Pedestrians play chicken with an autonomous vehicle
TLDR
This paper demonstrates how autonomous vehicles can use game theory to resolve the 'Freezing Robot Problem' by strategically asserting priority.
Key contributions
- Autonomous vehicles' unconditional yielding leads to the 'Freezing Robot Problem'.
- Proposes the Sequential Chicken game theory model for AVs to assert priority.
- First real-world demonstration with human subjects using an actual AV.
- Pedestrian behavior fits the model, suggesting avoidance of personal space and collision risks.
Why it matters
This research addresses a critical AV challenge: interacting with pedestrians without constant stalling. Demonstrating a game-theoretic solution in a real-world setting offers a practical path for AVs to navigate urban environments more effectively. This could lead to smoother traffic and more natural human-AV interactions.
Original Abstract
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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.