Grasping in the Wild: Learning 6DoF Closed-Loop Grasping From Low-Cost Demonstrations

• Published in: IEEE robotics and automation letters Vol. 5; no. 3; pp. 4978 - 4985
• Main Authors: Song, Shuran, Zeng, Andy, Lee, Johnny, Funkhouser, Thomas
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.07.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Cameras; Computer simulation; deep learning for visual perception; Deep learning in grasping and manipulation; Degrees of freedom; Grasping; Grasping (robotics); Grippers; Low cost; Machine learning; Robots; Task analysis; Visualization

Intelligent manipulation benefits from the capacity to flexibly control an end-effector with high degrees of freedom (DoF) and dynamically react to the environment. However, due to the challenges of collecting effective training data and learning efficiently, most grasping algorithms today are limit...