Two-Dimensional Following Lane-Changing (2DF-LC): A Framework for Dynamic Decision-Making and Rapid Behavior Planning

Lane changes require dynamic decision-making and rapid behavior planning, which are challenging for traffic modeling. We propose a two-dimensional following lane-changing framework (2DF-LC) that exploits the benefits of car-following (CF) models for computational efficiency, collision avoidance, and human-like behavior. This framework uses a sigmoid-based intelligent driver model (SIDM) with both longitudinal and lateral following. To avoid excessive acceleration at start-up, we develop an SIDM that ensures a smooth start-up. In the longitudinal plane, we introduce a transition function to create a double-target car-following model (DT-SIDM) that can handle sudden acceleration changes due to target switching, thereby guaranteeing stable longitudinal motion and dynamic collision avoidance. In the lateral plane, we develop a lateral movement car-following model (LM-SIDM) inspired by a social force model. The LM-SIDM defines both lane and gap forces, resulting in effective lateral motion and collision avoidance during lane changes. Simulations and tests in three typical scenarios show that 2DF-LC has high computational efficiency: it completes calculations within milliseconds. Compared with the widely used hierarchical motion planning system (HMPS) and integrated model and learning combined algorithm (IMLC) methods, 2DF-LC based on real trajectories reduces the errors by 49.5% and 16.1%, respectively, and achieves a 28.63% lower time-integrated anticipated collision time (TI-ACT) than the original trajectories, indicating improved safety. Moreover, 2DF-LC produces a smooth acceleration curve, with an average jerk value of 0.358 m/s³. The lane-change trajectory generated by 2DF-LC can also be followed and executed effectively in CarSim tests.

I. Introduction

Autonomous driving technology enhances traffic efficiency, reduces traffic accidents, and improves travel experience. However, complex traffic environments pose great challenges for autonomous driving [1], [2], [3]. Autonomous vehicles need to make safe, comfortable, and human-like decisions, plans, and controls. Lane change (LC) is a key subproblem of autonomous driving that involves vehicle movement between different lanes. Various lane change models [4], [5], [6], [7] are useful for simulating, optimizing, controlling and executing traffic performance, emissions, safety and comfort in various road scenarios and situations for traffic flow simulation and autonomous driving applications. Lane change behavior modeling consists of two stages: generating lane change intentions and executing lane changes [8], [9], [10]. This study focuses on the execution stage, namely how to dynamically and rapidly generate lane change trajectories that conform to human driver behavior characteristics. Lane change motion planning influences not only traffic flow and safety, but also passenger experience and social acceptance [11], [12], [13]. Therefore, a current research challenge is to design a method that can adapt to dynamic environment changes, capture human driving behavior characteristics comprehensively, and generate reasonable and feasible lane change trajectories rapidly.