A Lightweight Machine Learning Pipeline for LiDAR-simulation

Richard Marcus, Niklas Knoop, Bernhard Egger, Marc Stamminger

2022

Abstract

Virtual testing is a crucial task to ensure safety in autonomous driving, and sensor simulation is an important task in this domain. Most current LiDAR simulations are very simplistic and are mainly used to perform initial tests, while the majority of insights are gathered on the road. In this paper, we propose a lightweight approach for more realistic LiDAR simulation that learns a real sensor’s behavior from test drive data and transforms this to the virtual domain. The central idea is to cast the simulation into an image-to-image translation problem. We train our pix2pix based architecture on two real world data sets, namely the popular KITTI data set and the Audi Autonomous Driving Dataset which provide both, RGB and LiDAR images. We apply this network on synthetic renderings and show that it generalizes sufficiently from real images to simulated images. This strategy enables to skip the sensor-specific, expensive and complex LiDAR physics simulation in our synthetic world and avoids oversimplification and a large domain-gap through the clean synthetic environment.

Paper Citation

in Harvard Style

Marcus R., Knoop N., Egger B. and Stamminger M. (2022). A Lightweight Machine Learning Pipeline for LiDAR-simulation. In Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA, ISBN 978-989-758-584-5, pages 176-183. DOI: 10.5220/0011309100003277

in Bibtex Style

@conference{delta22,
author={Richard Marcus and Niklas Knoop and Bernhard Egger and Marc Stamminger},
title={A Lightweight Machine Learning Pipeline for LiDAR-simulation},
booktitle={Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,},
year={2022},
pages={176-183},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011309100003277},
isbn={978-989-758-584-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Conference on Deep Learning Theory and Applications - Volume 1: DeLTA,
TI - A Lightweight Machine Learning Pipeline for LiDAR-simulation
SN - 978-989-758-584-5
AU - Marcus R.
AU - Knoop N.
AU - Egger B.
AU - Stamminger M.
PY - 2022
SP - 176
EP - 183
DO - 10.5220/0011309100003277