Quantifying learning algorithm uncertainties in autonomous driving systems: Enhancing safety through Polynomial Chaos Expansion and High Definition maps

Ruihe Zhang; Chen Sun; Minghao Ning; Reza Valiollahimehrizi; Yukun Lu; Krzysztof Czarnecki; Amir Khajepour

doi:10.1016/j.aap.2024.107903

Quantifying learning algorithm uncertainties in autonomous driving systems: Enhancing safety through Polynomial Chaos Expansion and High Definition maps

Accid Anal Prev. 2024 Dec 28:211:107903. doi: 10.1016/j.aap.2024.107903. Online ahead of print.

Authors

Ruihe Zhang¹, Chen Sun², Minghao Ning³, Reza Valiollahimehrizi⁴, Yukun Lu⁵, Krzysztof Czarnecki⁶, Amir Khajepour⁷

Affiliations

¹ Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo ON, N2L 3G1, Canada. Electronic address: [email protected].
² Department of Data and System Engineering, University of Hong Kong, Pokfulam, Hong Kong, China. Electronic address: [email protected].
³ Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo ON, N2L 3G1, Canada. Electronic address: [email protected].
⁴ Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo ON, N2L 3G1, Canada. Electronic address: [email protected].
⁵ Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo ON, N2L 3G1, Canada. Electronic address: [email protected].
⁶ Department of Electrical and Computer Engineering, University of Waterloo, Waterloo ON, N2L 3G1, Canada. Electronic address: [email protected].
⁷ Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo ON, N2L 3G1, Canada. Electronic address: [email protected].

PMID: 39733602
DOI: 10.1016/j.aap.2024.107903

Abstract

Autonomous driving systems (ADS), leveraging advancements in learning algorithms, have the potential to significantly enhance traffic safety by reducing human errors. However, a major challenge in evaluating ADS safety is quantifying the performance uncertainties inherent in these black box algorithms, especially in dynamic and complex service environments. Addressing this challenge is crucial for maintaining public trust and promoting widespread ADS adoption. In this work, we propose a Polynomial Chaos Expansion (PCE) approach, utilizing High Definition (HD) maps to quantify positional uncertainties from an ADS object detection algorithm. The PCE-based approach also offers the flexibility for online self-updating, accommodating data shifts due to changing operational conditions. Tested in both simulation and real-world experiments, the PCE method demonstrates more accurate uncertainty quantification than baseline models. Additionally, the results highlight the importance and effectiveness of the self-updating capability, particularly when encountering weather changes.

Keywords: Autonomous driving; Safety testing; Uncertainty quantification; Validation and verification.