Acquisition of 3D Environments for Robotic Navigation
Matterport technology allows to create a “digital twin” of a physical indoor space. Thanks to the Matterport Pro2 camera, it is easy to acquire 3D information from an environment and to create a virtual space in which to train embodied agents. Thanks to this, the recently proposed Matterport3D dataset of spaces has attracted a lot of interest form the research community. Our aim is to acquire new environments, and we are particularly interested in places related with Italian Cultural Heritage. In this project, we present the 3D reconstruction of the Galleria Estense of Modena.
The navigable model is constituted by nearly 200 viewpoints. Each viewpoint consists in a high-definition 360 image of the surroundings. Thanks to this, it is possible to walk through the Galleria Estense as we were actually standing in the halls of the museum. Additionally, it is possible to reconstruct the 3D model of the art gallery. This could serve to train embodied agents in pre-existing simulators with 3D support.