Adapting AI Behaviors To Players in Driver San Francisco: Hinted-Execution Behavior Trees

The creative nature of games makes trying new ideas desirable, but these changes are sometimes very risky. We need to find ways to minimize risks while we build innovative experiences. Driver San Francisco did this by using Hinted-execution Behavior Trees; this technique allows developers to modify existing AI behaviors dynamically with very low risk, and was used to adapt Driver’s getaway AI to players’ skills. AI in Driver San Francisco Driver San Francisco is the latest installment of the Driver franchise, developed by Reflections, a Ubisoft Studio, and released in September 2011. In Driver, players take the role of detective John Tanner in his race to take down criminal lord Charles Jericho. The game was critically praised for its innovative shift mechanic (Grisham 2011), which allowed players to instantly jump to any other vehicle at any part of the city. A small team of engineers developed the AI in Driver. Our mandate was to create artificial drivers that can navigate through a busy city that are as skilled as the best human player. All the technology was brand new and tailor-made to enhance Driver’s experience.