This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Driver Workload in an Autonomous Vehicle
ISSN: 0148-7191, e-ISSN: 2688-3627
Published April 02, 2019 by SAE International in United States
This content contains downloadable datasetsAnnotation ability available
As intelligent automated vehicle technologies evolve, there is a greater need to understand and define the role of the human user, whether completely hands-off (L5) or partly hands-on. At all levels of automation, the human occupant may feel anxious or ill-at-ease. This may reflect as higher stress/workload. The study in this paper further refines how perceived workload may be determined based on occupant physiological measures. Because of great variation in individual personalities, age, driving experiences, gender, etc., a generic model applicable to all could not be developed. Rather, individual workload models that used physiological and vehicle measures were developed. Unlike some existing methods of workload estimation where one, or a few signals are used, such as electroencephalography (EEG), electrocardiography (ECG), we developed intelligent systems that use multiple physiological and vehicle signals based on an end-to-end deep neural learning architecture to make a robust estimation of workload. The deep neural learning system, MTS-CNN, is designed to learn workload patterns from synchronized, heterogeneous temporal signals. All data collected for training and testing are from real-world driving trips along the same route which comprised urban local roads and highways. Data from twenty participants whose driving experience ranged from a few months to several years were collected and analyzed. The experimental results indicate that the proposed driver workload estimation model is capable of learning well from the combined temporal physiological and vehicle signals and good performance was obtained on workload estimation.
CitationMurphey, Y., Kochhar, D., and Xie, Y., "Driver Workload in an Autonomous Vehicle," SAE Technical Paper 2019-01-0872, 2019, https://doi.org/10.4271/2019-01-0872.
Data Sets - Support Documents
|[Unnamed Dataset 1]|
|[Unnamed Dataset 2]|
|[Unnamed Dataset 3]|
- Yi, D., Su, J., Liu, C., and Chen, W., “Personalized Driver Workload Inference by Learning from Vehicle Related Measurements,” IEEE Transactions on Systems, Man, and Cybernetics: Systems1-10, 2017.
- Paxion, J., Galy, E., and Berthelon, C., “Mental Workload and Driving,” Frontiers in Psychology 5:1344, 2014.
- Heine, T., Lenis, G., Reichensperger, P., Beran, T. et al., “Electrocardiographic Features for the Measurement of Drivers' Mental Workload,” Applied Ergonomics 61:31-43, 2017.
- Zhang, J., Yin, Z., and Wang, R., “Recognition of Mental Workload Levels Under Complex Human-Machine Collaboration by Using Physiological Features and Adaptive Support Vector Machines,” IEEE Transactions on Human-Machine Systems 45(2):200-214, 2015.
- Murphey, Y.L., Xie, Y., and Kochhar, D., “Personalized Driver Workload Estimation in Real-World Driving,” SAE Technical Paper 2018-01-0511, 2018, doi:10.4271/2018-01-0511.
- Xie, Y., Murphey, Y.L., and Kochhar, D.S., “SVM Parameter Optimization Using Swarm Intelligence for Learning from Big Data,” in International Conference on Computational Collective Intelligence, 2018.
- Nair, V. and Hinton, G., “Rectified Linear Units Improve Restricted Boltzmann Machines,” in Proceedings of the 27th International Conference on Machine Learning, 2010.
- Zheng, Y., Liu, Q., Chen, E., Ge, Y. et al., “Exploiting Multi-Channels Deep Convolutional Neural Networks for Multivariate Time Series Classification,” Frontiers of Computer Science 10(1):96-112, 2016.
- Ma, J., Murphey, Y.L. and Zhao, H., “Real Time Drowsiness Detection Based on Lateral Distance Using Wavelet Transform and Neural Network,” in Computational Intelligence, 2015 IEEE Symposium Series on, 2015.