CoT-Drive：利用大语言模型与思维链提示实现高效自动驾驶运动预测
CoT-Drive: Efficient Motion Forecasting for Autonomous Driving with LLMs and Chain-of-Thought Prompting
AI总结：
CoT-Drive首次通过知识蒸馏将大语言模型的思维链场景理解能力迁移到轻量级语言模型，并构建Highway-Text和Urban-Text数据集，在边缘设备上实现高效、鲁棒的自动驾驶运动预测。
摘要：
准确的运动预测对于安全的自动驾驶（AD）至关重要。本研究提出CoT-Drive，这是一种通过利用大语言模型（LLMs）和思维链（CoT）提示方法来增强运动预测的新方法。我们引入了一种教师-学生知识蒸馏策略，以有效地将大语言模型先进的场景理解能力迁移到轻量级语言模型（LMs）中，确保CoT-Drive能够在边缘设备上实时运行，同时保持全面的场景理解和泛化能力。通过在不进行额外训练的情况下利用面向大语言模型的CoT提示技术，CoT-Drive生成语义标注，显著提升对复杂交通环境的理解，从而提高预测的准确性和鲁棒性。此外，我们提出了两个新的场景描述数据集，Highway-Text和Urban-Text，专门用于微调轻量级语言模型以生成针对特定上下文的语义标注。对五个真实世界数据集的综合评估表明，CoT-Drive优于现有模型，凸显了其在处理复杂交通场景方面的有效性和高效性。总体而言，本研究是首个考虑大语言模型在该领域实际应用的工作。它开创性地训练和使用轻量级大语言模型替代模型进行运动预测，设立了新的基准，并展示了将大语言模型集成到自动驾驶系统中的潜力。
英文摘要：
Accurate motion forecasting is crucial for safe autonomous driving (AD). This study proposes CoT-Drive, a novel approach that enhances motion forecasting by leveraging large language models (LLMs) and a chain-of-thought (CoT) prompting method. We introduce a teacher-student knowledge distillation strategy to effectively transfer LLMs' advanced scene understanding capabilities to lightweight language models (LMs), ensuring that CoT-Drive operates in real-time on edge devices while maintaining comprehensive scene understanding and generalization capabilities. By leveraging CoT prompting techniques for LLMs without additional training, CoT-Drive generates semantic annotations that significantly improve the understanding of complex traffic environments, thereby boosting the accuracy and robustness of predictions. Additionally, we present two new scene description datasets, Highway-Text and Urban-Text, designed for fine-tuning lightweight LMs to generate context-specific semantic annotations. Comprehensive evaluations of five real-world datasets demonstrate that CoT-Drive outperforms existing models, highlighting its effectiveness and efficiency in handling complex traffic scenarios. Overall, this study is the first to consider the practical application of LLMs in this field. It pioneers the training and use of a lightweight LLM surrogate for motion forecasting, setting a new benchmark and showcasing the potential of integrating LLMs into AD systems.
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。
