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

Hajek, W.; Gaponova, Irina; Fleischer, K; Krems, Josef F.

doi:10.1016/j.trf.2013.06.001

Cited by 48 publications

(21 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Literature on measuring physiological signals in the car can be divided into simulator studies [13,18,19,24,36] and field studies [14,15,18,28,30,33,40]. The major advantage of simulator studies is their relative ease of controlling experimental variables and conditions.…”

Section: Measuring Physiological Signals In the Carmentioning

confidence: 99%

Classifying driver workload using physiological and driving performance data

Solovey

Zec

Perez

et al. 2014

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

160

127

View full text Add to dashboard Cite

Understanding the driver's cognitive load is important for evaluating in-vehicle user interfaces. This paper describes experiments to assess machine learning classification algorithms on their ability to automatically identify elevated cognitive workload levels in drivers, leading towards the development of robust tools for automobile user interface evaluation. We look at using both driver performance as well as physiological data. These measures can be collected in real-time and do not interfere with the primary task of driving the vehicle. We report classification accuracies of up to 90% for detecting elevated levels of cognitive load, and show that the inclusion of physiological data leads to higher classification accuracy than vehicle sensor data evaluated alone. Finally, we show results suggesting that models can be built to classify cognitive load across individuals, instead of building individual models for each person. By collecting data from drivers in two large field studies on the highway (20 drivers and 99 drivers), this work extends prior work and demonstrates feasibility and potential of such measures for HCI research in vehicles.

show abstract

Section: Measuring Physiological Signals In the Carmentioning

confidence: 99%

Classifying driver workload using physiological and driving performance data

Solovey

Zec

Perez

et al. 2014

Proceedings of the SIGCHI Conference on Human Factors in Computing Systems

160

127

View full text Add to dashboard Cite

show abstract

“…As highlighted in Section I, there exist substantial distinctions between different drivers in term of driving characteristics. Consequently, awareness of individual drivers' workload with a satisfying performance will be of particular importance, which can be seen as the basis and prerequirement for adaptive aiding systems [9]. The concept of personalized system is now drawing increasing attention in a wide range of applications.…”

Section: Personalized Driver Workload Inferencementioning

confidence: 99%

“…In online implementation, VRMs data are classified via the trained classifier so that the driver workload category can be identified. Based on the real time workload information, adaptive aiding can be provided to the driver at the right time and in an appropriate manner [5], [9]. In the following sections, different components of the proposed PDWI system will be discussed in detail.…”

Section: Personalized Driver Workload Inferencementioning

confidence: 99%

“…To guarantee driving safety while maintaining convenience, it is important to monitor driver workload in real time, upon which "adaptive aiding" can be supplied to the driver at the right time and in a proper manner [5], [9]. For instance, an earlier and clearer collision warning signal can be given to a driver under high workload compared to a driver under low workload [9], [10]; human machine interface can also be optimized based on the awareness of drivers and vehicles [11] (e.g., switching off certain IVIS for drivers under high workload). By doing so, driver workload can be potentially kept at an appropriate level for safe driving.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Personalized Driver Workload Inference by Learning From Vehicle Related Measurements

Liu

2019

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

Adapting in-vehicle systems (e.g., advanced driver assistance systems and in-vehicle information systems) to individual drivers' workload can enhance both safety and convenience. To make this possible, it is a prerequisite to infer driver workload so that adaptive aiding can be provided to the driver at the right time and in an appropriate manner. Rather than developing an average model for all drivers, a personalized driver workload inference (PDWI) system considering individual drivers driving characteristics is developed using machine learning techniques via easily accessed vehicle related measurements (VRMs). The proposed PDWI system comprises two stages. In offline training, individual drivers workload is first automatically splitted into different categories according to its inherent data characteristics using fuzzy C-means (FCM) clustering. Then an implicit mapping between VRMs and different levels of workload is constructed via classification algorithms. In online implementation, VRMs samples are classified into different clusters, consequently driver workload type can be successfully inferred. A recently collected dataset from real-world naturalistic driving experiments is drawn to validate the proposed PDWI system. Comparative experimental results indicate that the proposed framework integrating FCM clustering and support vector machine classifier provides a promising workload recognition performance in terms of accuracy, precision, recall, F 1 -score, and prediction time. The interindividual differences in term of workload are also identified and can be accommodated by the proposed framework due to its adaptiveness.Index Terms-Fuzzy C-means (FCM) clustering, personalized aiding, support vector machine (SVM), workload recognition.

show abstract

“…In addition to studies conducted at the AgeLab, the task has been used extensively internationally as a method of inducing graded levels of cognitive workload with studies such as [1,2,4,5,6,7,13,21,23,24,26,30] being conducted utilizing the English version of the task or translations into French, German, Chinese, Japanese, Swedish, Korean, and Polish. Various translations of materials provided by international research teams can be found at http://agelab.mit.edu/study-tools.…”

Section: Introductionmentioning

confidence: 99%

The MIT AgeLab n-back

Reimer

Gulash²,

Foley³

et al. 2014

Adjunct Proceedings of the 6th International Conference on Automotive User Interfaces and Interactive Vehicular Applications

View full text Add to dashboard Cite

This paper briefly describes the background of the MIT AgeLab implementation of a delayed digit recall or nback task, and the capabilities of an android application developed to implement a multi-modal version. The MIT AgeLab n-back task is a well-established methodology for inducing graded levels of cognitive workload. It has been adopted for broad use as a multimodal surrogate demand and calibration task, and recently introduced as a driver and pedestrian distraction education tool.

show abstract

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

Cited by 48 publications

References 30 publications

Classifying driver workload using physiological and driving performance data

Classifying driver workload using physiological and driving performance data

Personalized Driver Workload Inference by Learning From Vehicle Related Measurements

The MIT AgeLab n-back

Contact Info

Product

Resources

About