Evaluation of "As-Intended" Vehicle Dynamics using the Active Inference Framework

TL;DR

This paper presents a computational model based on active inference to evaluate how well drivers' brains understand vehicle dynamics, using free energy as a metric, validated through simulator experiments.

Contribution

It introduces a novel application of the active inference framework to quantify vehicle behavior accuracy via a brain-inspired model and free energy measurement.

Findings

Strong correlation between free energy and expert subjective scores.

Free energy correlates with objective steering performance.

Model effectively assesses if vehicle behavior matches 'as-intended' expectations.

Abstract

We constructed a computational model of the driver's brain for steering tasks using the active inference framework, grounded in the free energy principle - a theory from computational neuroscience. This model enables quantitative estimation of how accurately the brain learns vehicle dynamics and performs appropriate steering, using a measure called variational free energy. Through driving simulator experiments, we observed strong correlations between variational free energy and both expert drivers' subjective "as-intended" scores and general participants' objective control performance. These results suggest that variational free energy provides a promising quantitative metric for evaluating whether a vehicle behaves "as-intended."