Artificial neural networks in robotic applications

Abstract

There are a number of problems that their analytical solutions are difficult to obtain using conventional techniques in robotics. This paper examines the use of Artificial Neural Networks (ANNs) as a new technique to solve such problems in the field of robotics. This paper presents an overview on ANNs applications to robot kinematics, dynamics, control, trajectory and task planning, and sensing. Moreover, the advantages and disadvantages of using and implementing ANNs to the robotic problems are outlined.