Abstract
This paper investigates the utility of Neural Radiance Fields (NeRF) models in extending the regions of operation of a mobile robot, controlled by Image-Based Visual Servoing (IBVS) via static CCTV cameras. Using NeRF as a 3D-representation prior, the robot’s footprint may be extrapolated geometrically and used to train a CNN-based network to extract it online from the robot’s appearance alone. The resulting footprint results in a tighter bound than a robot-wide bounding box, allowing the robot’s controller to prescribe more optimal trajectories and expand its safe operational floor area.
Useful links
Preprint: https://arxiv.org/abs/2408.01251
Bibtex
@inproceedings{nerfoot2024,
author={Daoxin Zhong and Luke Robinson and Daniele De Martini},
title={NeRFoot: Robot-Footprint Estimation for Image-Based Visual Servoing},
year={2024},
booktitle={ICRA 40th Anniversary (ICRA@40)},
url={https://arxiv.org/abs/2408.01251},
}