Conceptual design of a driving habit recognition framework

Dante Papada, Kathryn W. Jablokow

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

All drivers operate vehicles differently and demonstrate varying habits behind the wheel. Some drivers may execute vehicle maneuvers more cautiously than others, and some drivers may operate the vehicle with extreme inefficiencies. The habits developed by drivers can be viewed as a sequence or pattern of events that uniquely define the habitual behavior of the vehicle operator. In this paper, a conceptual design of a recognition system is discussed to classify sequences or patterns in vehicle data extracted from the Engine Control Unit in order to provide information about the vehicle operator's driving habits. Through an application of accepted pattern recognition techniques, Fuzzy Adaptive Resonance Theory, and Modern Control System Theory, a conceptual system framework was realized. To complement the conceptual design relationships between certain vehicle data parameters and certain human behaviors, models were developed to demonstrate these relationships created by this conceptual framework. These relationships were categorized and simulated in terms of vehicle safety and efficiency. Variables or factors were chosen to develop driving habit behavior models, such as wheel slippage, vehicle braking, fuel efficiency, and base or vehicle efficiency. The new conceptual framework was successfully validated through MATLAB simulations, consisting of 4 behavior models with a range of 11 variants. Evaluations of these behaviors provided the necessary feedback, via direct mapping of vehicle data points to a continuum of behavior types, to improve the vehicle operator's decision making.

Original languageEnglish (US)
Title of host publicationIEEE SSCI 2011
Subtitle of host publicationSymposium Series on Computational Intelligence - CIVTS 2011: 2011 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems
Pages59-66
Number of pages8
DOIs
StatePublished - 2011
EventSymposium Series on Computational Intelligence, IEEE SSCI2011 - 2011 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2011 - Paris, France
Duration: Apr 11 2011Apr 15 2011

Publication series

NameIEEE SSCI 2011: Symposium Series on Computational Intelligence - CIVTS 2011: 2011 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems

Other

OtherSymposium Series on Computational Intelligence, IEEE SSCI2011 - 2011 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2011
CountryFrance
CityParis
Period4/11/114/15/11

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Transportation

Fingerprint Dive into the research topics of 'Conceptual design of a driving habit recognition framework'. Together they form a unique fingerprint.

Cite this