EcoRacer: Game-Based Optimal Electric Vehicle Design and Driver Control Using Human Players

Yi Ren, Alparslan Emrah Bayrak, Panos Y. Papalambros

Research output: Contribution to journalArticle

22 Citations (Scopus)

Abstract

We compare the performance of human players against that of the efficient global optimization (EGO) algorithm for an NP-complete powertrain design and control problem. Specifically, we cast this optimization problem as an online competition and received 2391 game plays by 124 anonymous players during the first month from launch. We found that while only a small portion of human players can outperform the algorithm in the long term, players tend to formulate good heuristics early on that can be used to constrain the solution space. Such constraining of the search enhances algorithm efficiency, even for different game settings. These findings indicate that human-assisted computational searches are promising in solving comprehensible yet computationally hard optimal design and control problems, when human players can outperform the algorithm in a short term.

Original languageEnglish (US)
JournalJournal of Mechanical Design, Transactions Of the ASME
Volume138
Issue number6
DOIs
StatePublished - Jun 1 2016

Fingerprint

Electric vehicles
Powertrains
Global optimization

ASJC Scopus subject areas

  • Mechanical Engineering
  • Mechanics of Materials
  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications

Cite this

EcoRacer : Game-Based Optimal Electric Vehicle Design and Driver Control Using Human Players. / Ren, Yi; Bayrak, Alparslan Emrah; Papalambros, Panos Y.

In: Journal of Mechanical Design, Transactions Of the ASME, Vol. 138, No. 6, 01.06.2016.

Research output: Contribution to journalArticle

@article{dbec43438ab6477aa3c4a64dccd21f74,
title = "EcoRacer: Game-Based Optimal Electric Vehicle Design and Driver Control Using Human Players",
abstract = "We compare the performance of human players against that of the efficient global optimization (EGO) algorithm for an NP-complete powertrain design and control problem. Specifically, we cast this optimization problem as an online competition and received 2391 game plays by 124 anonymous players during the first month from launch. We found that while only a small portion of human players can outperform the algorithm in the long term, players tend to formulate good heuristics early on that can be used to constrain the solution space. Such constraining of the search enhances algorithm efficiency, even for different game settings. These findings indicate that human-assisted computational searches are promising in solving comprehensible yet computationally hard optimal design and control problems, when human players can outperform the algorithm in a short term.",
author = "Yi Ren and Bayrak, {Alparslan Emrah} and Papalambros, {Panos Y.}",
year = "2016",
month = "6",
day = "1",
doi = "10.1115/1.4033426",
language = "English (US)",
volume = "138",
journal = "Journal of Mechanical Design - Transactions of the ASME",
issn = "1050-0472",
publisher = "American Society of Mechanical Engineers(ASME)",
number = "6",

}

TY - JOUR

T1 - EcoRacer

T2 - Game-Based Optimal Electric Vehicle Design and Driver Control Using Human Players

AU - Ren, Yi

AU - Bayrak, Alparslan Emrah

AU - Papalambros, Panos Y.

PY - 2016/6/1

Y1 - 2016/6/1

N2 - We compare the performance of human players against that of the efficient global optimization (EGO) algorithm for an NP-complete powertrain design and control problem. Specifically, we cast this optimization problem as an online competition and received 2391 game plays by 124 anonymous players during the first month from launch. We found that while only a small portion of human players can outperform the algorithm in the long term, players tend to formulate good heuristics early on that can be used to constrain the solution space. Such constraining of the search enhances algorithm efficiency, even for different game settings. These findings indicate that human-assisted computational searches are promising in solving comprehensible yet computationally hard optimal design and control problems, when human players can outperform the algorithm in a short term.

AB - We compare the performance of human players against that of the efficient global optimization (EGO) algorithm for an NP-complete powertrain design and control problem. Specifically, we cast this optimization problem as an online competition and received 2391 game plays by 124 anonymous players during the first month from launch. We found that while only a small portion of human players can outperform the algorithm in the long term, players tend to formulate good heuristics early on that can be used to constrain the solution space. Such constraining of the search enhances algorithm efficiency, even for different game settings. These findings indicate that human-assisted computational searches are promising in solving comprehensible yet computationally hard optimal design and control problems, when human players can outperform the algorithm in a short term.

UR - http://www.scopus.com/inward/record.url?scp=84973530118&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973530118&partnerID=8YFLogxK

U2 - 10.1115/1.4033426

DO - 10.1115/1.4033426

M3 - Article

AN - SCOPUS:84973530118

VL - 138

JO - Journal of Mechanical Design - Transactions of the ASME

JF - Journal of Mechanical Design - Transactions of the ASME

SN - 1050-0472

IS - 6

ER -