Being able to explore an environment and understand the location and type of all objects therein is important for indoor robotic platforms that must interact closely with humans. However, it is difficult to evaluate progress in this area due to a lack of standardized testing which is limited due to the need for active robot agency and perfect object ground-truth. To help provide a standard for testing scene understanding systems, we present a new robot vision scene understanding challenge using simulation to enable repeatable experiments with active robot agency. We provide two challenging task types, three difficulty levels, five simulated environments and a new evaluation measure for evaluating 3D cuboid object maps. Our aim is to drive state-of-the-art research in scene understanding through enabling evaluation and comparison of active robotic vision systems.
@article{arxiv.2009.05246,
title = {The Robotic Vision Scene Understanding Challenge},
author = {David Hall and Ben Talbot and Suman Raj Bista and Haoyang Zhang and Rohan Smith and Feras Dayoub and Niko Sünderhauf},
journal= {arXiv preprint arXiv:2009.05246},
year = {2020}
}