摘要: |
In this UTC project, we successfully developed the technology of near real-time detection of driver interruptibility based on a range of sensor data streams. We used instances of drivers engaged in peripheral interactions as moments of ground truth for their split attention while managing interruptions. As a result, we demonstrated that sensor data could build a machine learning classifier to determine driver interruptibility every second with almost 95% accuracy. We also successfully identified sensor features that best explained the states where drivers performed peripheral interactions, which contributed to the high performance of our system. Based on our findings, we continue the project by applying this technology to improve the intelligence of in-car cyber-physical systems that mediate when drivers use technology to self-interrupt and when drivers are interrupted externally by technology. We are refining our key technology to create sensor-based models that retain information about the real-time mechanisms whereby drivers’ perceived value of the presented information interacts with the nature of the information and the attributes of the sensor-detected interruptible moments. As the delivery, we plan to develop a workload manager that mediates interruptions in cars, thereby increasing driver appreciation of the quality of presented information. |