Twenty-Five Years of the Intelligent Driver Model: Foundations, Extensions, Applications, and Future Directions

TL;DR

The paper surveys twenty-five years of the Intelligent Driver Model (IDM), detailing its nonlinear acceleration law and dynamic spacing that enable collision-free car-following behavior while capturing a range of traffic states. It analyzes IDM’s theoretical foundations, its connections to classic models, and its numerical properties, highlighting both its strengths in interpretability and practical realism and its limitations in stochasticity and human factors. The review categorizes extensions into deterministic physics-based, stochastic variants, and hybrid data-driven approaches, including RL- and ML-enhanced IDM forms, with substantial attention to automated driving applications. It argues for reimagining IDM as a modular, extensible framework that integrates big data, digital twins, and human–machine interaction to address modern, connected traffic systems, and it calls for standardized evaluation frameworks to fairly compare deterministic and stochastic CF models across diverse regimes.

Abstract

The Intelligent Driver Model (IDM), proposed in 2000, has become a foundational tool in traffic flow modeling, renowned for its simplicity, computational efficiency, and ability to capture diverse traffic dynamics. Over the past 25 years, IDM has significantly advanced car-following theory and found extensive application in intelligent transportation systems, including driver assistance systems and autonomous vehicle control. However, IDM's deterministic framework and simplified assumptions face limitations in addressing real-world complexities such as stochastic variability, driver heterogeneity, and mixed traffic conditions. This paper provides a systematic review and critical reflection on IDM's theoretical foundations, academic influence, practical applications, and model extensions. While highlighting IDM's contributions, we emphasize the need to extend the model into a modular and extensible framework. Future directions include integrating stochastic elements, human behavioral insights, and hybrid modeling approaches that combine physics-based structures with data-driven methodologies. By reimagining IDM as a flexible modeling basis, this paper aims to inspire its continued development to meet the demands of intelligent, connected, and increasingly complex traffic systems.

Figures (3)

• Figure 1: The red bars indicate the number of papers citing IDM in the Web of Science between 2000 and 2024. The blue bars indicate relevant papers published in the target list of journals (see Appendix) that at least use IDM for simulation or theoretical analysis rather than just citing it.
• Figure 2: Simulation results (solid lines) of the standard deviation $\sigma_v$ of the time series of the velocity of each car of IDM from jiangTrafficExperimentRevealsNature2014. The curves represent the simulation results while the markers such as circles represent the experimental results. The different colors represent different experiment runs in which the velocity of leading vehicle $v_l$ is 7,15,30,40 and 50 km/h.
• Figure 3: Dynamic phase diagram of on-ramp-induced congested traffic patterns simulated by IDM from treiberThreephaseTrafficTheoryTwophase2010. The abbreviations denote free traffic (FT), pinned localized cluster (PLC), moving localized cluster (MLC), homogeneous congested traffic (HCT), oscillatory congested traffic (OCT), and triggered stop-and-go (TSG) pattern.