Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Kyle Brown, Katherine Driggs-Campbell, Mykel J. Kochenderfer

TL;DR

A mathematical framework for describing the dynamics of interactive multi-agent traffic based on the partially observable stochastic game is introduced and provides a basis for discussing different driver modeling techniques.

Abstract

We present a review and taxonomy of 200 models from the literature on driver behavior modeling. We begin by introducing a mathematical framework for describing the dynamics of interactive multi-agent traffic. Based on the partially observable stochastic game, this framework provides a basis for discussing different driver modeling techniques. Our taxonomy is constructed around the core modeling tasks of state estimation, intention estimation, trait estimation, and motion prediction, and also discusses the auxiliary tasks of risk estimation, anomaly detection, behavior imitation and microscopic traffic simulation. Existing driver models are categorized based on the specific tasks they address and key attributes of their approach.

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

TL;DR

A mathematical framework for describing the dynamics of interactive multi-agent traffic based on the partially observable stochastic game is introduced and provides a basis for discussing different driver modeling techniques.

Abstract

We present a review and taxonomy of 200 models from the literature on driver behavior modeling. We begin by introducing a mathematical framework for describing the dynamics of interactive multi-agent traffic. Based on the partially observable stochastic game, this framework provides a basis for discussing different driver modeling techniques. Our taxonomy is constructed around the core modeling tasks of state estimation, intention estimation, trait estimation, and motion prediction, and also discusses the auxiliary tasks of risk estimation, anomaly detection, behavior imitation and microscopic traffic simulation. Existing driver models are categorized based on the specific tasks they address and key attributes of their approach.

Paper Structure

This paper contains 18 sections, 1 figure, 10 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Mathematical Formulation
  3. Driver Behavior Models
  4. Approaches to the Core Modeling Tasks
  5. State Estimation
  6. Intention Estimation
  7. Intention Space
  8. Intention Hypothesis Representation
  9. Intention Inference Paradigms
  10. Trait Estimation
  11. Trait Space
  12. Trait Hypothesis
  13. Trait Inference Paradigms
  14. Motion Prediction
  15. State-Transition models
  16. ...and 3 more sections

Figures (1)

  • Figure 1: The evolution of an n-agent Partially Observable Stochastic Game (POSG) visualized as a graphical model. Each layer (into the page) of the graphical model corresponds to a different agent. Time increases from left to right. Edges represent the direction of information flow.