Active inference as a model of collision avoidance behavior in human drivers
- 1Department of Cognitive Robotics, Delft University of Technology, Delft, Netherlands
- 2Waymo LLC, Mountain View, CA, USA. [email protected]
- 3Waymo LLC, Mountain View, CA, USA
Abstract
Collision avoidance - involving a rapid threat detection and quick execution of the appropriate evasive maneuver - is a critical aspect of driving. However, existing models of human collision avoidance behavior are fragmented, focusing on specific scenarios or only describing certain aspects of the avoidance behavior, such as response times. This paper addresses these gaps by proposing a computational cognitive model of human collision avoidance behavior based on active inference. Active inference provides a unified approach to modeling human behavior: the minimization of free energy. Building on prior active inference work, our model incorporates established cognitive mechanisms such as evidence accumulation to simulate human responses in three distinct collision avoidance scenarios: front-to-rear lead vehicle braking, lateral incursion by an oncoming vehicle, and another vehicle failing to yield at an intersection. We demonstrate that our model explains a wide range of empirical findings on human collision avoidance behavior. Specifically, the model closely reproduces both aggregate results from meta-analyses previously reported in the literature and detailed, scenario-specific effects observed in two recent driving simulator studies, including response timing, maneuver selection, and execution. Our results highlight the potential of active inference as a generalizable framework for understanding and modeling human behavior in complex real-life driving tasks.
Related
- Threat imminence and estimates of agency dictate proactive and reactive defensive behaviors in active place avoidance
- The diminishing returns of distance: Computational analysis of approach-avoidance behavior under threat of predation
- Reframing the lived experience of persistent dizziness: insights from active inference.
- A neuro-inspired computational framework for AGI: predictive coding, active inference and free energy minimisation.
- Two Routes to Interoceptive Prioritisation: Dissociating Likelihood Precision and Preference Reweighting in Active Inference
BibTeX
@article{schumann2026active,
title = {{Active inference as a model of collision avoidance behavior in human drivers}},
author = {Julian Frederik Schumann and Johan Engström and Leif Johnson and Matthew O’Kelly and João V. Messias and Jens Kober and Arkady Zgonnikov},
journal = {Nature Communications},
year = {2026},
month = jun,
doi = {10.1038/s41467-026-73345-0},
url = {https://doi.org/10.1038/s41467-026-73345-0},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Active inference as a model of collision avoidance behavior in human drivers
AU - Julian Frederik Schumann
AU - Johan Engström
AU - Leif Johnson
AU - Matthew O’Kelly
AU - João V. Messias
AU - Jens Kober
AU - Arkady Zgonnikov
PY - 2026
DA - 2026/06/10
JO - Nature Communications
DO - 10.1038/s41467-026-73345-0
UR - https://doi.org/10.1038/s41467-026-73345-0
AB - Collision avoidance - involving a rapid threat detection and quick execution of the appropriate evasive maneuver - is a critical aspect of driving. However, existing models of human collision avoidance behavior are fragmented, focusing on specific scenarios or only describing certain aspects of the avoidance behavior, such as response times. This paper addresses these gaps by proposing a computational cognitive model of human collision avoidance behavior based on active inference. Active inference provides a unified approach to modeling human behavior: the minimization of free energy. Building on prior active inference work, our model incorporates established cognitive mechanisms such as evidence accumulation to simulate human responses in three distinct collision avoidance scenarios: front-to-rear lead vehicle braking, lateral incursion by an oncoming vehicle, and another vehicle failing to yield at an intersection. We demonstrate that our model explains a wide range of empirical findings on human collision avoidance behavior. Specifically, the model closely reproduces both aggregate results from meta-analyses previously reported in the literature and detailed, scenario-specific effects observed in two recent driving simulator studies, including response timing, maneuver selection, and execution. Our results highlight the potential of active inference as a generalizable framework for understanding and modeling human behavior in complex real-life driving tasks.
SN - 2041-1723
ER -