Evaluation of Drivers' Interaction Ability at Social Scenarios: A Process-Based Framework

TL;DR

This paper introduces a process-oriented framework for evaluating drivers' interaction abilities during social driving scenarios, emphasizing the dynamic nature of interactions and providing a real-time scoring method validated at unsignalized intersections.

Contribution

It presents a novel framework that assesses drivers' interaction capabilities through process modeling, risk perception, and dynamic scoring, addressing limitations of outcome-focused metrics.

Findings

Framework effectively distinguishes conservative and aggressive driving behaviors.

Validated at intersections in China and the USA with good adaptability.

Demonstrates improved assessment of interaction dynamics over traditional metrics.

Abstract

Assessing drivers' interaction capabilities is crucial for understanding human driving behavior and enhancing the interactive abilities of autonomous vehicles. In scenarios involving strong interaction, existing metrics focused on interaction outcomes struggle to capture the evolutionary process of drivers' interactive behaviors, making it challenging for autonomous vehicles to dynamically assess and respond to other agents during interactions. To address this issue, we propose a framework for assessing drivers' interaction capabilities, oriented towards the interactive process itself, which includes three components: Interaction Risk Perception, Interaction Process Modeling, and Interaction Ability Scoring. We quantify interaction risks through motion state estimation and risk field theory, followed by introducing a dynamic action assessment benchmark based on a game-theoretical rational agent model, and designing a capability scoring metric based on morphological similarity distance. By calculating real-time differences between a driver's actions and the assessment benchmark, the driver's interaction capabilities are scored dynamically. We validated our framework at unsignalized intersections as a typical scenario. Validation analysis on driver behavior datasets from China and the USA shows that our framework effectively distinguishes and evaluates conservative and aggressive driving states during interactions, demonstrating good adaptability and effectiveness in various regional settings.