General and Multi-Criteria Approach to Study the Admissibility and Quality of a Driving Intention

Determining the admissibility and quality of driving intentions, generated by an automated intelligent vehicle and by a human driver, is a sine qua none task in a human-intelligent vehicle share navigation. Our paper proposes a generic method to quantify driving intentions. These intentions are defined by a sequence of velocities. This formulation is based on metrics already discussed in the literature. It proposes a way to use them to evaluate a state, making a judgment, and to extend this evaluation to a sequence of states. This quantification determines whether the intention is safely achievable and defines a quality taking into account several criteria (safety, comfort, context, energy consumption). It is thus possible to compare and rank the intentions according to a set of criteria. This article defines a proposed implementation that has been tested on a driving simulator. For a given scenario, we tested our solution on several intentions in order to show the interest of our solution, and the possibility to compare the intentions between them.