ITSC 2025 Paper Abstract

Paper FR-EA-T40.3

Jeon, Sujae (Korea Advanced Institute of Science and Technology), Kim, Yeeun (University of Central Florida), Yeo, Hwasoo (KAIST)

A Two-Dimensional Lane-Changing Model with Asymmetric Driving Behavior for Autonomous Vehicles

Scheduled for presentation during the Regular Session "S40b-Cooperative and Connected Autonomous Systems" (FR-EA-T40), Friday, November 21, 2025, 14:10−14:30, Cooleangata 4

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Cooperative Driving Systems and Vehicle Coordination in Multi-vehicle Scenarios, Validation of Cooperative Driving and Connected Vehicle Systems

Abstract

As autonomous vehicles are increasingly integrated into real-world traffic, there is a growing demand for models that ensure not only safety and efficiency but also human-like driving behavior. To address this, various autonomous driving models have made proposed to mimic human characteristics. However, most of these models focus solely on one-dimensional car-following and lack smooth integration with lane-changing behavior. This limitation restricts their ability to reproduce complex and context-aware driving behavior. Therefore, this study proposes a two-dimensional driving behavior model that incorporates human-like characteristics. The model calculates both longitudinal and lateral accelerations using relational variables derived from an asymmetric repulsive force model. For longitudinal control, a weight-based approach is employed to simultaneously account for the influence of multiple surrounding vehicles, enabling more complex and human-like driving behavior. For lateral control, the model adopts a spring-mass-damper system, in which the spring coefficient is dynamically adjusted based on surrounding traffic conditions. This allows for flexible responses such as lane-change abandonment or timing adjustments. Simulation results show that the proposed model enables smoother behavior transitions and reduces the impact on surrounding traffic, while also reproducing adaptive behaviors such as lane-change abandonment under unsafe conditions.