---
title: "Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle Interactions"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.25917v1"
permalink: "https://feed.astralor.com/items/itm_4f170f01d34f646efdbfc7a0"
published: "2026-08-26T15:32:46.000Z"
score: 75
channel: "ai"
tags: ["Interaction Measurement","Game Theory","Dataset Evaluation","Autonomous Driving","Trajectory Prediction"]
---

# Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle Interactions

## AI commentary

> This paper brings game theory back to real data, reminding us not to chase a universal model blindly. For engineers working on autonomous driving decision or trajectory prediction, it offers a reusable diagnostic toolkit to determine which interaction structure fits your scenarios. I strongly suggest testing it with your own datasets.

## At a glance

This paper presents a trajectory-based interaction measurement framework to identify interaction events from real-world driving data and quantify behavioral change onset, temporal organization, post-onset response dynamics, and ordering stability. The framework is evaluated on six public datasets—INTERACTION, highD, inD, rounD, Waymo Open Motion, and nuPlan—covering diverse road geometries and interaction types. Results show that both concurrent and sequential behavioral changes constitute substantial proportions of observed interactions; among sequential interactions, stable ordering is more prevalent than alternating ordering, indicating that persistent asymmetric roles are common. Importantly, temporal precedence does not necessarily coincide with a measurable behavioral response, suggesting temporal ordering alone may not sufficiently characterize behavioral dependence. The findings imply that different game-theoretic formulations are better regarded as complementary modeling abstractions for different interaction regimes rather than a universal structure.

## Key points

- Proposes a trajectory-level interaction measurement framework that verifies candidate interactions via behavioral deviations.
- Systematically evaluated on six real-world datasets covering following, merging, and conflicting scenarios.
- Finds both concurrent and sequential behavioral changes prevalent; stable ordering is more common than alternating.
- Shows temporal precedence does not necessarily yield measurable responses, challenging universal game-theoretic models.

## Full text

Game-theoretic models provide principled frameworks for modeling vehicle interactions, but their underlying temporal assumptions have not been systematically examined against real-world driving behavior. In particular, it remains unclear how simultaneous, sequential, and asymmetric interaction structures can be measured from vehicle trajectories. This paper develops a trajectory-based interaction measurement framework to identify interaction events and quantify behavioral change onset, temporal organization, post-onset response dynamics, and ordering stability. The framework uses behavioral deviations to verify candidate interactions. We evaluate the framework on six real-world trajectory datasets, including INTERACTION, highD, inD, rounD, Waymo Open Motion, and nuPlan, covering diverse road geometries, traffic environments, and interaction types. The results show that concurrent and sequential behavioral changes both constitute substantial proportions of observed following, merging, and conflicting interactions. Among sequential interactions, stable ordering is more prevalent than alternating ordering, indicating that persistent asymmetric roles are a common interaction structure. Importantly, temporal precedence does not necessarily coincide with a measurable behavioral response, indicating that temporal ordering alone may not be sufficient to characterize behavioral dependence. These findings show that real-world interactions exhibit concurrent, sequential, and persistently ordered temporal structures. Different game-theoretic formulations are therefore better regarded as complementary modeling abstractions for different interaction regimes rather than as a universal structure governing all vehicle interactions.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_4f170f01d34f646efdbfc7a0