Learning to Move an Object by the Humanoid Robots by Using Deep Reinforcement Learning

Abstract

This paper proposes an algorithm for learning to move the desired object by humanoid robots. In this algorithm, the semantic segmentation algorithm and Deep Reinforcement Learning (DRL) algorithms are combined. The semantic segmentation algorithm is used to detect and recognize the object be moved. DRL algorithms are used at the walking and grasping steps. Deep Q Network (DQN) is used to walk towards the target object by means of the previously defined actions at the gate manager and the different head positions of the robot. Deep Deterministic Policy Gradient (DDPG) network is used for grasping by means of the continuous actions. The previously defined commands are finally assigned for the robot to stand up, turn left side and move forward together with the object. In the experimental setup, the Robotis-Op3 humanoid robot is used. The obtained results show that the proposed algorithm has successfully worked.

Advancements in Deep Reinforcement Learning and Inverse Reinforcement Learning for Robotic Manipulation: Toward Trustworthy, Interpretable, and Explainable Artificial Intelligence

“…In addition, with the developments in simulation technology, the further development of training algorithms has enabled them to improve their performance over time, and the area and number of uses have increased accordingly. Developments in simulation environments such as ROS [121], Gazebo [94], Webots [122], and V-REP [123] and advances in simulation physics engines have accelerated the development of DRL.…”

Tiny-YOLO distance measurement and object detection coordination system for the BarelangFC robot

“…Aslan et al [9] introduced semantic segmentation algorithms to a simulation and compared the accuracy, segmentation performance, and number of parameters. A year later, they combined a semantic algorithm with deep reinforcement learning (DRL) to recognize an object moving toward the robot [10].…”