发表机构
Indian Statistical Institute; Sorbonne University Abu Dhabi; Sorbonne Center for Artificial Intelligence; SQC & OR（印度统计研究所; 阿布扎比索邦大学; 索邦人工智能中心; 统计质量控制与运筹学研究室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出SIGMA框架，结合LLM实现自适应交通信号多目标控制，在SUMO仿真中较基准控制器降低等待与排队时长、提升通行量，且具备鲁棒性与统计可靠性。
AI 中文摘要
交通信号控制是一类复杂的序列决策问题，需在通行量、延迟公平性、信号稳定性及应急车辆优先级之间进行实时适配与权衡。现有强化学习（RL）方法常固定目标、忽略动态优先级变化，且无法在几何相似的路口间泛化。本文提出SIGMA（Symmetry-aware, Intelligent, Geometric, Multi-objective Adaptive traffic control，即感知对称性、智能型、几何化多目标自适应交通控制），这一强化学习框架融合大语言模型（LLM）实现自适应目标调参与方向不变学习。SIGMA将自然语言应急指令转换为多目标演员-评论家控制器的优先级向量，规避手动奖励工程；旋转数据增强提升其在四路交叉路口间的迁移能力，离线-在线学习确保稳定初始化及对动态需求的逐步适配。本文定义了覆盖应急服务水平、LLM故障下的 graceful degradation（优雅降级）、需求敏感性的可靠性属性，并通过自助统计法验证。在SUMO仿真平台上，针对四个加尔各答城市路口，与固定定时控制、感应控制及DQN控制器对比，SIGMA可降低平均及应急等待时间、排队长度，提升通行量；消融实验证实其对组件故障及几何旋转的鲁棒性。总体而言，SIGMA提供了具备统计可靠性保证的可靠、语言引导型多目标交通控制系统。
英文摘要
Traffic signal control is a complex sequential decision-making problem requiring real-time adaptation and trade-offs among throughput, delay fairness, signal stability, and emergency vehicle priority. Existing RL methods often fix objectives, ignore dynamic priority changes, and fail to generalize across geometrically similar intersections.We propose SIGMA (Symmetry-aware, Intelligent, Geometric, Multi-objective Adaptive traffic control), an RL framework enhanced with a large language model (LLM) for adaptive objective tuning and orientation-invariant learning. SIGMA converts natural-language emergency commands into priority vectors for a multi-objective actor-critic controller, avoiding manual reward engineering. Rotational augmentation improves transferability across four-way intersections, while offline-to-online learning ensures stable initialization and gradual adaptation to changing traffic.We define reliability properties covering emergency service levels, graceful degradation under LLM failures, and demand sensitivity, validated via bootstrap statistics. Evaluated in SUMO on four Kolkata-based urban intersections against fixed-time, actuated, and DQN controllers, SIGMA reduces average/emergency waiting times and queue lengths, and boosts throughput. Ablation studies confirm robustness to component failures and geometric rotations. Overall, SIGMA offers a reliable, language-guided, multi-objective traffic control system with statistical reliability assurance.
