This paper presents a novel inverse kinematics solution for robotic arm based on artificial neural network (ANN) architecture. The motion of robotic arm is controlled by the kinematics of ANN. A new artificial neural network approach for inverse kinematics is proposed. The novelty of the proposed ANN is the inclusion of the feedback of current joint angles configuration of robotic arm as well as the desired position and orientation in the input pattern of neural network, while the traditional ANN has only the desired position and orientation of the end effector in the input pattern of neural network. In this paper, a six DOF Denso robotic arm with a gripper is controlled by ANN. The comprehensive experimental results proved the applicability and the efficiency of the proposed approach in robotic motion control. The inclusion of current configuration of joint angles in ANN significantly increased the accuracy of ANN estimation of the joint angles output. The new controller design has advantages over the existing techniques for minimizing the position error in unconventional tasks and increasing the accuracy of ANN in estimation of robot's joint angles.

Tungsten inert gas arc welding-based shaped metal deposition is a novel additive manufacturing technology which can be used for fabricating solid dense parts by melting a cold wire on a substrate in a layer-by-layer manner via continuous DC arc heat. The shaped metal deposition method would be an alternative way to traditional manufacturing methods, especially for complex featured and large-scale solid parts manufacturing, and it is particularly used for aerospace structural components, manufacturing, and repairing of die/molds and middle-sized dense parts. This article presents the designing, constructing, and controlling of an additive manufacturing system using tungsten inert gas plus wire-based shaped metal deposition method. The aim of this work is to design and develop tungsten inert gas plus wire-based shaped metal deposition system to be used for fabricating different components directly from computer-aided design data with minimum time consumed in programming and less boring task compared to conventional robotic systems. So, this article covers the important design steps from computer-aided design data to the final deposited part. The developed additive system is capable of producing near-net-shaped components of sizes not exceeding 400 mm in three-dimensional directly from computer-aided design drawing. The results showed that the developed system succeeded to produce near-netshaped parts for various features of SS308LSi components. Additionally, workshop tests have been conducted in order to verify the capability and reliability of the developed additive manufacturing system. The developed system is also capable of reducing the buy-to-fly ratio from 5 to 2 by reducing waste material from 1717 to 268 g for the sample components.

Human-robot interaction HRI is one of the most important research areas in robotics. A novel approach for HRI on a robotic arm is proposed by using online teaching to eliminate the effect of tool inertia. The position error is reduced in repeated motion. A multi-axis F/T sensor is attached to Denso robotic arm to measure six components of force and torque. A new controller structure is introduced by modifying the virtual spring control with tool inertia effect compensation. The human hand force and torque are transformed to the desired position/orientation (P/O) through the instantaneous matching between the direct human guidance and the robot response. The motions according to the experimental results have been compared with different teaching control variables. The results are shown significant improvement in teaching performance. The repeated motion errors are obviously reduced.