Integrating artificial immune systems and multi-layer perceptron-biogeography-based optimization for enhanced inverse kinematics in robotic arm

Abstract

Determining required joint angles to achieve a desired position in a manipulator’s arm is a complicated problem without simple analytical solutions. This paper researches several computational methods based on artificial intelligence (AI) for calculating the joint positions of the 6-DOF robotic arm. We can extrapolate relevance, for example, to the crucial role that robotic manipulator arms play in industrial and medical applications, where enhanced precision and movement efficiency may sharply boost performance and expand applicability. Here, we investigate the effectiveness of methods, such as the artificial immune system (AIS) and multi-layer perceptron-biogeography-based optimization (MLP-BBO). Those AI-driven methods have been applied to determine joint angles for reaching desired positions through simulations for the robotic arm. The results show that the AIS and MLP-BBO approach can handle the intrinsic complexities of the task, thus testifying to the practicability and dependability of these two methods in this application. From the findings in the study, it was indicated that AI-driven techniques can effectively answer the complex problem of the robotic manipulator arm in finding joint angles.