DRIFT: Risk-Constrained Diffusion with Imitation Priors for Mixed-Autonomy Traffic Generation
For researchers in intelligent transportation systems, DRIFT provides a unified framework to generate realistic mixed-autonomy traffic scenarios for safety and stability diagnostics, addressing a known bottleneck in capturing heterogeneous behavioral distributions.
DRIFT is a mixed-autonomy traffic generation framework that uses risk-constrained diffusion with imitation priors to generate executable trajectories under heterogeneous AV penetration. It achieves a strong safety-efficiency trade-off in closed-loop benchmarks, demonstrating the importance of candidate executability and long-tail feedback.
Future intelligent transportation systems are envisioned to evolve toward a long-term mixed-autonomy paradigm, where human-driven vehicles (HVs) and autonomous vehicles (AVs) coexist within highly coupled traffic ecosystems. Such coexistence introduces pronounced heterogeneity, amplified uncertainty, and increasingly intricate interaction dynamics. In this context, it remains fundamentally challenging to simultaneously capture the heterogeneous behavioral distribution shifts arising from dynamic AV penetration, generate diverse yet executable trajectories under strong inter-vehicle coupling, and conduct reliable closed-loop safety and stability diagnostics for rare but high-impact events. To this end, we present risk-constrained diffusion with imitation priors (DRIFT), a mixed-autonomy traffic generation framework which unifies heterogeneity-aware conditional encoding, conditional diffusion-based executable trajectory generation, and progressive adversarial alignment enhanced by risk-aware long-tail feedback, thereby enabling traffic behaviors to be iteratively generated, filtered, selected, and validated within a closed-loop execution pipeline. In addition, a unified evaluation protocol is developed to jointly characterize safety, efficiency, and closed-loop stability across representative traffic scenarios and AV penetration regimes. Experimental results demonstrate that DRIFT achieves a strong safety-efficiency trade-off in closed-loop mixed-autonomy benchmarks, while further revealing the critical influence of candidate executability, online selection, and long-tail feedback on executable traffic evolution.