Ctx2TrajGen: Traffic Context-Aware Microscale Vehicle Trajectories using Generative Adversarial Imitation Learning
This addresses data scarcity and domain shift issues for traffic behavior analysis and autonomous driving systems, though it appears incremental as it builds on existing methods like GAIL, PPO, and WGAN-GP.
The paper tackled the problem of modeling microscopic vehicle trajectories for traffic analysis and autonomous driving by proposing Ctx2TrajGen, a context-aware framework using generative adversarial imitation learning, which demonstrated superior performance in realism, diversity, and contextual fidelity on the DRIFT dataset.
Precise modeling of microscopic vehicle trajectories is critical for traffic behavior analysis and autonomous driving systems. We propose Ctx2TrajGen, a context-aware trajectory generation framework that synthesizes realistic urban driving behaviors using GAIL. Leveraging PPO and WGAN-GP, our model addresses nonlinear interdependencies and training instability inherent in microscopic settings. By explicitly conditioning on surrounding vehicles and road geometry, Ctx2TrajGen generates interaction-aware trajectories aligned with real-world context. Experiments on the drone-captured DRIFT dataset demonstrate superior performance over existing methods in terms of realism, behavioral diversity, and contextual fidelity, offering a robust solution to data scarcity and domain shift without simulation.