Computer Vision

Robotics

Bi-directional Domain Adaptation for Sim2Real Transfer of Embodied Navigation Agents

April 1, 2021

Abstract

Deep reinforcement learning models are notoriously data hungry, yet real-world data is expensive and time consuming to obtain. The solution that many have turned to is to use simulation for training before deploying the robot in a real environment. Simulation offers the ability to train large numbers of robots in parallel, and offers an abundance of data. However, no simulation is perfect, and robots trained solely in simulation fail to generalize to the real-world, resulting in a “sim-vs-real gap”. How can we overcome the trade-off between the abundance of less accurate, artificial data from simulators and the scarcity of reliable, real-world data? In this paper, we propose Bi-directional Domain Adaptation (BDA), a novel approach to bridge the sim-vs-real gap in both directions -- real2sim to bridge the visual domain gap, and sim2real to bridge the dynamics domain gap. We demonstrate the benefits of BDA on the task of PointGoal Navigation. BDA with only 5k real-world (state, action, next-state) samples matches the performance of a policy fine-tuned with ~600k samples, resulting in a speed-up of ~120×.

Download the Paper

AUTHORS

Written by

Joanne Truong

Sonia Chernova

Dhruv Batra

Publisher

RA-L 2021

Related Publications

June 10, 2025

Robotics

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Mido Assran, Adrien Bardes, David Fan, Quentin Garrido, Russell Howes, Mojtaba Komeili, Matthew Muckley, Ammar Rizvi, Claire Roberts, Koustuv Sinha, Artem Zholus, Sergio Arnaud, Abha Gejji, Ada Martin, Francois Robert Hogan, Daniel Dugas, Piotr Bojanowski, Vasil Khalidov, Patrick Labatut, Francisco Massa, Marc Szafraniec, Kapil Krishnakumar, Yong Li, Xiaodong Ma, Sarath Chandar, Franziska Meier, Yann LeCun, Michael Rabbat, Nicolas Ballas

June 10, 2025

April 16, 2025

Robotics

Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D

Paul McVay, Sergio Arnaud, Ada Martin, Arjun Majumdar, Krishna Murthy Jatavallabhula, Phillip Thomas, Ruslan Partsey, Daniel Dugas, Abha Gejji, Alexander Sax, Vincent-Pierre Berges, Mikael Henaff, Ayush Jain, Ang Cao, Ishita Prasad, Mrinal Kalakrishnan, Mike Rabbat, Nicolas Ballas, Mido Assran, Oleksandr Maksymets, Aravind Rajeswaran, Franziska Meier

April 16, 2025

December 05, 2020

Robotics

Reinforcement Learni9ng

Neural Dynamic Policies for End-to-End Sensorimotor Learning

Deepak Pathak, Abhinav Gupta, Mustafa Mukadam, Shikhar Bahl

December 05, 2020

June 23, 2020

Robotics

Learning Robot Skills with Temporal Variational Inference

Tanmay Shankar, Abhinav Gupta

June 23, 2020

August 13, 2020

Robotics

Learning Robot Skills with Temporal Variational Inference | Facebook AI Research

Tanmay Shankar, Abhinav Gupta

August 13, 2020

Help Us Pioneer The Future of AI

We share our open source frameworks, tools, libraries, and models for everything from research exploration to large-scale production deployment.