Out of the Box: Embodied Navigation in the Real World

TL;DR

This paper explores transferring visual navigation models from simulation to real-world robots, addressing architectural gaps and demonstrating successful deployment on a low-cost robot in unseen environments.

Contribution

It identifies architectural issues affecting Sim2Real transfer and proposes tailored solutions, enabling effective real-world deployment of navigation models trained in simulation.

Findings

Successful deployment of navigation models on a LoCoBot in unseen environments

Architectural adjustments improve Sim2Real transfer performance

Models achieve satisfying results in real-world scenarios without scene-specific priors

Abstract

The research field of Embodied AI has witnessed substantial progress in visual navigation and exploration thanks to powerful simulating platforms and the availability of 3D data of indoor and photorealistic environments. These two factors have opened the doors to a new generation of intelligent agents capable of achieving nearly perfect PointGoal Navigation. However, such architectures are commonly trained with millions, if not billions, of frames and tested in simulation. Together with great enthusiasm, these results yield a question: how many researchers will effectively benefit from these advances? In this work, we detail how to transfer the knowledge acquired in simulation into the real world. To that end, we describe the architectural discrepancies that damage the Sim2Real adaptation ability of models trained on the Habitat simulator and propose a novel solution tailored towards the deployment in real-world scenarios. We then deploy our models on a LoCoBot, a Low-Cost Robot equipped with a single Intel RealSense camera. Different from previous work, our testing scene is unavailable to the agent in simulation. The environment is also inaccessible to the agent beforehand, so it cannot count on scene-specific semantic priors. In this way, we reproduce a setting in which a research group (potentially from other fields) needs to employ the agent visual navigation capabilities as-a-Service. Our experiments indicate that it is possible to achieve satisfying results when deploying the obtained model in the real world. Our code and models are available at https://github.com/aimagelab/LoCoNav.