Abstract

H. Bao, K. Lekkala, L. Itti, Real-world Visual Navigation in a Simulator: A New Benchmark, In: The First Workshop on Populating Empty Cities (POETS)--Virtual Humans for Robotics and Autonomous Driving at CVPR 2024, 2nd Round, Jun 2024. (Cited by 3)

Abstract: In this paper, we explore advanced techniques in novel view rendering, particularly Gaussian Splatting, to create a simulator using a large-scale outdoor dataset. Our simulator, Beogym, is data-driven and built from data collected using a mobile robot. Our proposed pipeline processes the dataset to obtain an interconnected sequence of Gaussian splat files. These are then used by an engine to load appropriate splat files and render image frames during simulation. Beogym offers first-person view imagery, facilitating realistic training environments that could be used for enhancing and evaluating the learning capabilities of autonomous agents for visual navigation. It incorporates a sophisticated motion model and a sequence graph for seamless querying and loading of different sectors of the environment. The result closely resembles real-world navigation through smooth transitions across splat files.

Themes: Computer Vision, Machine Learning