Abstract

The automotive domain is an excellent domain for investigating augmented cognition methods, and one of the domains that can provide the applications. We developed, applied and tested indirect (or derived) measures to estimate driver state risks, validated by direct state-sensing methods, with major European vehicle manufacturers, suppliers and research institutes in the project AIDE (Adaptive Integrated Driver-vehicle InterfacE). The project developed an interface with the driver that integrates different advanced driver assistant systems and in-vehicle information systems and adapted the interface to different driver or traffic conditions. This paper presents an overview of the AIDE project and will then focus on the adaptation aspect of AIDE. Information presented to the driver could be adapted on basis of environmental conditions (weather and traffic), and on basis of assessed workload, distraction, and physical condition of the driver. The adaptation of how information is presented to the driver or the timing of when information is presented to the driver is of importance. Adapting information, however, also results in systems that are less transparent to the driver. © 2009 Springer.

Abstract

Cars, trucks and busses are more and more equipped with functions and services that drivers are supposed to operate and understand. The most important developments in this area are the Advanced Driver Assistance Systems (ADAS) and In Vehicle Information Systems (IVIS). In order to make sure that the driver understands and appreciates (comfort) these services and traffic safety is not at risk (distraction, workload), the HMI's (Human Machine Interfaces) of all these functions should be attuned to each other, to the driver, and to the context. For attuning the functions to each other, a HMI platform is needed on which these functions are integrated. For attuning the functions to the driver it is necessary to have knowledge about the momentary state of the driver and of the intentions of the driver at a certain moment. For attuning the functions to the context, it is required to sense the relevant environmental conditions or states. This paper shows that a recent cognitive task load model from process control domain can be applied for the design of adaptive in-car user interfaces. Furthermore, current developments of such interfaces are being discussed. © Springer-Verlag Berlin Heidelberg 2007.