CurricuVLM：通过基于视觉语言模型的个性化安全关键课程学习实现安全自动驾驶
CurricuVLM: Towards Safe Autonomous Driving via Personalized Safety-Critical Curriculum Learning with Vision-Language Models
AI总结：
CurricuVLM利用视觉语言模型分析自动驾驶车辆行为，识别性能弱点并动态生成个性化安全关键训练场景，在Waymo数据集上超越基线，提升导航成功、驾驶效率与安全性。
摘要：
确保自动驾驶系统的安全性仍然是一个关键挑战，尤其是在处理罕见但可能造成灾难性后果的安全关键场景时。尽管现有研究已探索为自动驾驶车辆（AV）测试生成安全关键场景，但在将这些场景有效融入策略学习以提升安全性方面的工作仍然有限。此外，开发能够适应自动驾驶车辆不断演变的行为模式和性能瓶颈的训练课程在很大程度上仍未得到探索。为解决这些挑战，我们提出了CurricuVLM，一个新颖的框架，利用视觉语言模型（VLMs）实现自动驾驶智能体的个性化课程学习。我们的方法独特地利用VLMs的多模态理解能力来分析智能体行为、识别性能弱点，并动态生成针对性的训练场景以进行课程适应。通过对不安全驾驶情境的叙述性描述进行全面分析，CurricuVLM进行深入推理以评估自动驾驶车辆的能力并识别关键行为模式。随后，该框架综合定制针对这些已识别局限性的训练场景，实现有效且个性化的课程学习。在Waymo开放运动数据集上的大量实验表明，CurricuVLM在常规和安全关键场景中均优于最先进的基线，在导航成功、驾驶效率和安全指标方面取得了优越性能。进一步分析显示，CurricuVLM作为一种通用方法，可与各种强化学习算法集成以增强自动驾驶系统。代码和演示视频可在https://zihaosheng.github.io/CurricuVLM/获取。
英文摘要：
Ensuring safety in autonomous driving systems remains a critical challenge, particularly in handling rare but potentially catastrophic safety-critical scenarios. While existing research has explored generating safety-critical scenarios for autonomous vehicle (AV) testing, there is limited work on effectively incorporating these scenarios into policy learning to enhance safety. Furthermore, developing training curricula that adapt to an AV's evolving behavioral patterns and performance bottlenecks remains largely unexplored. To address these challenges, we propose CurricuVLM, a novel framework that leverages Vision-Language Models (VLMs) to enable personalized curriculum learning for autonomous driving agents. Our approach uniquely exploits VLMs' multimodal understanding capabilities to analyze agent behavior, identify performance weaknesses, and dynamically generate tailored training scenarios for curriculum adaptation. Through comprehensive analysis of unsafe driving situations with narrative descriptions, CurricuVLM performs in-depth reasoning to evaluate the AV's capabilities and identify critical behavioral patterns. The framework then synthesizes customized training scenarios targeting these identified limitations, enabling effective and personalized curriculum learning. Extensive experiments on the Waymo Open Motion Dataset show that CurricuVLM outperforms state-of-the-art baselines across both regular and safety-critical scenarios, achieving superior performance in terms of navigation success, driving efficiency, and safety metrics. Further analysis reveals that CurricuVLM serves as a general approach that can be integrated with various RL algorithms to enhance autonomous driving systems. The code and demo video are available at: https://zihaosheng.github.io/CurricuVLM/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
