Loading…

Fitting cornering speed models with one-class support vector machines

© 2019 IEEE. This paper investigates the modelling of cornering speed using road curvature as a predictive variable, which is of interest for advanced driver assistance system (ADAS) applications including eco-driving assistance and curve warning. Such models are common in the driver modelling and h...

Full description

Saved in:
Bibliographic Details
Main Authors: James Fleming, Xingda Yan, Roberto Lot
Format: Default Conference proceeding
Published: 2019
Subjects:
Online Access:https://hdl.handle.net/2134/12623843.v1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1818167435666128896
author James Fleming
Xingda Yan
Roberto Lot
author_facet James Fleming
Xingda Yan
Roberto Lot
author_sort James Fleming (7308476)
collection Figshare
description © 2019 IEEE. This paper investigates the modelling of cornering speed using road curvature as a predictive variable, which is of interest for advanced driver assistance system (ADAS) applications including eco-driving assistance and curve warning. Such models are common in the driver modelling and human factors literature, yet lack reliable parameter estimation methods, requiring an ad-hoc evaluation of the upper envelope of the data followed by linear regression to that envelope. Considering the space of possible combinations of lateral acceleration and cornering speed, we cast the modelling of cornering speed as an 'outlier detection' problem which may be solved using one-class Support Vector Machine (SVM) methods from machine learning. For an existing cornering model, we suggest a fitting method using a specific choice of kernel function in a one-class SVM. As the parameters of the cornering speed model may be recovered from the SVM solution, this provides a more robust and reproducible fitting method for this model of cornering speed than the existing envelope-based approaches. In addition, this gives comparable outlier detection performance to generic SVM methods based on Radial Basis Function (RBF) kernels while reducing training times by a factor of 10, indicating potential for use in adaptive eco-driving assistance systems that require retraining either online or between drives.
format Default
Conference proceeding
id rr-article-12623843
institution Loughborough University
publishDate 2019
record_format Figshare
spelling rr-article-126238432019-08-29T00:00:00Z Fitting cornering speed models with one-class support vector machines James Fleming (7308476) Xingda Yan (9097163) Roberto Lot (8270391) Uncategorised value © 2019 IEEE. This paper investigates the modelling of cornering speed using road curvature as a predictive variable, which is of interest for advanced driver assistance system (ADAS) applications including eco-driving assistance and curve warning. Such models are common in the driver modelling and human factors literature, yet lack reliable parameter estimation methods, requiring an ad-hoc evaluation of the upper envelope of the data followed by linear regression to that envelope. Considering the space of possible combinations of lateral acceleration and cornering speed, we cast the modelling of cornering speed as an 'outlier detection' problem which may be solved using one-class Support Vector Machine (SVM) methods from machine learning. For an existing cornering model, we suggest a fitting method using a specific choice of kernel function in a one-class SVM. As the parameters of the cornering speed model may be recovered from the SVM solution, this provides a more robust and reproducible fitting method for this model of cornering speed than the existing envelope-based approaches. In addition, this gives comparable outlier detection performance to generic SVM methods based on Radial Basis Function (RBF) kernels while reducing training times by a factor of 10, indicating potential for use in adaptive eco-driving assistance systems that require retraining either online or between drives. 2019-08-29T00:00:00Z Text Conference contribution 2134/12623843.v1 https://figshare.com/articles/conference_contribution/Fitting_cornering_speed_models_with_one-class_support_vector_machines/12623843 All Rights Reserved
spellingShingle Uncategorised value
James Fleming
Xingda Yan
Roberto Lot
Fitting cornering speed models with one-class support vector machines
title Fitting cornering speed models with one-class support vector machines
title_full Fitting cornering speed models with one-class support vector machines
title_fullStr Fitting cornering speed models with one-class support vector machines
title_full_unstemmed Fitting cornering speed models with one-class support vector machines
title_short Fitting cornering speed models with one-class support vector machines
title_sort fitting cornering speed models with one-class support vector machines
topic Uncategorised value
url https://hdl.handle.net/2134/12623843.v1