A full freedom pose measurement method for industrial robot based on reinforcement learning algorithm.

In this current era, the field of robotics has made much advancement and has also produced novelties than any other advanced research areas. The usage of robots has become an imperative part of the defense-oriented applications. The missions which are difficult to be performed by human beings can certainly be accomplished by the robots nowadays. The most crucial part for an industrial- and defense-based robot is to perform pose movements accurately for optimal usage of robotics as a replacement of human beings. This paper proposes a comprehensive introduction to the proposed hybrid approach PSO–RL which uses reinforcement learning (RL) and Particle swarm optimization (PSO). It summarizes the usage of proposed PSO-RL for pose measurement of robots in defense and industrial manufacturing systems. The hybrid PSO–RL is a promising technique for measuring poses in robots with accuracy and for optimizing obstacle avoidance error. In this paper, robot's core movements are analyzed; speed of movements is given importance, and an attempt is made to provide more accurate moves with high precision. In order to optimize the efficiency of robotic operations, a full freedom pose measurement method based on PSO–RL is proposed. By using the characteristics of two-wheel independent driving industrial robot, the performance of the robot in three moving modes is evaluated. The experimental results show that the proposed PSO-RL method has the advantages of high accuracy, high measurement efficiency, high success rate of grabbing and avoiding obstacles. It outperforms the existing methods such as least square method and micro-displacement cyclic correction method with respect to maximum error, RMSE score and time complexity. [ABSTRACT FROM AUTHOR]