Home // ICONS 2020, The Fifteenth International Conference on Systems // View article

Data-driven Approach for Accurate Estimation and Validation of Ego-Vehicle Speed

Authors:
Adina Aniculaesei
Meng Zhang
Andreas Rausch

Keywords: data-based multiresolutional learning; precise parameter estimation; automotive; ego-vehicle speed estimation; Euro NCAP requirements.

Abstract:
This paper proposes a data-oriented approach for the accurate estimation of the ego-vehicle speed. The approach combines long-term estimation with short-term estimation mechanisms to produce an accurate estimation of vehicle's tire circumference. The long-term estimation method approximates a standard value for the tire circumference on the basis of wheel speed measurements. In turn, the short-term estimation computes an estimation error for the tire circumference based on Global Positioning System (GPS) sensor data. The ego-vehicle speed is then computed on the basis of the estimated tire circumference and the current wheel speed measurement. In this approach, several error sources are considered: the GPS data, the road gradient and the rounding off of the estimated vehicle speed. The approach is validated on two real-world test data batches against the European New Car Assessment Programme (Euro NCAP) safety requirements. The results of the experimental validation demonstrate that the proposed vehicle speed estimation algorithm performs within the limits of the Euro NCAP requirements.

Pages: 72 to 77

Copyright: Copyright (c) IARIA, 2020

Publication date: February 23, 2020

Published in: conference

ISSN: 2308-4243

ISBN: 978-1-61208-771-9

Location: Lisbon, Portugal

Dates: from February 23, 2020 to February 27, 2020