Decision support issues in automated driving systems

Machine learning and computational processing have advanced such that automated driving systems (ADSs) are no longer a distant reality. Many automobile manufacturers developed prototypes; however, there exist numerous decision support issues requiring resolution to ensure mass ADS adoption. In the coming decades, it is likely production ADSs will only be partially autonomous. Such operate within predetermined conditions require driver intervention when they violated. Since forecasts of their 20-year market penetration relatively low, in heterogeneous traffic characterized by vehicles varying autonomy levels. Under these conditions, effective must consider intangible, subjective, emotional factors as well influences human cognition; otherwise, risks distrust unsatisfactory performance based on an incomplete understanding its environment. We survey literature relevant issues, identify open problems, propose research directions for resolution.