Stackelberg Punishment and Bully-Proofing Autonomous Vehicles

TL;DR

This paper introduces a method to compute Stackelberg punishments to promote cooperative behavior in autonomous vehicles, effectively discouraging aggressive driving through strategic behavior that minimizes punishment costs.

Contribution

It generalizes Stackelberg equilibrium to develop a punishment strategy that enforces cooperation with minimal costs, demonstrated in autonomous vehicle scenarios.

Findings

Self-driving cars with Stackelberg punishment policies reduce bullying behavior.

The approach efficiently computes punishments using existing algorithms.

Experimental results show improved social negotiation in driving scenarios.

Abstract

Mutually beneficial behavior in repeated games can be enforced via the threat of punishment, as enshrined in game theory's well-known "folk theorem." There is a cost, however, to a player for generating these disincentives. In this work, we seek to minimize this cost by computing a "Stackelberg punishment," in which the player selects a behavior that sufficiently punishes the other player while maximizing its own score under the assumption that the other player will adopt a best response. This idea generalizes the concept of a Stackelberg equilibrium. Known efficient algorithms for computing a Stackelberg equilibrium can be adapted to efficiently produce a Stackelberg punishment. We demonstrate an application of this idea in an experiment involving a virtual autonomous vehicle and human participants. We find that a self-driving car with a Stackelberg punishment policy discourages human drivers from bullying in a driving scenario requiring social negotiation.