Path planning optimization of six-degree-of-freedom robotic manipulators using evolutionary algorithms

Sandi Baressi Šegota,Milan Saga,Ivan Lorencin,Zlatan Car,Nikola Anđelić

doi:10.1177/1729881420908076

Sandi Baressi Šegota, Milan Saga + Show 3 more

Open Access

https://doi.org/10.1177/1729881420908076

Copy DOI

Abstract

Lowering joint torques of a robotic manipulator enables lowering the energy it uses as well as increase in the longevity of the robotic manipulator. This article proposes the use of evolutionary computation algorithms for optimizing the paths of the robotic manipulator with the goal of lowering the joint torques. The robotic manipulator used for optimization is modelled after a realistic six-degree-of-freedom robotic manipulator. Two cases are observed and these are a single robotic manipulator carrying a weight in a point-to-point trajectory and two robotic manipulators cooperating and moving the same weight along a calculated point-to-point trajectory. The article describes the process used for determining the kinematic properties using Denavit–Hartenberg method and the dynamic equations of the robotic manipulator using Lagrange–Euler and Newton–Euler algorithms. Then, the description of used artificial intelligence optimization algorithms is given – genetic algorithm using random and average recombination, simulated annealing using linear and geometric cooling strategy and differential evolution. The methods are compared and the results show that the genetic algorithm provides best results in regard to torque minimization, with differential evolution also providing comparatively good results and simulated annealing giving the comparatively weakest results while providing smoother torque curves.

Highlights

To achieve movement, the torque of robot manipulators actuator needs to be higher than the inertial torsion of the joint the actuator is moving.[1,2] The movement requires use of energy directly proportional to the actuator torque
The curves provided by the genetic algorithm (GA) have a tendency to show sudden changes in joint torque, which can negatively impact the durability of the robotic manipulator, while the ones provided by the differential evolution (DE) have a tendency to have one of the joints of the robotic manipulator have a high torque, with very low joint torques on the other joints
The generated results are not optimal in regard to the smoothness of the curves, where simulated annealing (SA) shows the best results in comparison with other algorithms used, and stress placed on second joint of robotic manipulator(s)

Summary

Introduction

The torque of robot manipulators actuator (e.g. an electrical motor) needs to be higher than the inertial torsion of the joint the actuator is moving.[1,2] The movement requires use of energy directly proportional to the actuator torque. Minimizing the actuator torque, which is dependent on the joint trajectory, will mean that the movement of the robotic manipulator requires less energy, as well as prolong the work life of the robotic manipulator.[3]. It is possible to define the problem of joint torque optimization in a way that makes it possible to use artificial intelligence (AI) methods, namely the evolutionary. Computing optimization methods, in an attempt to achieve the lower amounts of actuator torque.[4,5,6]

Methods

Discussion

Conclusion