AUTOLAB: UC Berkeley Automation Lab

UC Berkeley’s AUTOLAB, directed by Professor Ken Goldberg, is a leading center for research in robotics and automation sciences.  The lab supports approximately 30 postdocs, PhD students, and undergrads pursuing projects in Robust Robot Grasping and Manipulation for Warehouses, Homes, and Robot-Assisted Surgery.  We focus on methods at the intersection of analytic theory (eg, geometric and statistical models, motion planning) and deep learning.

AUTOLab in the News

Aug 11, 2020

Oct 23, 2018

Drilling Down on Depth Sensing and Deep Learning

This post explores two independent innovations and the potential for combining them in robotics. Today, Deep Learning is showing promise for end-to-end learning of playing video games and performing robotic manipulation tasks.

July 30, 2018
New York Times

Shake Hands with the Future

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.

May 09, 2018

How robots are grasping the art of gripping

These unstructured environments represent the next frontier for researchers across the field of robotics, but such environments are particularly problematic for robots that grip. Any robot hoping to interact physically with the outside world faces an inherent uncertainty in how objects will react to touch. “Grasping is the critical grand challenge right now,” says Ken Goldberg, an engineer at the University of California, Berkeley.

Mar 26, 2018
MIT Tech Review

Exclusive: This is the most dexterous robot ever created

The most nimble-fingered machine yet shows how machine learning can teach robots to recognize and pick up different types of objects, a skill that could transform many factories and warehouses.

Mar 1, 2018

How Flight Simulation Tech Can Help Turn Robots Into Surgeons

An “open-source” Stewart Platform Research Kit (SPRK) for simulating heartbeats and breathing for surgical robotics and a new algorithm for automated surgical cutting based on intermittent synchronization will be presented March 1 at the first International Symposium on Medical Robotics (ISMR) in Atlanta, GA.

Oct 26, 2017

DART: Noise Injection for Robust Imitation Learning
We show how DART can be applied in a complex system that leverages both classical robotics and learning techniques to teach the first robot to make a bed.

Oct 17, 2017

Learning Long Duration Sequential Task Structure From Demonstrations with Application in Surgical Robotics
This post summarizes results from three recent papers that propose algorithms that learn to decompose a longer task into shorter subtasks.

May 26, 2017

This robot arm’s AI thinks like we do about how to grab something
AI is helping there in the form of systems like Dex-Net, which uses deep learning to let a robotic arm improvise an effective grip for objects it’s never seen before.

May 25, 2017
MIT Technology Review

Meet the Most Nimble-Fingered Robot Yet
A dexterous multi-fingered robot practiced using virtual objects in a simulated world, showing how machine learning and the cloud could revolutionize manual work.

Jan 12, 2017
Fast Company

Why It’s So Hard For Robots To Get A Grip
Robots are all thumbs. Engineers are working to improve dexterity so bots can take over housekeeping drudgework—as well as people’s jobs.

May 31, 2016
IEEE Spectrum

Would You Trust a Robot Surgeon to Operate on You?
Precise and dexterous surgical robots may take over the operating room

May 16-21, 2016
ICRA 2016

Unsupervised Trajectory Segmentation of Multi-Modal Surgical Demonstrations with Deep Learning
Automating Multiple-Throw Multilateral Surgical Suturing
With a Mechanical Needle Guide and Sequential Convex Optimization

May 4, 2016
MIT Technology Review

Nimble-Fingered Robot Outperforms the Best Human Surgeons
A surgical robot was able to repair pigs’ bowels more accurately than human doctors.

March 9, 2016
Rolling Stone

Inside the Artificial Intelligence Revolution: A Special Report, Pt. 2
Self-driving cars, war outsourced to robots, surgery by autonomous machines – this is only the beginning

June 26, 2015

Autonomous Tumor Localization and Extraction
Palpation, Incision, Debridement and Adhesive Closure with the da Vinci Research Kit
Winner of Best Video Award at Hamlyn Surgical Robotics Symposium, London, June 2015

May 26-30, 2015
ICRA 2015

Surgical Debridement
Performing Surgical Subtasks without Human Intervention

February 4, 2015

How robots could be your future surgeons
Doctors have been using robotics to assist with surgery for a couple of decades. But now, they’re experimenting with teaching the robots to do more surgical tasks on their own.

October 23, 2014
The New York Times

New Research Center Aims to Develop Second Generation of Surgical Robots
A research center intended to help develop medical robots that can perform low-level and repetitive surgical tasks, freeing doctors to concentrate on the most challenging and complex aspects of the operations they perform.

October 22, 2014
The New York Times

Scientists Consider Repurposing Robots for Ebola
Robotics scientists nationwide are pondering an intriguing possibility: Might robotic technologies deployed in rescue and disaster situations be quickly repurposed to help contain the Ebola epidemic?


The Laboratory for Automation Science and Engineering (AUTOLAB) is part of the University of California, Berkeley.