A Taxonomy and Review of Algorithms for Modeling and Predicting Human Driver Behavior

TL;DR

This paper provides a comprehensive taxonomy and review of algorithms for modeling and predicting human driver behavior, unifying various aspects like intent, traits, and motion prediction within a stochastic game framework.

Contribution

It introduces a unified approach to driver modeling by framing it as inference in a multi-agent stochastic game, covering multiple modeling tasks and classifying existing methods.

Findings

Unified modeling framework for driver behavior

Classification of driver models based on tasks and attributes

Identification of open research challenges

Abstract

An open problem in autonomous driving research is modeling human driving behavior, which is needed for the planning component of the autonomy stack, safety validation through traffic simulation, and causal inference for generating explanations for autonomous driving. Modeling human driving behavior is challenging because it is stochastic, high-dimensional, and involves interaction between multiple agents. This problem has been studied in various communities with a vast body of literature. Existing reviews have generally focused on one aspect: motion prediction. In this article, we present a unification of the literature that covers intent estimation, trait estimation, and motion prediction. This unification is enabled by modeling multi-agent driving as a partially observable stochastic game, which allows us to cast driver modeling tasks as inference problems. We classify driver models into a taxonomy based on the specific tasks they address and the key attributes of their approach. Finally, we identify open research opportunities in the field of driver modeling.