Human-Like Interactive Lane-Change Modeling Based on Reward-Guided Diffusive Predictor and Planner

Lane changing presents a dynamic scenario characterized by intricate interactions among vehicles. Within mixed-autonomy traffic environment, modeling a human-like lane-change trajectory enables human drivers to better understand and predict autonomous vehicles’ behaviors, thereby enhancing road safety and travel efficiency. In this study, we achieve human-like interactive lane-change modeling based on a novel framework named Diff-LC. The human-like modeling of LCV behaviors relies on an advanced diffusive planner, and the implemented trajectory is selected based on the recovered LCV reward function learned through Multi-Agent Adversarial Inverse Reinforcement Learning (MA-AIRL). To account for interactions between FVs and LCVs, we further employ a diffusive predictor to forecast future behaviors of FVs conditioned on both historical and planned trajectories. Additionally, we leverage the recovered reward function of FVs to enable controllable prediction of trajectories. In the experimental part, we begin by analyzing the significance of features in the recovered reward functions and then proceed to compare the distinctions between the LCV and the FV. To validate the effectiveness of the proposed framework, we compare the diffusive predictor and planner with several state-of-the-art methods. The results demonstrate that motions planned by Diff-LC closely reach the intended positions with small displacement errors and exhibit highly similar speed and jerk distributions to those of human drivers. We also conduct a dynamic simulation to evaluate Diff-LC’s performance across different traffic conditions. Finally, we explore customized generation using the Diffusion Posterior Sampling method. The codes can be found at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/zeonchen/Diff-LC/</uri>.