Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Survey on Data-Driven Modeling of Human Drivers' Lane-Changing Decisions

Linxuan Huang, Dong-Fan Xie, Li Li, Zhengbing He

TL;DR

The paper addresses the challenge of modeling lane-changing decisions driven by human drivers using data-driven methods. It surveys ML, DL, RL, and data-physics hybrids, detailing data sources, inputs/outputs, objectives, validation, and model architectures. It identifies robustness and uncertainty as major hurdles and highlights opportunities for hybrid, multimodal, and interactive LCD modeling. The findings underscore the potential of data-driven LCD to enhance safety, efficiency, and interoperability of mixed-traffic environments with autonomous vehicles.

Abstract

Lane-changing (LC) behavior, a critical yet complex driving maneuver, significantly influences driving safety and traffic dynamics. Traditional analytical LC decision (LCD) models, while effective in specific environments, often oversimplify behavioral heterogeneity and complex interactions, limiting their capacity to capture real LCD. Data-driven approaches address these gaps by leveraging rich empirical data and machine learning to decode latent decision-making patterns, enabling adaptive LCD modeling in dynamic environments. In light of the rapid development of artificial intelligence and the demand for data-driven models oriented towards connected vehicles and autonomous vehicles, this paper presents a comprehensive survey of data-driven LCD models, with a particular focus on human drivers LC decision-making. It systematically reviews the modeling framework, covering data sources and preprocessing, model inputs and outputs, objectives, structures, and validation methods. This survey further discusses the opportunities and challenges faced by data-driven LCD models, including driving safety, uncertainty, as well as the integration and improvement of technical frameworks.

A Survey on Data-Driven Modeling of Human Drivers' Lane-Changing Decisions

TL;DR

The paper addresses the challenge of modeling lane-changing decisions driven by human drivers using data-driven methods. It surveys ML, DL, RL, and data-physics hybrids, detailing data sources, inputs/outputs, objectives, validation, and model architectures. It identifies robustness and uncertainty as major hurdles and highlights opportunities for hybrid, multimodal, and interactive LCD modeling. The findings underscore the potential of data-driven LCD to enhance safety, efficiency, and interoperability of mixed-traffic environments with autonomous vehicles.

Abstract

Lane-changing (LC) behavior, a critical yet complex driving maneuver, significantly influences driving safety and traffic dynamics. Traditional analytical LC decision (LCD) models, while effective in specific environments, often oversimplify behavioral heterogeneity and complex interactions, limiting their capacity to capture real LCD. Data-driven approaches address these gaps by leveraging rich empirical data and machine learning to decode latent decision-making patterns, enabling adaptive LCD modeling in dynamic environments. In light of the rapid development of artificial intelligence and the demand for data-driven models oriented towards connected vehicles and autonomous vehicles, this paper presents a comprehensive survey of data-driven LCD models, with a particular focus on human drivers LC decision-making. It systematically reviews the modeling framework, covering data sources and preprocessing, model inputs and outputs, objectives, structures, and validation methods. This survey further discusses the opportunities and challenges faced by data-driven LCD models, including driving safety, uncertainty, as well as the integration and improvement of technical frameworks.
Paper Structure (22 sections, 18 equations, 5 figures, 3 tables)

This paper contains 22 sections, 18 equations, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. The evolution of data-driven LCD models
  3. Data-driven LCD models
  4. LCD models based on classical ML
  5. LCD models based on DL methods
  6. LCD models based on RL
  7. Data-physics hybrid model
  8. The framework of data-driven LCD models
  9. Data sources
  10. Data preprocessing methods
  11. Inputs and outputs
  12. Model structure
  13. Objectives of LCD
  14. Validation methods
  15. Opportunities and challenges
  16. ...and 7 more sections

Figures (5)

  • Figure 1: Keyword time zone distribution map of data-driven LC models.
  • Figure 2: The architecture of LCD model considering driving styleZHANG_2023_LEARNING.
  • Figure 3: The parallel network with dynamical weightsHAN_2024_MODELING.
  • Figure 4: Framework of data-driven LC models.
  • Figure 5: Modular and end-to-end method architecture.