Search papers, labs, and topics across Lattice.
This paper presents an experimental evaluation of the Sequential Chicken game-theoretic model for autonomous vehicle (AV) interaction with pedestrians, implemented on a real AV. The study demonstrates that pedestrians adapt their behavior according to the model's predictions, balancing the risk of collision with the cost of yielding delays. The fitted model reveals a low time value of collision, indicating that pedestrians consider proxemic personal space penalties in addition to actual collisions.
Autonomous vehicles can learn to navigate pedestrian interactions more efficiently by subtly threatening collisions, as humans do, without compromising safety.
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.
