Timezone: »

No RL, No Simulation: Learning to Navigate without Navigating
Meera Hahn · Devendra Singh Chaplot · Shubham Tulsiani · Mustafa Mukadam · James M Rehg · Abhinav Gupta

Fri Dec 10 08:30 AM -- 10:00 AM (PST) @ None #None

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.

Author Information

Meera Hahn (Georgia Institute of Technology)
Devendra Singh Chaplot (Carnegie Mellon University)
Shubham Tulsiani (UC Berkeley)
Mustafa Mukadam (Facebook AI Research)
James M Rehg (Georgia Institute of Technology)
Abhinav Gupta (Facebook AI Research/CMU)

More from the Same Authors