Adaptive control in human-machine systems
Human Factors Psychology
Telerobotics, automation, and human supervisory control
Telerobotics, automation, and human supervisory control
User Modeling and User-Adapted Interaction
A model for types and levels of human interaction with automation
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
FAC '09 Proceedings of the 5th International Conference on Foundations of Augmented Cognition. Neuroergonomics and Operational Neuroscience: Held as Part of HCI International 2009
| Hi-index | 0.00 |
One of the current research areas in automotive field is aimed at improving driving safety with regards to the development of preventive support systems, also called ADAS (Advanced Driver Assistance Systems). These systems are able to detect a critical situation and to inform timely the driver, so that a repairing maneuver can be performed. From the human factors point of view, driving is considered as a complex cognitive task that can be summarized by four main sub-processes: perception, analysis, decision and action. To be performed, each phase presumes the achievement of the previous one, An exception occurs when humans overcome planning / decision phase and go directly from analysis / interpretation to action / execution (almost in automatic way). This paper intends to propose, following the main literature on human-centered automation, how the ADAS intervention can be designed without negative impact on driving safety. In particular, a forward collision warning has been studied. For this study, the Levels Of Automation (LOA) classified by Parasuramam and Sheridan (2000) has been used as well as the studies in the domain of the so-called Adaptive Automation (AA) (Kaber Riley, Endsley 2001; Scerbo 1996), that allow to adapt the information to the driver's workload and to the context level of dangerousness.