Vision-Based Robotic Object Grasping—A Deep Reinforcement Learning Approach

Abstract

This paper focuses on developing a robotic object grasping approach that possesses the ability of self-learning, is suitable for small-volume large variety production, and has a high success rate in object grasping/pick-and-place tasks. The proposed approach consists of a computer vision-based object detection algorithm and a deep reinforcement learning algorithm with self-learning capability. In particular, the You Only Look Once (YOLO) algorithm is employed to detect and classify all objects of interest within the field of view of a camera. Based on the detection/localization and classification results provided by YOLO, the Soft Actor-Critic deep reinforcement learning algorithm is employed to provide a desired grasp pose for the robot manipulator (i.e., learning agent) to perform object grasping. In order to speed up the training process and reduce the cost of training data collection, this paper employs the Sim-to-Real technique so as to reduce the likelihood of damaging the robot manipulator due to improper actions during the training process. The V-REP platform is used to construct a simulation environment for training the deep reinforcement learning neural network. Several experiments have been conducted and experimental results indicate that the 6-DOF industrial manipulator successfully performs object grasping with the proposed approach, even for the case of previously unseen objects.

Reinforcement Learning Algorithms and Applications in Healthcare and Robotics: A Comprehensive and Systematic Review

“…In [ 73 ], the authors discuss a vision-based approach to robotic object grasping that utilizes DRL to enable robots to achieve a high success rate in grasping objects. The introduced technique combines computer vision and deep RL to facilitate the learning and improvement of the robots’ grasping capabilities.…”

A Review of Machine Learning and Deep Learning for Object Detection, Semantic Segmentation, and Human Action Recognition in Machine and Robotic Vision

“…They excel in tracking moving objects and predicting future actions based on historical data. Some deep learning applications in robotic vision include object grasping and pick-and-place operations [124]. Offline reinforcement learning algorithms have also surfaced, facilitating continuous learning in robots without erasing previous knowledge [125].…”

Development of a SCARA robot arm for palletizing applications based on computer vision

“…Especially the integration of computer vision in the robot controller has helped increase the ability of robots and helped perform other tasks that required interaction with the environment. In the robotic vision system, the information in the surrounding environment is perceived by cameras [1][2][3][4][5]. A computer processes the vision data to provide useful information to the robot controller.…”

“…These features are used in simple cases where the interested objects are very different compared to the background. In complex scenarios, machine learning or deep learning methods are applied [19][20][21][22].…”