Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluation.

Navigating complex indoor environments requires a deep understanding of the space the robotic agent is acting into to correctly inform the navigation process of the agent towards the goal location. In recent learning-based navigation approaches, the scene understanding and navigation abilities of the agent are achieved simultaneously by collecting the required experience in simulation. Unfortunately, even if simulators represent an efficient tool to train navigation policies, the resulting models often fail when transferred into the real world, mainly because they are not able to capture and generalize the key properties of the scene, giving rise to a domain gap issue. One possible solution is to provide the navigation model with mid-level visual representations containing important domain-invariant properties of the scene. But, what are the best representations that facilitate the transfer of a model to the real-world? How can representations be combined to provide the most useful information to the navigation model? In this work we address these issues by proposing a benchmark of Deep Learning architectures to combine a range of mid-level visual representations, to perform a PointGoal navigation task following a Reinforcement Learning setup. All the proposed navigation models have been trained with the Habitat simulator on a synthetic office environment and have been tested on the same real-world environment using a real robotic platform. Moreover, to efficiently assess their performance in a real context, a validation tool has been proposed to generate realistic navigation episodes inside the simulator, avoiding the deployment of the navigation models in the real world. Our experiments showed that navigation models can benefit from the multi-modal input and that our validation tool can provide good estimation of the expected navigation performance in the real world, while saving time and resources. The acquired synthetic and real 3D models of the environment, together with the code of our validation tool built on top of Habitat, are publicly available at the following link: iplab.dmi.unict.it/EmbodiedVN/