Adaptive impedance control for unknown environment

Abstract

This report presents a simulation, design, build and evaluation of a 2 degree of freedom robotic arm guided by an adaptive impedance control algorithm governed by a neural network. This neural network is trained and evaluated by an adaptive genetic algorithm, the implementation of the robot arm consists of a 3D printed interconnected body controlled by Python and Arduino equipped with high torque servo motors. Interaction force sensors are installed around the end effector of the robotic arm as feedback to the neural network to exert manipulative decisions.