A Survey: Robot Grasping

The field of autonomous robotics has made significant progress with the advent of learning methods that have been successfully applied in robotics and have achieved tremendous accuracy. Today, we can observe the successful application of classical machine learning, computer vision, and reinforcement learning in various robotic tasks like path planning, perception, locomotion, grasping, manipulation etc. But the big question remains, "Is robotics ready for the real world?" While it is true that we have now successfully deployed some robots in the real world, with some even interacting and collaborating with humans, many tasks remain difficult for robots to accomplish. In this survey paper, we focus on robot grasping, which is a significant challenge for robots and hinders their successful deployment in the real world. Our paper aims to review, categorize, and describe research in robotics focusing on robot grasping, the role of robot grippers and learning methods explored towards achieving intelligent control of robots when executing a grasping task.