Resolving Conflict in Decision-Making for Autonomous Driving

TL;DR

This paper analyzes conflicts in game-theoretic decision-making models for autonomous driving, introduces a new approach called Augmented Altruism to reduce conflict, and validates it through theoretical analysis and human experiments.

Contribution

It identifies conflict issues in Stackelberg game models, proposes Augmented Altruism to mitigate these conflicts, and demonstrates improved alignment with human decision-making.

Findings

Conflict causes sub-optimal behavior in existing models

Augmented Altruism reduces conflict in Stackelberg games

Model aligns better with human decision-making patterns

Abstract

Recent work on decision making and planning for autonomous driving has made use of game theoretic methods to model interaction between agents. We demonstrate that methods based on the Stackelberg game formulation of this problem are susceptible to an issue that we refer to as conflict. Our results show that when conflict occurs, it causes sub-optimal and potentially dangerous behaviour. In response, we develop a theoretical framework for analysing the extent to which such methods are impacted by conflict, and apply this framework to several existing approaches modelling interaction between agents. Moreover, we propose Augmented Altruism, a novel approach to modelling interaction between players in a Stackelberg game, and show that it is less prone to conflict than previous techniques. Finally, we investigate the behavioural assumptions that underpin our approach by performing experiments with human participants. The results show that our model explains human decision-making better than existing game-theoretic models of interactive driving.