Predicting the Effects of Driver Distraction by On-Board Devices: An Integrated Model Approach
As drivers gain access to increasingly numerous and complex on-boarddevices for support (e.g., navigation) and "infotainment" (e.g., newsand e-mail), many have raised serious concerns about the issue ofdriver distraction - excessive attention to secondarydevices rather than the primary -driving task. In this talk I willdiscuss how we can better understand and alleviate driver distractionby modeling driver behavior in a cognitive architecture. A cognitivearchitecture is a computational framework that incorporates built-in,well-tested parameters and constraints for cognitive andperceptual-motor processes. We have developed a driver model in theACT-R architecture that combines lower-level controllers for speed andlateral position with a higher-level cognitive process for situationawareness and task management. When integrated with models ofsecondary-task behavior, the driver model generates apriori behavioral predictions about how secondary tasks affectdriver performance. Such predictions can in turn be used to evaluateand compare on-board devices to facilitate development and testing. Toillustrate this approach, I will describe an integrated model ofcell-phone dialing and driving and validate the model's predictionswith control and eye-movement data collected from human drivers in afixed-base driving simulator.