Workload-adaptive cruise control – A new generation of advanced driver assistance systems

A foreseeable development of advanced driver assistance systems (ADAS) is the adaptation of ADAS’s control parameters to the actual workload of the human operator, enabling a level of assistance appropriately gauged to a driver’s current resources. Before such a feature can be introduced, however, three questions must be answered: (1) Is it technically possible to detect high workload levels using low-interference techniques? (2) Can such a system increase safety? (3) How can acceptance of such a system be optimized and confusion minimized? To answer these questions a simulator study was conducted using two systems: first, regular active cruise control (ACC) and second, workload-adaptive cruise control (WACC) systems. Participants were connected to a physiological signal measurement device that recorded heart rate, galvanic skin response and respiration. Participants also filled out subjective questionnaires to establish acceptance and system awareness. In cases for which usable physiological data were available, high workload conditions were identified in 83.7% of the classification sample by an algorithm based on physiological measurements. These data show that it is technologically possible to adapt driver assistance systems that employ physiological data for the detection of driver workload. Subjective measurements showed a preference for the WACC system. Moreover, objective data measurements revealed a safety advantage of the WACC over the ACC system: using WACC, no significant difference in brake reaction time, but a significant lower rate of deceleration, was found. Furthermore, 85.1% of participants were unaware of the adaptive behavior of the WACC, which was simulated by a change from a 1-s to a 2-s headway. These results suggest that a nondetectable change in regulation parameters led to higher safety in critical situations. Therefore, WACC systems should be considered as a next step in the development of ADAS.

[1]  Natasha Merat,et al.  Surrogate in-vehicle information systems and driver behaviour: effects of visual and cognitive load in simulated rural driving , 2005 .

[2]  William B. Rouse,et al.  Modeling the dynamics of mental workload and human performance in complex systems , 1993, IEEE Trans. Syst. Man Cybern..

[3]  Bor-Shong Liu,et al.  In-vehicle workload assessment: effects of traffic situations and cellular telephone use. , 2006, Journal of safety research.

[4]  David J. C. MacKay,et al.  Information Theory, Inference, and Learning Algorithms , 2004, IEEE Transactions on Information Theory.

[5]  Dick de Waard,et al.  The measurement of drivers' mental workload , 1996 .

[6]  Steffen Leonhardt,et al.  ECG on the Road: Robust and Unobtrusive Estimation of Heart Rate , 2011, IEEE Transactions on Biomedical Engineering.

[7]  William J. Horrey,et al.  Assessing Interference from Mental Workload Using a Naturalistic Simulated Driving Task: A Pilot Study , 2006 .

[8]  Tim Lüth,et al.  A system for unobtrusive in-car vital parameter acquisition and processing , 2010, 2010 4th International Conference on Pervasive Computing Technologies for Healthcare.

[9]  Gerald J.S. Wilde,et al.  The Theory of Risk Homeostasis: Implications for Safety and Health , 1982 .

[10]  Nicholas Roy,et al.  The impact of a naturalistic hands-free cellular phone task on heart rate and simulated driving performance in two age groups , 2011 .

[11]  Dick de Waard,et al.  Monitoring drivers' mental workload in driving simulators using physiological measures. , 2010, Accident; analysis and prevention.

[12]  R. Yerkes,et al.  The relation of strength of stimulus to rapidity of habit‐formation , 1908 .

[13]  Regan L. Mandryk,et al.  A fuzzy physiological approach for continuously modeling emotion during interaction with play technologies , 2007, Int. J. Hum. Comput. Stud..

[14]  George Forman,et al.  Apples-to-apples in cross-validation studies: pitfalls in classifier performance measurement , 2010, SKDD.

[15]  David B. Kaber,et al.  Out‐of‐the‐loop performance problems and the use of intermediate levels of automation for improved control system functioning and safety , 1997 .

[16]  J. Veltman,et al.  Physiological workload reactions to increasing levels of task difficulty. , 1998, Ergonomics.

[17]  Mica R. Endsley,et al.  The Out-of-the-Loop Performance Problem and Level of Control in Automation , 1995, Hum. Factors.

[18]  Bryan Reimer,et al.  Driver wellness, safety and the development of an AwareCar , 2009 .

[19]  Jennifer Healey,et al.  Toward Machine Emotional Intelligence: Analysis of Affective Physiological State , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[20]  Johan Engström,et al.  Effects of visual and cognitive load in real and simulated motorway driving , 2005 .

[21]  Bryan Reimer,et al.  An on-road assessment of the impact of cognitive workload on physiological arousal in young adult drivers , 2009, AutomotiveUI.

[22]  K A Brookhuis,et al.  The effects of mobile telephoning on driving performance. , 1991, Accident; analysis and prevention.

[23]  D. Kahneman,et al.  Attention and Effort , 1973 .

[24]  Michael Burmester,et al.  AttrakDiff: Ein Fragebogen zur Messung wahrgenommener hedonischer und pragmatischer Qualität , 2003, MuC.

[25]  E. Duffy,et al.  The psychological significance of the concept of arousal or activation. , 1957, Psychological review.

[26]  Bryan Reimer,et al.  Impact of Cognitive Task Complexity on Drivers’ Visual Tunneling , 2009 .

[27]  D. Strayer,et al.  Supertaskers: Profiles in extraordinary multitasking ability , 2010, Psychonomic bulletin & review.

[28]  Robert J. Cox,et al.  A Method for Optimal Division of Data Sets for Use in Neural Networks , 2005, KES.

[29]  Jennifer Healey,et al.  SmartCar: detecting driver stress , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[30]  Nasser M. Nasrabadi,et al.  Pattern Recognition and Machine Learning , 2006, Technometrics.

[31]  Koichi Sagawa,et al.  Time domain heart rate variability index for assessment of dynamic stress , 1998, Computers in Cardiology 1998. Vol. 25 (Cat. No.98CH36292).

[32]  Bryan Reimer,et al.  Sensitivity of Physiological Measures for Detecting Systematic Variations in Cognitive Demand From a Working Memory Task , 2012, Hum. Factors.

[33]  Ying Wang,et al.  The Impact of Systematic Variation of Cognitive Demand on Drivers' Visual Attention across Multiple Age Groups , 2010 .

[34]  Bryan Reimer,et al.  Monitoring, managing, and motivating driver safety and well-being , 2011, IEEE Pervasive Computing.

[35]  B. Reimer,et al.  Physiological Reactivity to Graded Levels of Cognitive Workload across Three Age Groups: An On-Road Evaluation , 2010 .

[36]  W. Kirchner Age differences in short-term retention of rapidly changing information. , 1958, Journal of experimental psychology.

[37]  Ying Wang,et al.  A Field Study on the Impact of Variations in Short-Term Memory Demands on Drivers’ Visual Attention and Driving Performance Across Three Age Groups , 2012, Hum. Factors.

[38]  B. Reimer,et al.  An Evaluation of Time of Day Influences on Simulated Driving Performance and Physiological Arousal , 2010 .

[39]  Bryan Reimer,et al.  The impact of cognitive workload on physiological arousal in young adult drivers: a field study and simulation validation , 2011, Ergonomics.

[40]  J. Dusek,et al.  Impact of Incremental Increases in Cognitive Workload on Physiological Arousal and Performance in Young Adult Drivers , 2009 .

[41]  H Summala,et al.  Cognitive load and detection thresholds in car following situations: safety implications for using mobile (cellular) telephones while driving. , 1999, Accident; analysis and prevention.

[42]  G. L. Freeman The relationship between performance level and bodily activity level. , 1940 .

[43]  Gerd Szwillus,et al.  Mensch & Computer 2003 , 2003 .

[44]  Eric McAdams,et al.  An integrated device to evaluate a driver’s functional state , 2009, Behavior research methods.