Estimating the risk associated with transportation technology using multifidelity simulation

Erik J. Schlicht, Nichole L. Morris

Research output: Contribution to journalArticle

Abstract

This paper provides a quantitative method for estimating the risk associated with candidate transportation technology, before it is developed and deployed. The proposed solution extends previous methods that rely exclusively on low-fidelity human-in-the-loop experimental data, or high-fidelity traffic data, by adopting a multifidelity approach that leverages data from both low- and high-fidelity sources. The multifidelity method overcomes limitations inherent to existing approaches by allowing a model to be trained inexpensively, while still assuring that its predictions generalize to the real-world. This allows for candidate technologies to be evaluated at the stage of conception, and enables a mechanism for only the safest and most effective technology to be developed and released.
Original languageUndefined/Unknown
JournalICML Submission
StatePublished - Jan 30 2017

Keywords

  • stat.AP
  • stat.ML

Cite this

Estimating the risk associated with transportation technology using multifidelity simulation. / Schlicht, Erik J.; Morris, Nichole L.

In: ICML Submission, 30.01.2017.

Research output: Contribution to journalArticle

@article{ad194b9abbf946fa840a0d9deadd9295,
title = "Estimating the risk associated with transportation technology using multifidelity simulation",
abstract = "This paper provides a quantitative method for estimating the risk associated with candidate transportation technology, before it is developed and deployed. The proposed solution extends previous methods that rely exclusively on low-fidelity human-in-the-loop experimental data, or high-fidelity traffic data, by adopting a multifidelity approach that leverages data from both low- and high-fidelity sources. The multifidelity method overcomes limitations inherent to existing approaches by allowing a model to be trained inexpensively, while still assuring that its predictions generalize to the real-world. This allows for candidate technologies to be evaluated at the stage of conception, and enables a mechanism for only the safest and most effective technology to be developed and released.",
keywords = "stat.AP, stat.ML",
author = "Schlicht, {Erik J.} and Morris, {Nichole L.}",
year = "2017",
month = "1",
day = "30",
language = "Undefined/Unknown",
journal = "ICML Submission",

}

TY - JOUR

T1 - Estimating the risk associated with transportation technology using multifidelity simulation

AU - Schlicht, Erik J.

AU - Morris, Nichole L.

PY - 2017/1/30

Y1 - 2017/1/30

N2 - This paper provides a quantitative method for estimating the risk associated with candidate transportation technology, before it is developed and deployed. The proposed solution extends previous methods that rely exclusively on low-fidelity human-in-the-loop experimental data, or high-fidelity traffic data, by adopting a multifidelity approach that leverages data from both low- and high-fidelity sources. The multifidelity method overcomes limitations inherent to existing approaches by allowing a model to be trained inexpensively, while still assuring that its predictions generalize to the real-world. This allows for candidate technologies to be evaluated at the stage of conception, and enables a mechanism for only the safest and most effective technology to be developed and released.

AB - This paper provides a quantitative method for estimating the risk associated with candidate transportation technology, before it is developed and deployed. The proposed solution extends previous methods that rely exclusively on low-fidelity human-in-the-loop experimental data, or high-fidelity traffic data, by adopting a multifidelity approach that leverages data from both low- and high-fidelity sources. The multifidelity method overcomes limitations inherent to existing approaches by allowing a model to be trained inexpensively, while still assuring that its predictions generalize to the real-world. This allows for candidate technologies to be evaluated at the stage of conception, and enables a mechanism for only the safest and most effective technology to be developed and released.

KW - stat.AP

KW - stat.ML

M3 - Article

JO - ICML Submission

JF - ICML Submission

ER -