Home

Vision

Journey

Thinking

Technology

Join us

Team

Menu image

Connect

Google

Alphabet

Privacy & Terms

Everyday Robots

Born from X, and working alongside teams at Google, we’re building a new type of robot. One that can learn by itself, to help anyone with (almost) anything.

[pageTitle] | [siteTitle]

Ikechukwu Uchendu

Ted Xiao

Robot sorting in real and sim 

Efficiently Initializing Reinforcement Learning With Prior Policies

News

Research

Chelsea Finn

Eric Jang

Robot sorting objects that it has learned from this new research. 

Can Robots Follow Instructions for New Tasks?

Mengyuan Yan

Yao Lu

AW-Opt: Learning Robotic Skills with Imitation and Reinforcement at Scale

Combining RL + IL at Scale

Daniel Ho

Kanishka Rao

RetinaGAN

Shortening the Sim to Real Gap

Zhuo Xu

COCOI

Pushing Objects in 3D

Mohi Khansari

Action-Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data

Action-Image: Teaching Grasping in Sim 

Alexander Herzog

Thinking While Moving: Deep Reinforcement Learning with Concurrent Control

Can Robots Think and Move? 

Learning Latent Plans from Play

Alex Irpan

Peter Pastor

Scalable Deep Reinforcement Learning for Robotic Manipulation

Scalable Deep Reinforcement Learning from Robotic Manipulation (QT-Opt)

Sergey Levine

Large-scale data collection with an array of robots

Deep Learning for Robots: Learning from Large-Scale Interaction