, the best accepted motion related behavior is a human-like motion of the robot. Such behavior is difficult to obtain with commonly used finite state machine based planners, but can easily be evoked when human controls the robot. The paper presents the way of transforming such knowledge from human controller to reactive planner in the robot navigation module. Reactive planner is based on machine learning, neural networks in particular. The planner consists of two separate neural networks, one serving as predictor of dynamic obstacles behavior, second one serving as the reactive planner itself, producing desirable actions of the robot both in terms of velocity and direction. Planner was verified on real robot producing human-like behavior when used in real environment.

Neuro-fuzzy systems have been used for robot navigation applications because of their ability to exert human like expertise and to utilize acquired knowledge to develop autonomous navigation strategies. In this paper, neuro-fuzzy based system is proposed for reactive navigation of a mobile robot using behavior based control. The proposed algorithm uses discrete sampling based optimal training of neural network. With a view to ascertain the efficacy of proposed system; the proposed neuro-fuzzy system's performance is compared to that of neural and fuzzy based approaches. Simulation results along with detailed behavior analysis show effectiveness of our algorithm in all kind of obstacle environments.

Neural network based systems have been used in past years for robot navigation applications because of their ability to learn human expertise and to utilize this knowledge to develop autonomous navigation strategies. In this paper, neural based systems are developed for mobile robot reactive navigation. The proposed systems transform sensors' input to yield wheel velocities. Novel algorithm is proposed for optimal training of neural network. With a view to ascertain the efficacy of proposed system; developed neural system's performance is compared to other neural and fuzzy based approaches. Simulation results show effectiveness of proposed system in all kind of obstacle environments.

IFAC Proceedings Volumes, 1998

This paper describes a neural network model for the reactive navigation of a mobile robot. The system defines a series of reactive behaviors: stop, avoid , stroll , wall following, etc. depending on the information obtained from a set of proximity sensors distributed in the periphery of the robot. Reinforcing learning permits the adaptative navigation of the robot.

Since last decade, navigation of mobile robot has received considerable attention in the field of research due to its applications, where the involvement of human directly is difficult or dangerous. In this paper, we present the development of robust control algorithm for navigation of mobile robot using artificial intelligent technique (AIT). The ability of learning for neural network (an AIT) is used to develop a strong adaptive back stepping controller that does not requires the knowledge of the robot dynamic. Therefore, we combined the ANN and kinematic control technique to solve the localization problem for safe and smooth navigation at narrow corridors. To navigate robustly inside environment and reach the goal position safely; different types of sensors has been mounted on the robot body. ANN has been used to train the system for working environment. A Matlab simulation platform is used to validate the experimental result. Finally, the success of proposed control algorithm is verified through the simulation experiment, which shows its superior performance and disturbance rejection.

IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02, 2002

This article presents an artificial neural network (ANN) structure applied to control a mobile robot movement in dynamically changing environments (environments wirh mobile obstacles), The proposed structure is a backward neural one. So, ir is based on past andfihrre positions, and on a optimal pre-established parh. The past pasirions provide rhe ANN with memory of the mobile robot previous positions. On the other hand, rhe future positions provide rhe ANN with a goal, i.e., where the robot shouldgo. Basedon this information, the robot da nor lose ifs goal, even (f if has to avoid an obstacle. The results show the eflciency ofthe ANXin aform ofsimulations

2012

A new paradigm of intelligent navigation system for mobile robot has been enriched with some common features like: criteria for optimal performance and ways to optimize design, structure and control of robot. With the growing need for the deployment of intelligent and highly autonomous systems, it would be beneficial to flawlessly combine robust learning capabilities of artificial neural networks with a high level of knowledge interpretability provided by fuzzy-logic. Fuzzy-neural network is able to build comprehensive knowledge bases considering sensor-rich system with real time constraints by adaptive learning, rule extraction and insertion, and neural/fuzzy reasoning. This technique is simulated and also compared with other simulation studies by previous researcher . The training for back propagation algorithm and its navigational performances analysis has been done in real experimental setup. As experimental result matches well with the simulation result, the realism of method i...