Unsupervised Domain Adaptation for Visual Navigation

Abstract

Advances in visual navigation methods have led to intelligent embodied navigation agents capable of learning meaningful representations from raw RGB images and perform a wide variety of tasks involving structural and semantic reasoning. However, most learning-based navigation policies are trained and tested in simulation environments. In order for these policies to be practically useful, they need to be transferred to the real-world. In this paper, we propose an unsupervised domain adaptation method for visual navigation. Our method translates the images in the target domain to the source domain such that the translation is consistent with the representations learned by the navigation policy. The proposed method outperforms several baselines across two different navigation tasks in simulation. We further show that our method can be used to transfer the navigation policies learned in simulation to the real world.

Deep Reinforcement Learning Workshop at NeurIPS 2020. Camera Ready Version

References in corpus (9)

• Unsupervised Cross-Domain Image Generation
• The Replica Dataset: A Digital Replica of Indoor Spaces
• Learning to Explore using Active Neural SLAM
• Grounded Language Learning in a Simulated 3D World
• Gated-Attention Architectures for Task-Oriented Language Grounding
• PyRobot: An Open-source Robotics Framework for Research and Benchmarking
• Learning Exploration Policies for Navigation
• Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks
• Learning to Navigate Using Mid-Level Visual Priors