Characterizing Human Feedback-Based Control in Naturalistic Driving Interactions via Gaussian Process Regression with Linear Feedback

2025-12-09

AI Summary

This study investigates the feedback control mechanisms underlying natural human driver interactions at unsignalized intersections, aiming to inform socially aware autonomous vehicle decision-making. Method: Leveraging naturalistic driving data collected from a driving simulator, we propose a Weighted Gaussian Process Regression (W-GPR) framework that integrates both linear and nonlinear prior knowledge to construct an interpretable, state-dependent feedback controller. Contribution/Results: Our approach enables the first quantitative estimation of individual feedback gains and reveals statistically significant associations between these gains and behavioral traits—including driving style and risk preference—while characterizing strategic heterogeneity across driver subpopulations. Experimental results demonstrate that W-GPR substantially enhances both interpretability and generalization capability of the learned controller, establishing a novel data-driven paradigm for modeling human-like interactive driving strategies.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: Behavior Learning & Control

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Understanding driver interactions is critical to designing autonomous vehicles to interoperate safely with human-driven cars. We consider the impact of these interactions on the policies drivers employ when navigating unsigned intersections in a driving simulator. The simulator allows the collection of naturalistic decision-making and behavior data in a controlled environment. Using these data, we model the human driver responses as state-based feedback controllers learned via Gaussian Process regression methods. We compute the feedback gain of the controller using a weighted combination of linear and nonlinear priors. We then analyze how the individual gains are reflected in driver behavior. We also assess differences in these controllers across populations of drivers. Our work in data-driven analyses of how drivers determine their policies can facilitate future work in the design of socially responsive autonomy for vehicles.

Problem

• Models human driver behavior as feedback controllers using Gaussian Process regression.
• Analyzes driver interactions at unsigned intersections via driving simulator data.
• Assesses controller differences across driver populations for autonomous vehicle design.

Innovation

• Models driver responses as Gaussian Process feedback controllers
• Computes feedback gain using linear and nonlinear priors
• Analyzes driver behavior differences across populations