Immune network simulation of reactive control of a robot arm manipulator

The field of robotics is an important application area for artificial immune systems. We can make use of the immune system properties to control and to identify complex or even unknown systems. Much research has been done in studying the dynamics of the autonomous mobile robot with particular interest in obstacle avoidance and/or trajectory following. Our research is concerned with robot arm manipulator trajectory planning which is based on sensor-based reactive control. In order to control a robot, it must be kinematically analyzed and the result of this analysis entered into the controller of the robot. Kinematics analysis starts with calculating the forward kinematics solution (FKS). The FKS is a prerequisite for obtaining the inverse kinematics solution (IKS) that is entered into the robot controller and forms the basis of the remote control of the robot. While calculating the IKS, there are many possible poses that links of that manipulator can take to reach the designated point in the robot space. An important question, when a manipulator is dealing with a real dynamically changing environment, is what is the best pose that will get to the target point in the shortest time. We use one of the features of the immune system to build a network of manipulator joints that will interact together to reach the desired target point within the shortest time. The use of an artificial immune network simulator in this research is to play the role of prediction for robot behavior in the new environment.