LeAD: The LLM Enhanced Planning System Converged with End-to-end Autonomous Driving

-- A principal barrier to large-scale deployment of urban autonomous driving systems lies in the prevalence of complex scenarios and edge cases. Existing systems fail to effectively interpret semantic information within traffic contexts and discern intentions of other participants, consequently generating decisions misaligned with skilled drivers' reasoning patterns. The high-frequency E2E subsystem maintains real-time perception-planning-control cycles, while the low-frequency LLM module enhances scenario comprehension through multi-modal perception fusion with HD maps and derives optimal decisions via chain-of-thought (CoT) reasoning when baseline planners encounter capability limitations. Our experimental evaluation in the CARLA Simulator demonstrates LeAD's superior handling of unconventional scenarios, achieving 71 points on Leaderboard V1 benchmark, with a route completion of 93%. I. INTRODUCTION Autonomous driving systems have witnessed significant advancements in recent years, particularly since the inception of E2E architectures, where deep learning-based models have achieved remarkable performance improvements. However, large-scale open-road deployment of such systems remains infeasible. Beyond challenges like perception limitations and insufficient training data coverage for extreme long-tail scenarios, a critical barrier lies in models' deficient processing capabilities within high-density complex traffic environments and irregular traffic situations[1].