NY Times Article

Shake Hands with the Future

A July 2018 New York Times feature story about the state of the art in robot grasping by Mae Ryan, Cade Metz, and Rumsey Taylor.

In the article and stylized videos, 3 of the 6 grasping projects (red boxes below) describe ongoing research in the UC Berkeley AUTOLab including
Dex-Net, a novel deep-learning approach to Universal Picking for warehouses and homes.

"...What you really want is a robot that can pick up anything, even stuff it has never seen before. That is what AUTOLab researchers have built over the last few years... The system benefits from dramatic advances in machine learning. The Berkeley researchers modeled the physics of more than 10,000 objects, identifying the best way to pick up each one. Then, using an algorithm called a neural network, the system analyzed all this data, learning to recognize the best way to pick up any item. In the past, researchers had to program a robot to perform each task. Now it can learn these tasks on its own."

NY Times Website, 30 July 2018

Business Section, page B1, 31 July 2018

Business Section, page B6-7, 31 July 2018

Universal Picking with the Dexterity Network (Dex-Net)>. An investigation that combines analytics, stochastics, and deep learning for Universal Picking of previously unseen objects from bins, involving AUTOLab PhD students Jeff Mahler, Matt Matl, Bill DeRose, David Gealy, Steve McKinley, Mike Danielczuk, and Ashwin Balakrishna.

SCHooL: Scalable Collaborative Human-Robot Learning. An ongoing National Science Foundation research project on robot learning with "surface decluttering" as an integrated application. A Berkeley AI Research (BAIR) project involving Profs. Anca Dragan, Pieter Abbeel, Stuart Russell, postdocs Ajay Tanwani, Aviv Tamar, Roy Fox, Ron Berenstein, and PhD students Dylan Hadfield-Menell, Sanjay Krishnan, and Rena Dorph and Jacqueline Barber from the Lawrence Hall of Science.

Robot Bed Making (paper in preparation, stay tuned!) A research project involving AUTOLab PhD students Michael Laskey and Daniel Seita, postdocs Ron Berenstein and Ajay Tanwani, Honda researchers Soshi Iba, Nawid Jamali, and Prakash Baskaran, and colleagues from the Toyota Research Institute (TRI).

UC Berkeley AUTOLab

Berkeley AI Research (BAIR) Lab

NY Times article with videos

Prof. Ken Goldberg

This research was performed at UC Berkeley's AUTOLAB in affiliation with the Berkeley AI Research (BAIR) Lab, Berkeley Deep Drive (BDD), the Real-Time Intelligent Secure Execution (RISE) Lab, and the CITRIS "People and Robots" (CPAR) Initiative, supported in part by donations from Siemens, Google, Amazon Robotics, Toyota Research Institute, Autodesk, ABB, Samsung, Knapp, Loccioni, Honda, Intel, Comcast, Cisco, Hewlett-Packard and by equipment grants from PhotoNeo, NVidia, and Intuitive Surgical.