A lot of researches studies robot arms and the ability of controlling it to track targets
which depends on the type of motors used, DC motors or servo motors. In addition to
response time that DC and motor can give as a physical structure.
Robots
consists of number of junctions built of solid materials (robot arms(
connected together by motors and the total structure lets the robot to move, these robots
can be used in places that humans cannot act inside it or in places which we need a lot of
repeated actions.
This search aimes to study the robot arm movement by controlling the motors and its
response to a drawn line using a PID controller to achive the most accuracy by using the
distrubushion constants of the camera lens which used by the robot to see. All the cameras
need to be calibrated and the constants used to move the robot in X,Y,Z.
This research is centered on design of a serial industrial manipulator with 4 degrees
of freedom(4-DOF) in order to manipulation on production linesand packaging tasks of
small pieces, it is characterized by flexibility and the possibility of compa
tibility with other
robots in the work area.
Research explains the Mechanical description of the manipulator and the study of the
inverse kinematic and direct kinematics in addition to the study of the path of the
manipulator.Manipulator electric engines are servo motors (DC Servo motor). The design
of the electronic driving system of the robot depends on the Arduino Board(Arduino
UNO).
The application interface, which was built within the software (Microsoft Visual
Studio), allows to easily control the manipulator.Where the robot three-dimensional model
(3D) simulates the movement of the robot at work.
In the latter part of the research we discussed practical prototype test results of the
robotic manipulator that we have designed and implemented.
This paper presents the possibility of replacing the mathematical
optimizer in the Model Predictive Control Algorithm (MPC) with a
Feedforward Neural Network Optimizer (FNNO). The optimizer
trained offline to reduce the cost function. This maintai
n the system
model of the system, which is essential in MPC to get accepted
accuracy. we solve optimization problem faster than the algorithms
of traditional optimization, which we built, based on digital
computing.
