Hierarchical Game-Theoretic Planning for Autonomous Vehicles

TL;DR

This paper presents a hierarchical game-theoretic planning algorithm for autonomous vehicles that enables real-time, safe, and effective decision-making by decomposing complex dynamic games into strategic and tactical components, accounting for human behavior.

Contribution

It introduces a novel hierarchical decomposition of dynamic game-theoretic planning, allowing real-time autonomous vehicle decision-making with non-deterministic human models.

Findings

Richer and safer autonomous behaviors achieved.

Improved planning efficiency over existing methods.

Effective handling of non-rational human decision models.

Abstract

The actions of an autonomous vehicle on the road affect and are affected by those of other drivers, whether overtaking, negotiating a merge, or avoiding an accident. This mutual dependence, best captured by dynamic game theory, creates a strong coupling between the vehicle's planning and its predictions of other drivers' behavior, and constitutes an open problem with direct implications on the safety and viability of autonomous driving technology. Unfortunately, dynamic games are too computationally demanding to meet the real-time constraints of autonomous driving in its continuous state and action space. In this paper, we introduce a novel game-theoretic trajectory planning algorithm for autonomous driving, that enables real-time performance by hierarchically decomposing the underlying dynamic game into a long-horizon "strategic" game with simplified dynamics and full information structure, and a short-horizon "tactical" game with full dynamics and a simplified information structure. The value of the strategic game is used to guide the tactical planning, implicitly extending the planning horizon, pushing the local trajectory optimization closer to global solutions, and, most importantly, quantitatively accounting for the autonomous vehicle and the human driver's ability and incentives to influence each other. In addition, our approach admits non-deterministic models of human decision-making, rather than relying on perfectly rational predictions. Our results showcase richer, safer, and more effective autonomous behavior in comparison to existing techniques.