EyesOnRoad - an anti-distraction Field Operational Test

Important results from the project

The data collected during the project is to our knowledge unique in the world, and will be used for continued research in follow-up projects. The project has successfully shown that; -a machine vision based sensor for driver visual (in-) attention can read driver attention status continuously in daily traffic situations -the collected EOR time durations are similar to earlier data, collected in similar situations but manually annotated -the number of warning events per time travelled may be reduced by an audiovisual warning for Eyes-Off-Road time greater than 3 seconds

Expected long term effects

The project set out to evaluate the possibility to influence the driver´s visual behaviour toward a reduction of critically long glances away from the road. Defining critically long glances away from the road as `warnable events´ and looking at the frequency of distraction warnings over the baseline, treatment and repeated baseline conditions, a tendency was found that the number of warnings were reduced in treatment condition compared to both baselines. This difference was not significant on a group level, but it is nevertheless interesting.

Approach and implementation

To evaluate the possibility of influencing the driver´s visual behavior toward a reduction of critically long glances away from the road. A Field Operational Test was carried out with an online warning alerting the driver if s/he was looking away from the roadway for too long. The experimental protocols used was within group ABA design, meaning data was collected in three phases, baseline, treatment and repeated baseline. This allows for testing the effect of warnings compared to no warnings, and also a possibility to see whether the effects of warnings persist after removal.