Throughout the twentieth century, the automobile and its infrastructure were developed in such a way as to become the dominant transport mode for passengers as well as goods in most countries. Improvements in vehicle quality have helped to increase comfor, safety, capacity, and to reduce pollutions. However, the automobile is still very inefficient in terms of safety (with more than one million deaths on the roads per year), of energy (with an efficiency up to ten times worst than rail) and in terms of space usage, in particular in its private form (where it stands still for most of the time).
In order to meet a continuously growing demand for transport, the solutions for industrialized countries now lie in better use of intermodality but also in new technologies for vehicle control.
Indeed, the control techniques for vehicles have not changed basically in the last one hundred years with the driver having the total responsibility of his/her vehicle through mechanical impediments (steering wheel and pedals). These primitive controls lead to inefficiencies and accidents. As vehicle safety and traffic engineering has improved, the proportion of accidents due to driver error has increased with a result that automotive engineering has focused on accident migration rather than avoidance.
The only way to dramatically improve (defined as maximum throughput per unit of space) while at the same time drastically reduce the number of accidents is to remove the driver from the control loop.
The major problem which has been encountered in the study of automated highway systems is the deployment of this technology. Recent work show however that there are several realistic paths towards this deployment and that the technologies are arriving at a faster pace than expected ten years ago. We can now identify three paths which can lead to full driving automation in large parts of the road network:
Our research projects focus on the development and experimentation of techniques for all of these approaches.