Modeling Differences in Behavior Within and Between Drivers

Conference paper

Abstract

A new generation of driver assistance systems such as advanced collision warning and intelligent brake assist are now available options for the modern automobile. However, the addition of each new system increases the information load on the driver and potentially detracts from their ability to safely operate the vehicle. Over 10 years ago, we [Pentland A, Liu A (1999) A modeling and prediction of human behavior, Neural Comput 11, 229–242] suggested that a car that could infer the current intent of the driver would be able to appropriately manage the suite of systems and provide task relevant information to the driver in a timely fashion. This “smart car” would observe the driver’s pattern of behaviour in terms of their control of the vehicle then infer their current driving task using a Markov Dynamic Model. The approach could recognize driver actions from their initial behaviour with high accuracy under simulated driving conditions. Since that time new computational approaches and improved in-vehicle technology (e.g., GPS technology, advanced radar and video/computer vision, etc.) have moved the realization of this concept further along. Yet, one fundamental question still needs to be carefully addressed: Can these driver models, built on statistical descriptions of driver behaviour, accurately model the differences between drivers or changes within an individual driver’s behaviour? In this paper, I describe some examples of these differences and discuss their potential impact on a model’s ability to consistently recognize behaviour. To ensure the acceptance of the next generation driver assistance systems, these issues will have to be resolved.

Keywords

Markov Dynamic Model Individual differences Driving style Driver experience Fatigue 

References

  1. 1.
    Abe A, Miyatake H, Oguri K (2007) A study on switching AR_HMM driving behavior model depending on driver’s states. In: 2007 IEEE Intelligent Transportation Systems Conference, Seattle, WA, pp 806–811Google Scholar
  2. 2.
    Amata H, Miyajima C, Nishino T, Kitaoka N, Takeda K (2009) Prediction model of driving behavior based on traffic conditions and driver types. In: 12th International IEEE Conference on Intelligent Transportation Systems, St. LouisGoogle Scholar
  3. 3.
    Banks S, Dinges DF (2007) Behavioral and physiological consequences of sleep restriction. J Clin Sleep Med 3:519–528Google Scholar
  4. 4.
    Baulk SD, Biggs S, van den Heuvel C, Reid K, Dawson D (2006) Managing driver fatigue: quantifying real world performance impairment, final report, Australian Transport Safety Bureau, final report GR 2006/01, 2006Google Scholar
  5. 5.
    Bellet T, Tattegrain-Veste H (1999) A framework for representing driver knowledge. Int J Cogn Ergon 3:37–49CrossRefGoogle Scholar
  6. 6.
    Doshi A, Trivedi M (2009) On the roles of eye gaze and head dynamics in predicting driver’s intent to change lane. IEEE Trans Intell Trans Syst 10:453–462CrossRefGoogle Scholar
  7. 7.
    Gunzelmann G, Moore LR, Salvucci DD, Gluck KA (2009) Fluctuations in alertness and sustained attention: predicting driver performance. In: Ninth International Conference on Cognitive Modeling, ManchesterGoogle Scholar
  8. 8.
    Land MF (1992) Predictable eye-head coordination during driving. Nature 359:318–320CrossRefGoogle Scholar
  9. 9.
    Land MF, Horwood J (1995) Which part of the road guides steering? Nature 377:339–340CrossRefGoogle Scholar
  10. 10.
    Lim J, Dinges DF (2010) A meta-analysis of the impact of short-term sleep deprivation on cognitive variables. Psychol Bull 136:375–389CrossRefGoogle Scholar
  11. 11.
    Liu A (1998) What the driver’s eye tells the car’s brain. In: Underwood G (ed) Eye guidance in reading, driving, and scene perception. Elsevier, Oxford, pp 431–452CrossRefGoogle Scholar
  12. 12.
    Liu A, Pentland A (1997) Towards real-time recognition of driver intentions. In: IEEE Intelligent Transportation Systems Conference, BostonGoogle Scholar
  13. 13.
    Mandalia HM, Salvucci DD (2005) Using support vector machines for lane detection. In: Human factors and ergonomics 49th annual meeting, pp 1965–1969Google Scholar
  14. 14.
    McCall JC, Wipf DP, Trivedi MM, Rao BD (2007) Lane change intent analysis using robust operators and sparse bayesian learning. IEEE Trans Intell Trans Syst 8:431–440CrossRefGoogle Scholar
  15. 15.
    Mourant RR, Rockwell TH (1970) Mapping eye-movement patterns to the visual scene in driving: an exploratory study. Hum Factors 12:81–87Google Scholar
  16. 16.
    Oliver N, Pentland AP (2000) Driver behavior recognition and prediction in a SmartCar. In: Verly JG (ed) Enhanced and synthetic vision, vol 4023, SPIE, pp 280–290Google Scholar
  17. 17.
    Pentland A, Liu A (1999) Modeling and prediction of human behavior. Neural Comput 11:229–242CrossRefGoogle Scholar
  18. 18.
    Peters RD, Kloeppel E, Alicandri E (1999) Effects of partial and total sleep deprivation on driving performance, Federal Highway Administration, US Department of Transportation, FHWA-RD-94-046Google Scholar
  19. 19.
    Qiao L, Sato M, Abe K, Takeda H (1996) Self-supervised learning algorithm of environmental recognition in driving vehicle. IEEE Trans Syst Man Cybern Pt A 26:843–850CrossRefGoogle Scholar
  20. 20.
    Qiao L, Sato M, Takeda H (1995) Learning algorithm of environmental recognition in driving vehicle. IEEE Trans Syst Man Cybern 25:917–925CrossRefGoogle Scholar
  21. 21.
    Reyner LA, Horne JA (1998) Falling asleep at the wheel: are drivers aware of prior sleepiness? Int J Legal Med 111:120–123CrossRefGoogle Scholar
  22. 22.
    Salvucci DD (2006) Modeling driver behavior in a cognitive architecture. Hum Factors 48:362–380CrossRefGoogle Scholar
  23. 23.
    Salvucci DD, Liu A (2002) The time course of a lane change: Driver control and eye-movement behavior. Transp Res Part F 5:123–132Google Scholar
  24. 24.
    Schmidt EA, Kineses WE, Schrauf M, Haufe S, Schubert R, Curio G (2007) Assessing drivers’ vigilance state during monotonous driving. In: 4th International driving symposium on human factors in driver assessment, training, and vehicle design, StevensonGoogle Scholar
  25. 25.
    Takahashi H, Kuroda K (1996) A study on automated shifting and shift timing using a driver’s mental model. In: Masaki I (ed) IEEE Intelligent Vehicles Symposium, IEEE, Tokyo, pp 300–305Google Scholar
  26. 26.
    Tango F, Minin L, Tesauri F, Montanari R (2010) Field tests and machine learning approaches for refining algorithms and correlations of driver’s model parameters. Appl Ergon 41:211–224CrossRefGoogle Scholar
  27. 27.
    Taubman-Ben-Ari O, Mikulincer M, Gillath O (2004) The multidimensional driving style inventory—scale construction and validation. Accid Anal Prev 36:323–332CrossRefGoogle Scholar
  28. 28.
    Tsogas M, Dai X, Thomaidis G, Lytrivis P, Amditis A (2008) Detection of maneuvers using evidence theory. In: 2008 IEEE Intelligent Vehicle Symposium, Eindhoven, pp 126–131Google Scholar
  29. 29.
    van Dongen HPA, Maislin G, Mullington JM, Dinges DF (2003) The cumulative cost of additional wakefulness: dose-response effects on neurobehavioral functions and sleep physiology from chronic sleep restriction and total sleep deprivation. Sleep 26:117–126Google Scholar
  30. 30.
    Wierwille WW, Ellsworth LA, Wreggit SS, Fairbanks RJ, Kirn CL (1994) Research on vehicle based driver status/performance monitoring: development, validation, and refinement of algorithms for detection of driver drowsiness, final report, National Highway Traffic Safety Administration, final report DOT HS 808 247Google Scholar

Copyright information

© Springer-Verlag Italia Srl 2011

Authors and Affiliations

  1. 1.Man Vehicle Laboratory, Department Of Aeronautics and AstronauticsMassachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations