UNet-Based Keypoint Regression for 3D Cone Localization in Autonomous Racing
Abstract
Accurate cone localization in 3D space is essential in autonomous racing for precise navigation around the track. Approaches that rely on traditional computer vision algorithms are sensitive to environmental variations, and neural networks are often trained on limited data and are infeasible to run in real time. We present a UNet-based neural network for keypoint detection on cones, leveraging the largest custom-labeled dataset we have assembled. Our approach enables accurate cone position estimation and the potential for color prediction. Our model achieves substantial improvements in keypoint accuracy over conventional methods. Furthermore, we leverage our predicted keypoints in the perception pipeline and evaluate the end-to-end autonomous system. Our results show high-quality performance across all metrics, highlighting the effectiveness of this approach and its potential for adoption in competitive autonomous racing systems.
Cite
@article{arxiv.2602.21904,
title = {UNet-Based Keypoint Regression for 3D Cone Localization in Autonomous Racing},
author = {Mariia Baidachna and James Carty and Aidan Ferguson and Joseph Agrane and Varad Kulkarni and Aubrey Agub and Michael Baxendale and Aaron David and Rachel Horton and Elliott Atkinson},
journal= {arXiv preprint arXiv:2602.21904},
year = {2026}
}
Comments
8 pages, 9 figures. Accepted to ICCV End-to-End 3D Learning Workshop 2025 and presented as a poster; not included in the final proceedings due to a conference administrative error