Andere Kunden interessierten sich auch für
![Kinematic Modeling Methods]( "Kinematic Modeling Methods")
Kinematic Modeling Methods38,99 €![Identification and Observer Adaptive Schemes Based on Neural Networks]( "Identification and Observer Adaptive Schemes Based on Neural Networks")
Identification and Observer Adaptive Schemes Based on Neural Networks32,99 €![Nelder Mead Trained Neural Networks For Short Term Load Forecasting]( "Nelder Mead Trained Neural Networks For Short Term Load Forecasting")
Nelder Mead Trained Neural Networks For Short Term Load Forecasting32,99 €![Artificial Neural Networks (ANNs) and GIS for flood forecasting]( "Artificial Neural Networks (ANNs) and GIS for flood forecasting")
Artificial Neural Networks (ANNs) and GIS for flood forecasting46,99 €![Clustering based fuzzy controller for speed control of DC motor]( "Clustering based fuzzy controller for speed control of DC motor")
Clustering based fuzzy controller for speed control of DC motor26,99 €![Passivity Based Modeling and Control of Continuous Biological Reactors]( "Passivity Based Modeling and Control of Continuous Biological Reactors")
Passivity Based Modeling and Control of Continuous Biological Reactors46,99 €![Project Management and Artificial Neural Networks]( "Project Management and Artificial Neural Networks")
Project Management and Artificial Neural Networks32,99 €
The applications of mobile robots have grown significantly during the last few years due to the fast development in sensors and microprocessors systems. These applications include material handling, hospital services, military applications ... etc. The need for a precise motion control becomes very crucial in order to support such applications. The adaptive motion control for mobile robot is one of the important areas of research. The design of an adaptive kinematic controller for a nonholonomic differential drive mobile robot based on neural network topology is considered in this work, and work is divided into three stages. Firstly, to identify the inverse kinematics behavior of the differential drive mobile robot system, the Multi-Layer Perceptron neural network has been used. The second stage is the simulation test to check the robustness of the controller. The final stage is the practical work. A National Instrument differential drive mobile robot platform has been used whichis perfectly compatible with the LabVIEW2011 software. The controller is implemented in LabVIEW2011 and then deployed to the mobile robot kit through a wireless communication.