Key points are not available for this paper at this time.
The recent DARPA-sponsored automated vehicle "Challenges" have generated strong interest in both the research community and the general public, raising consciousness about the possibilities for vehicle automation. Driverless vehicles make good subjects for the visually-oriented media, and they pose enough interesting research challenges to occupy generations of graduate students. However, automated vehicles also have the potential to help solve a variety of real-world problems. Engineers need to think carefully about which of those problems we are actually solving.A well-engineered system should be designed to satisfy specific needs, and those needs should be reflected in the definition of system requirements. Alternative technological approaches can then be evaluated and traded off based on their ability to meet the requirements. The article describes the rather different needs of the public road transportation system and the military transportation system, and then shows how those needs influence the requirements for automated vehicle systems. These requirements point toward significantly different technical approaches, but it is possible to find some limited areas of technical commonality.
Steven E Shladover (Thu,) studied this question.