As a driver, have you ever asked yourself whether to make left turns? Unprotected left turns, that is, left turns with oncoming traffic, are among the most difficult and dangerous driving maneuvers. Although the risk of each individual left turn is negligible, if you are designing the behavior of a large fleet of self-driving cars, small individual risks add up to a significant number of expected injuries in the aggregate. Whether a fleet of cars should make left turns is a question that any developer of self-driving cars and any designer of mapping and routing applications faces today.
A more general issue is at stake here: the decision of whether to make left turns involves a trade-off between safety and mobility (the time it takes to get to a destination). You gain safety at the expense of mobility by driving around the block and thereby avoiding left turns. But you gain mobility at the expense of safety by designing self-driving cars to zip through small gaps in oncoming traffic. Other situations that exemplify this mobility—safety trade-offs include merging onto highway lanes, driving through crosswalks with limited visibility, or avoiding detours by routing through school zones. Such maneuvers are very common, and we will soon be able to regulate them centrally via software as cars become increasingly automated.