HiDrive: A Closed-Loop Benchmark for High-Level Autonomous Driving

2026-05-11

AI Summary

This work addresses critical limitations in existing autonomous driving evaluation benchmarks, which often lack sufficient scene diversity and fail to assess higher-order driving capabilities such as legal compliance, ethical reasoning, and emergency response. To bridge this gap, the authors propose a closed-loop evaluation benchmark that explicitly incorporates long-tail scenarios and advanced decision-making skills. For the first time, legal compliance, moral judgment, and context-aware emergency maneuvers are integrated into an end-to-end assessment framework. Built upon a high-fidelity physics and rendering engine, the benchmark features rare objects and unconventional traffic situations, and introduces multidimensional quantitative metrics covering collision avoidance, traffic rule adherence, and ethical reasoning. Experimental results demonstrate that this platform enables more comprehensive and fine-grained evaluation of autonomous driving systems in complex, real-world environments.

Abstract

End-to-end autonomous driving has witnessed rapid progress, yet existing benchmarks are increasingly saturated, with state-of-the-art models achieving near-perfect scores on widely used open-loop and closed-loop benchmarks. This saturation does not mean that the problem has been solved; instead, it reveals that current benchmarks remain limited in scenario diversity, object variety, and the breadth of driving capabilities they evaluate. In particular, they lack sufficient long-tail scenarios involving rare but safety-critical objects and fail to assess advanced decision-making such as legal compliance, ethical reasoning, and emergency response. To address these gaps, we propose HiDrive, a new closed-loop benchmark for end-to-end autonomous driving that emphasizes long-tail scenarios and a richer evaluation of driving capabilities. HiDrive introduces a diverse set of rare objects and uncommon traffic situations, and expands evaluation from basic driving skills to more advanced capabilities, including rule compliance, moral reasoning, and context-dependent emergency maneuvers. Correspondingly, we extend previous collision-avoidance-centered metrics into a comprehensive evaluation system that encompasses collision and braking, traffic-rule compliance, and moral-reasoning indicators. Built on a more advanced physics engine, HiDrive provides physically realistic lighting and high-fidelity visual rendering, offering a more challenging and realistic testbed for assessing whether autonomous driving systems can handle the complexity of real-world deployment. The HiDrive software, source code, digital assets, and documentation are available at https://github.com/VDIGPKU/HiDrive.

Problem

• autonomous driving
• benchmark
• long-tail scenarios
• ethical reasoning
• traffic-rule compliance

Innovation

• closed-loop benchmark
• long-tail scenarios
• moral reasoning
• traffic-rule compliance
• high-fidelity simulation