Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction Study

📅 2026-08-06
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the challenge of predicting high-risk cut-in maneuvers by human drivers in competitive driving scenarios by proposing a data-driven modeling approach that integrates game theory with inverse reinforcement learning. For the first time, game-theoretic inverse reinforcement learning is applied to cut-in behavior prediction, leveraging high-dimensional driving features and trained on the high-fidelity highD dataset. The work systematically uncovers the trade-off mechanism between instantaneous and temporally consistent features in balancing precision and recall. Experimental results demonstrate that the proposed method achieves an overall prediction accuracy exceeding 75%, with a cut-in prediction precision of 51% and recall of 49%, substantially outperforming conventional physics-based game-theoretic approaches, which yield only 4.4% precision.
📝 Abstract
Capturing the strategic decision-making inherent in competitive human driving is critical for autonomous vehicle safety and traffic simulation. This study demonstrates that game-theoretic Inverse Reinforcement Learning (IRL) provides a robust framework for this challenge. We present a comprehensive analysis comparing data-driven IRL models against an established physics-based game-theoretic approach for predicting aggressive, safety-critical cut-in lane changes. Using the high-fidelity highD dataset, we systematically develop and evaluate a series of IRL models with increasing feature complexity. Our results reveal significant advantages: the best-performing IRL models achieve an overall prediction accuracy exceeding 75 percent while maintaining a Cut-In precision up to 51 percent and recall up to 49 percent. This represents a significant improvement over the established physics-based benchmark, which achieved only 4.4 percent precision in these high-stakes scenarios. The analysis reveals a clear trade-off: incorporating granular, instantaneous features yields higher precision, while adding temporal consistency features maximizes recall. These findings suggest that IRL-based models can effectively bridge the gap between microscopic driver intent and macroscopic safety outcomes, providing a more reliable foundation for modeling interactions in mixed-autonomy environments.
Problem

Research questions and friction points this paper is trying to address.

competitive driving
cut-in prediction
strategic decision-making
autonomous vehicle safety
human driving modeling
Innovation

Methods, ideas, or system contributions that make the work stand out.

Game-Theoretic Inverse Reinforcement Learning
Cut-in Prediction
Competitive Driving Modeling
HighD Dataset
Mixed-Autonomy Interaction
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
Y
Yu (Fred) Song
Department of Civil and Architectural Engineering and Construction Management, University of Wyoming