Optimization of Energy in Robotic ARM Using GA

Abstract

This presentation proposes genetic algorithm (GA) to optimize the point-to-point trajectory planning for a 3-link robot arm. The objective function for the proposed GA is to minimizing traveling time and space, while not exceeding a maximum pre-defined torque, without collision with any obstacle in the robot workspace. Fourth and fifth polynomials are used to describe the segments that connect initial, intermediate, and final point at joint-space. Direct kinematics has been used for avoiding the singular configurations of the robot arm. The algorithm finds the shortest path for the end effector. This is done by choosing two points one initial point and final point in X-Y coordinate. Now, we find the minimum path for travelling of the end factor, and the distance between them. All the distance covered by the end effector is divided in ten equal parts. Due to which, the error is minimized and the accuracy is increased due to divide ten equal parts. Now by using GA for ten equal parts find out the suitable angle using inverse kinematic. The GA is applied for all the intermediate points between the initial and final point. Since the GA is used for all the ten points hence the accuracy is increased. Now, this problem is formulated by the equal distance travel by the robot hand with reference to previous position. The objective function is to minimize the energy consumed by each motor using GA. We assume that the first angle moved is very small than the second & the second angle moved is less than the third one. This selection was due to the reason that for the first motor the power requirement is greatest, lesser for the second motor and least for the third motor, because the load associated with the motors is decreasing respectively. Above results have been compared with manual movements of robotic arm. Results show that after Using GA, for the same set of location. The energy consumed is lesser than in manual control of robotic arm.