Pedestrians play chicken with an autonomous vehicle
For developers of autonomous vehicle decision-making algorithms, this work provides a first real-world demonstration of a game-theoretic approach to pedestrian interaction, though it is incremental as it applies existing theory to a new domain.
This paper demonstrates and evaluates the use of Sequential Chicken game theory to resolve the Freezing Robot Problem in autonomous vehicles, showing that pedestrian behavior under constrained safety conditions fits the model with a low time value of collision.
Automated vehicles (AVs) are commonly programmed to yield unconditionally to pedestrians in the interest of safety. However, this design choice can give rise to the Freezing Robot Problem in which pedestrians learn to assert priority at every interaction, causing vehicles to stall and make no progress. The game theoretic Sequential Chicken model has shown that, like human drivers, AVs can resolve this problem by trading credible threats of very small risks of collision or larger risks of less severe invasion of personal space against the value of time due to yielding delays. This paper presents the first demonstration and evaluation of this approach using a real AV with human subjects and shows that pedestrian behavior under experimentally constrained safety conditions can be well fitted by Sequential Chicken, with a low time value of collision, suggestive of their planning to avoid proxemic personal space penalties as well as actual collisions.