Interactive Car-Following: Matters but NOT Always

TL;DR

This paper introduces a new metric to measure interaction in car-following, enabling adaptive control strategies that mimic human behavior, showing that drivers do not always react to the lead vehicle but act based on context.

Contribution

The paper proposes a novel interaction intensity metric and an adaptive switching control framework for car-following, improving performance and data efficiency over traditional methods.

Findings

Interaction intensity varies significantly among drivers.

Drivers sometimes take safety-critical or intentional actions without reacting to the lead vehicle.

The proposed framework outperforms unified control strategies in simulations.

Abstract

Following a leading vehicle is a daily but challenging task because it requires adapting to various traffic conditions and the leading vehicle's behaviors. However, the question `Does the following vehicle always actively react to the leading vehicle?' remains open. To seek the answer, we propose a novel metric to quantify the interaction intensity within the car-following pairs. The quantified interaction intensity enables us to recognize interactive and non-interactive car-following scenarios and derive corresponding policies for each scenario. Then, we develop an interaction-aware switching control framework with interactive and non-interactive policies, achieving a human-level car-following performance. The extensive simulations demonstrate that our interaction-aware switching control framework achieves improved control performance and data efficiency compared to the unified control strategies. Moreover, the experimental results reveal that human drivers would not always keep reacting to their leading vehicle but occasionally take safety-critical or intentional actions -- interaction matters but not always.