Abstract
This study suggests an adaptive Artificial Neural Network (ANN) controller that based on Stochastic Fractal Search algorithm (SFS), the purpose of the Adaptive Neural Controller (ANC) is to track a proposed velocities and path trajectory with the minimum required error, in the presence of mobile robot parameters time variation and dynamical system model uncertainties. The proposed ANC will consist of two sub-neural controllers; the Kinematic Neural feedback Controller (KNC) and the Dynamic Neural feedback Controller (DNC). The external feedback kinematic neural controller is responsible for generating velocity tracking signals that track the mobile robot linear and angular velocities depending on the robot posture error and the desired velocities, while the internal dynamic neural controller is used to enhance the mobile robot against parameters uncertainty, parameters time variation and disturbance noise. The stochastic fractal search algorithm is a Metaheuristic Optimization Algorithm (MOA) that has been used to optimize the Neural Networks (NNs) weight connections to has the behavior of an adaptive nonlinear trajectory tracking controller of a differential drive wheeled mobile robot. The proposed controller has the capability to prepare an appropriate dynamic control left and right torque signals to drive various mobile robot platforms using the same offline optimized weight connections. Metaheuristic optimization algorithms have been used due to theirs unique characteristics especially theirs free of derivative, ability to optimize discretely and continuous nonlinear functions and their ability to get rid of local minimum solution trapping.
Highlights
Since the first launch of the Artificial Neural Networks (ANNs) and they have been used in many life fields and applications such as; image and signal processing (Lee and Kipke, 2006), systems identification (Kim et al, 1994), robotic control (De Sousa Junior and Hemerly, 2000), classification and clustering of data pattern sets
This study suggests an Adaptive Neural Controller (ANC), that's trained offline using a Metaheuristic Optimization Algorithms (MOA), called Stochastic Fractal Search algorithm (SFS) (Salimi, 2015) that is motivated by the development of regular phenomenon, inspired from the fractal mathematical idea and from the diffusion feature that seen often in random
Statistical procedure, all agents are ranked with respect to the fitness of the agents, these agents will be Adaptive neural controller has been proposed by given a probability value that follows a simple this study to track a desired designed trajectory, in distribution as shown in Eq (4): which the NN has been trained using a recently proposed MOA called SFS algorithm due to its free derivative, faster convergence and ability to escape local minima solution
Summary
Since the first launch of the Artificial Neural Networks (ANNs) and they have been used in many life fields and applications such as; image and signal processing (Lee and Kipke, 2006), systems identification (Kim et al, 1994), robotic control (De Sousa Junior and Hemerly, 2000), classification and clustering of data pattern sets. Many papers have been made to develop the performance of the back propagation algorithm, while other have just left this concept and migrate to other types of algorithms that called Metaheuristic Optimization Algorithms (MOA) (Siddique and Tokhi, 2001; Rakitianskaia and Engelbrecht, 2009; Bai and Xiong, 2009) especially in the training phase of the NNs. The neural based controllers of the robotic systems have been gained a great significance in the few recent years. The neural based controllers of the robotic systems have been gained a great significance in the few recent years These networks were recommended for their learning ability, intelligent, adaptive behavior and their high performance.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Research Journal of Applied Sciences, Engineering and Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
