Bi-directional Domain Adaptation for Sim2Real Transfer of Embodied Navigation Agents
Authors:
- Joanne TruongJTJoanne Truong
- Sonia ChernovaSCSonia Chernova
- Dhruv BatraDBDhruv Batra
Preprint
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 ~120x.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?IEEE Robotics and Automation Letters, 2020
- Learning Fast Adaptation With Meta Strategy OptimizationIEEE Robotics and Automation Letters, 2020
- Habitat: A Platform for Embodied AI Research2019
- Learning to Walk Via Deep Reinforcement Learning2019
- Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience2019
- VR-Goggles for Robots: Real-to-Sim Domain Adaptation for Visual ControlIEEE Robotics and Automation Letters, 2019
- A flexible and scalable SLAM system with full 3D motion estimation2011