Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/160349
Title: An automated machine learning (AutoML) method of risk prediction for decision-making of autonomous vehicles
Authors: Shi, Xiupeng
Wong, Yiik Diew
Chai, Chen
Li, Michael Zhi Feng
Keywords: Engineering::Civil engineering
Issue Date: 2020
Source: Shi, X., Wong, Y. D., Chai, C. & Li, M. Z. F. (2020). An automated machine learning (AutoML) method of risk prediction for decision-making of autonomous vehicles. IEEE Transactions On Intelligent Transportation Systems, 22(11), 7145-7154. https://dx.doi.org/10.1109/TITS.2020.3002419
Journal: IEEE Transactions on Intelligent Transportation Systems
Abstract: This study presents a domain-specific automated machine learning (AutoML) for risk prediction and behaviour assessment, which can be used in the behavioural decision-making and motion trajectory planning of autonomous vehicles (AVs). The AutoML enables end-to-end machine learning from vehicle movement and sensing data to detailed risk levels and corresponding behaviour characteristics, which integrates three main components of: unsupervised risk identification by surrogate risk indicators and big data clustering, feature learning based on XGBoost, and model auto-tuning by Bayesian optimisation. Then, the functions and performance of AutoML are evaluated based on NGSIM data, with assumptions of various sensing configurations or data acquisition conditions. AutoML achieves satisfactory results of behaviour-based risk prediction, which has a predictive power of 91.7% overall accuracy for four risk levels, and about 95% accuracy for safe-risk distinction. Bayesian optimisation guides the self-learning of AutoML to get the optimised feature subsets and hyperparameter values. The identification of key features not only produces better performance with fewer computation costs, but also provides data-driven insights about AV design, such as sensor configurations and sensor data mining, from risk decision-making perspectives. The application potentials of AutoML in AVs are discussed.
URI: https://hdl.handle.net/10356/160349
ISSN: 1524-9050
DOI: 10.1109/TITS.2020.3002419
Schools: School of Civil and Environmental Engineering 
Nanyang Business School 
Rights: © 2020 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:CEE Journal Articles
NBS Journal Articles

SCOPUSTM   
Citations 20

18
Updated on May 26, 2023

Web of ScienceTM
Citations 10

31
Updated on May 25, 2023

Page view(s)

47
Updated on May 31, 2023

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.