Robust Prediction of Lane Departure Based on Driver Physiological Signals 2016-01-0115
Lane change events can be a source of traffic accidents; drivers can make improper lane changes for many reasons. In this paper we present a comprehensive study of a passive method of predicting lane changes based on three physiological signals: electrocardiogram (ECG), respiration signals, and galvanic skin response (GSR). Specifically, we discuss methods for feature selection, feature reduction, classification, and post processing techniques for reliable lane change prediction. Data were recorded for on-road driving for several drivers. Results show that the average accuracy of a single driver test was approx. 70%. It was greater than the accuracy for each cross-driver test. Also, prediction for younger drivers was better.
Citation: Kochhar, D., Zhao, H., Watta, P., and Murphey, Y., "Robust Prediction of Lane Departure Based on Driver Physiological Signals," SAE Technical Paper 2016-01-0115, 2016, https://doi.org/10.4271/2016-01-0115. Download Citation
Author(s):
Dev S. Kochhar, Hong Zhao, Paul Watta, Yi Murphey
Affiliated:
Ford Motor Company, University of Michigan
Pages: 9
Event:
SAE 2016 World Congress and Exhibition
ISSN:
0148-7191
e-ISSN:
2688-3627
Related Topics:
Vehicle drivers
Reliability
SAE MOBILUS
Subscribers can view annotate, and download all of SAE's content.
Learn More »