Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching

Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching

Show other versions (1)

This paper presents a robotic pick-and-place system that is capable of grasping and recognizing both known and novel objects in cluttered environments. The key new feature of the system is that it handles a wide range of object categories without needing any task-specific training data for novel obj...

Full description

Bibliographic Details
Main Authors: Zeng, Andy (Author), Song, Shuran (Author), Yu, Kuan-Ting (Author), Donlon, Elliott S (Author), Hogan, Francois R. (Author), Bauza Villalonga, Maria (Author), Ma, Daolin (Author), Taylor, Orion Thomas (Author), Liu, Melody (Author), Romo, Eudald (Author), Fazeli, Nima (Author), Alet, Ferran (Author), Chavan Dafle, Nikhil Narsingh (Author), Holladay, Rachel (Author), Morena, Isabella (Author), Qu Nair, Prem (Author), Green, Druck (Author), Taylor, Ian (Author), Liu, Weber (Author), Funkhouser, Thomas (Author), Rodriguez, Alberto (Author)
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor), Massachusetts Institute of Technology. Department of Mechanical Engineering (Contributor)
Format: Article
Language:English
Published: Institute of Electrical and Electronics Engineers (IEEE), 2020-09-01T16:02:35Z.
Subjects:
Article
Online Access:Get fulltext
Show all versions (2)

Similar Items