No RL, No Simulation: Learning to Navigate without Navigating

Meera Hahn · Devendra Singh Chaplot · Shubham Tulsiani · Mustafa Mukadam · James Rehg · Abhinav Gupta

Keywords: [ Reinforcement Learning and Planning ] [ Deep Learning ] [ Graph Learning ]

[ Abstract ]
[ OpenReview
Fri 10 Dec 8:30 a.m. PST — 10 a.m. PST


Most prior methods for learning navigation policies require access to simulation environments, as they need online policy interaction and rely on ground-truth maps for rewards. However, building simulators is expensive (requires manual effort for each and every scene) and creates challenges in transferring learned policies to robotic platforms in the real-world, due to the sim-to-real domain gap. In this paper, we pose a simple question: Do we really need active interaction, ground-truth maps or even reinforcement-learning (RL) in order to solve the image-goal navigation task? We propose a self-supervised approach to learn to navigate from only passive videos of roaming. Our approach, No RL, No Simulator (NRNS), is simple and scalable, yet highly effective. NRNS outperforms RL-based formulations by a significant margin. We present NRNS as a strong baseline for any future image-based navigation tasks that use RL or Simulation.

Chat is not available.