Human injury-based safety decision of automated vehicles.

Automated vehicles (AVs) are anticipated to improve road traffic safety. However, prevailing decision-making algorithms have largely neglected the potential to mitigate injuries when confronting inevitable obstacles. To explore whether, how, and to what extent AVs can enhance human protection, we propose an injury risk mitigation-based decision-making algorithm. The algorithm is guided by a real-time, data-driven human injury prediction model and is assessed using detailed first-hand information collected from real-world crashes. The results demonstrate that integrating injury prediction into decision-making is promising for reducing traffic casualties. Because safety decisions involve harm distribution for different participants, we further analyze the potential ethical issues quantitatively, providing a technically critical step closer to settling such dilemmas. This work demonstrates the feasibility of applying mining tools to identify the underlying mechanisms embedded in crash data accumulated over time and opens the way for future AVs to facilitate optimal road traffic safety.