发表机构
State Key Laboratory of Automotive Simulation and Control, Jilin University; Center of Research for Cyber Security and Network (CSNET), Faculty of Computer Science and Information Technology, Universiti Malaya; Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg; IMT, Department of Humanities and Technology, Roskilde University; Center for Security, Theory and Algorithmic Research, International Institute of Information Technology; Department of Computer Science and Engineering, College of Informatics, Korea University（吉林大学汽车仿真与控制国家重点实验室; 马来西亚大学计算机科学与信息技术学院网络安全与网络研究中心; 卢森堡大学安全、可靠性与信任跨学科中心; 罗斯基勒大学人文与技术系IMT; 国际信息技术研究所安全、理论与算法研究中心; 韩国大学信息学院计算机科学与工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对物联网支持的自动驾驶规划问题，提出大语言模型增强可微轨迹规划框架。通过以周围智能体为中心的数据增强、复杂度感知的语义增强模块及可微优化模块，提升规划效果，在相关基准测试中取得高分，验证了在线部署和实时闭环执行能力。
AI 中文摘要
自动驾驶规划是物联网支持的智能交通系统的关键组成部分，要求车辆在复杂城市环境中根据多源上下文信息生成安全、高效且可执行的轨迹。虽然模仿学习在大规模数据集上显示出前景，但基于模仿学习的规划器仍存在复杂长尾交互覆盖有限、与下游约束细化一致性弱以及在实时约束下高级场景语义利用不足等问题。为解决这些问题，本文提出了一种用于物联网支持的自动驾驶的大语言模型增强可微轨迹规划框架。具体而言，引入以周围智能体为中心的数据增强策略，重新组织周围智能体轨迹作为额外规划监督，无需收集额外原始数据来改善训练分布。进一步设计了一个复杂度感知的基于异步大语言模型的语义增强模块，以可控的在线开销提取与场景相关的高级语义特征。此外，纳入一个可微优化模块，在向上游规划器反向传播优化梯度时，通过显式残差惩罚细化生成的轨迹。实验表明，该方法在nuPlan闭环非反应式和反应式Hard20基准测试中分别取得了83.63和78.29的最佳总体分数，CARLA-ROS测试进一步验证了其在线部署和实时闭环执行能力。
英文摘要
Autonomous driving planning is a key component of IoT-enabled intelligent transportation systems, requiring vehicles to generate safe, efficient, and executable trajectories in complex urban environments from multi-source contextual information. While imitation learning (IL) has shown promise on large-scale datasets, IL-based planners still suffer from limited coverage of complex long-tail interactions, weak consistency with downstream constrained refinement, and insufficient use of high level scene semantics under real time constraints. To address these issues, this paper proposes a large language model (LLM) enhanced differentiable trajectory planning framework for IoT-enabled autonomous driving. Specifically, we introduce a surrounding agent centric data augmentation strategy to reorganize sur rounding agent trajectories as additional planning supervision, thereby improving the training distribution without collecting additional raw data. We further design a complexity-aware asyn chronous LLM-based semantic enhancement module to extract scene-related high-level semantic features with controlled online overhead. In addition, a differentiable optimization module is incorporated to refine generated trajectories with explicit residual penalties while backpropagating optimization gradients to the upstream planner. Experiments show that the proposed method achieves the best overall scores of 83.63 and 78.29 on the nuPlan closed-loop nonreactive and reactive Hard20 benchmarks, respectively, and CARLA-ROS tests further verify its online deployment and real time closed-loop execution capability.
Comments13 pages, 5 figures
