NavDreams: Towards Camera-Only RL Navigation Among Humans

TL;DR

This paper explores camera-only robot navigation in crowded spaces using world models to predict future scenes, demonstrating successful simulation and real-world transfer of learned policies.

Contribution

It applies world model-based reinforcement learning to camera-only navigation in crowded environments, showing effective scene modeling and policy transfer from simulation to real robot.

Findings

World models can predict future image sequences with consistent geometry.

Navigation policies trained in simulation transfer successfully to real robots.

State-of-the-art methods achieve success in camera-only crowd navigation.

Abstract

Autonomously navigating a robot in everyday crowded spaces requires solving complex perception and planning challenges. When using only monocular image sensor data as input, classical two-dimensional planning approaches cannot be used. While images present a significant challenge when it comes to perception and planning, they also allow capturing potentially important details, such as complex geometry, body movement, and other visual cues. In order to successfully solve the navigation task from only images, algorithms must be able to model the scene and its dynamics using only this channel of information. We investigate whether the world model concept, which has shown state-of-the-art results for modeling and learning policies in Atari games as well as promising results in 2D LiDAR-based crowd navigation, can also be applied to the camera-based navigation problem. To this end, we create simulated environments where a robot must navigate past static and moving humans without colliding in order to reach its goal. We find that state-of-the-art methods are able to achieve success in solving the navigation problem, and can generate dream-like predictions of future image-sequences which show consistent geometry and moving persons. We are also able to show that policy performance in our high-fidelity sim2real simulation scenario transfers to the real world by testing the policy on a real robot. We make our simulator, models and experiments available at https://github.com/danieldugas/NavDreams.