Embodied-AI Workshop
CVPR 2020
  • Overview
  • (NEW) Live Sessions
  • Invited Talks
  • Challenges
  • Organizers
  • Overview

    There is an emerging paradigm shift from ‘Internet AI’ towards ‘Embodied AI’ in the computer vision, NLP, and broader AI communities. In contrast to Internet AI’s focus on learning from datasets of images, videos, and text curated from the internet, embodied AI enables learning through interaction with the surrounding environment.

    The goal of this workshop is to bring together researchers from the fields of computer vision, language, graphics, and robotics to share and discuss the current state of intelligent agents that can:

    The Embodied AI 2020 workshop will be held in conjunction with CVPR 2020 in Seattle, WA over two days, Jun 14 and Jun 15. It will feature a host of invited talks covering a variety of topics in Embodied AI, three exciting challenges, and a panel discussion.


    Live Sessions!


    Join Zoom Meeting
    June 14th | 5-6 PM PST

    Panel consists of researchers who have built various simulation environments and physics engines.
    Topics are based on questions, likely involving the need for simulation, progress in developing AI agents in simulation, need for photo-realism, physics engines for simulation, multi-agent capabilities, sim-to-real, the future of simulators, accessibility of such environments to all, and more!





    Join Zoom Meeting
    June 15th | 9-10 AM PST


    Panel consists of speakers at this workshop.
    Topics are based on questions, likely involving cognitive development in humans, progress in embodied AI tasks, sim-2-real transfer, robotics, embodied AI for all, and more!

    Invited Talks


    Motivation for Embodied AI Research

    Alison Gopnik
    UC Berkeley


    Linda Smith
    Indiana

    Embodied Navigation

    Raquel Urtasun
    Uber ATG Toronto
    University of Toronto


    Piotr Mirowski
    DeepMind

    Embodied Perception

    Alex Schwing
    UIUC


    Deepak Pathak
    FAIR, UC Berkeley
    CMU (Starting Fall 2020)

    Robotics

    Dieter Fox
    Nvidia, UW


    Franziska Meier
    FAIR

    Sim-2-Real Transfer

    Judy Hoffman
    Georgia Tech


    Sonia Chernova
    Georgia Tech

    Embodied AI for All

    Heidi Hysell
    Alpha Drive


    Rishabh Jain
    Eval AI
    Georgia Tech


    Challenges

    The Embodied AI 2020 workshop will host three exciting challenges focusing on the problems of point navigation, object navigation, and the transfer of models from simulated environments to the real world. More details regarding data, submission instructions and timelines can be found on the individual challenge websites.


    iGibson Challenge
    Habitat Challenge
    RoboTHOR Challenge
    Although these challenges use three different simulation engines, the APIs, action and observation spaces, as well as agent are unified. Thus, participants are encouraged to participate in all challenges as these can use identical setups.

    In more detail, the challenges relate to each other as follows:
    iGibson Habitat RoboTHOR
    Problem PointNav PointNav/ObjNav ObjNav
    Test setup Real Simulation Real
    Agent LoCoBot
    Observations RGB-D
    Actions Discrete/Continuous Discrete Discrete/Continuous

    Challenge Results

    iGibson Challenge
    Organizer Video

    Winners


    Habitat Challenge
    Organizer Video

    ObjectNav Winners

    PointNav Winners


    RoboTHOR Challenge
    Organizer Video

    Organizers

    The Embodied AI 2020 workshop is a joint effort by a large set of researchers from a variety of organizations. They are listed below in alphabetical order.

    Jose M. Alvarez
    NVIDIA
    Anelia Angelova
    Google
    Dhruv Batra
    GaTech, FAIR
    Angel X. Chang
    SFU
    Samyak Datta
    GaTech
    Matt Deitke
    AI2, UW
    Ali Farhadi
    Apple, UW
    Aaron Gokaslan
    FAIR
    Aleksandra Faust
    Google
    Jose A. Iglesias-Guitian
    UDC, CITIC
    Abhishek Kadian
    FAIR
    Aniruddha Kembhavi
    AI2, UW
    Vangelis Kokkevis
    TRI
    Vladlen Koltun
    Intel
    Eric Kolve
    AI2
    Stefan Lee
    Oregon State
    Yongjoon Lee
    Zoox
    Eric (Chengsu) Li
    Stanford
    Antonio Lopez
    CVC, UAB
    Oleksandr Maksymets
    FAIR
    Jitendra Malik
    UC Berkeley
    Roberto Martín-Martín
    Stanford
    Roozbeh Mottaghi
    AI2, UW
    Devi Parikh
    GaTech, FAIR
    German Ros
    Intel
    Manolis Savva
    SFU, FAIR
    Dustin Schwenk
    AI2
    Philipp Slusallek
    DFKI
    Julian Straub
    FAIR
    Jie Tan
    Google
    Alexander Toshev
    Google
    Fei Xia
    Stanford
    Erik Wijmans
    GaTech
    Amir Zamir
    EPFL