Special Session Ⅻ
AI-Driven Transportation Management and Optimization
(人工智能驱动的交通管理与优化)
Chair: | Co-chair: |
|
|
Wenhui Zhang | Xia Zhao |
Northeast Forestry University, China | Beijing University of Civil Engineering and Architecture, China |
Keywords: | Topics (including but not limited to): |
· Artificial Intelligence (人工智能) · Traffic Management (交通管理) · Deep Learning (深度学习) · Reinforcement Learning (强化学习) · Digital Twin (数字孪生) · Smart Transportation (智慧交通) | · Deep Learning-based Real-time Traffic Flow Prediction & Dynamic Control (基于深度学习的实时交通流预测与动态调控) · Reinforcement Learning for Adaptive Traffic Signal Coordination (自适应交通信号协同的强化学习方法) · Cooperative Routing for Connected Autonomous Vehicle Fleets (网联自动驾驶车队协同路径规划) · AI-enabled Public Transit Resource Allocation (智能公交资源优化配置系统) · Digital Twin-based Infrastructure Health Monitoring (基于数字孪生的基础设施健康监测) · Multi-Objective Optimization for Low-Carbon Transportation (低碳交通多目标优化技术) |
Summary:
· Artificial Intelligence (AI) technologies are profoundly transforming the paradigms of transportation management and optimization. This session focuses on cutting-edge AI applications in transportation, exploring how advanced algorithms such as deep learning and reinforcement learning can enhance the intelligence of transportation systems. Key topics include: deep learning-based real-time traffic flow prediction and dynamic control, reinforcement learning for adaptive traffic signal coordination, cooperative routing for connected autonomous vehicle fleets, and AI-enabled public transit resource allocation. The research also highlights innovative applications of digital twins in infrastructure health monitoring and multi-objective optimization for low-carbon transportation. Through case studies and technical discussions, this session demonstrates how AI technologies can effectively address critical challenges such as traffic congestion, resource allocation, and sustainable development, providing new insights for the future of intelligent transportation systems.
· 人工智能（AI）技术正在深刻改变现代交通系统的管理与优化模式。本专题聚焦AI在交通领域的前沿应用，探讨如何通过深度学习、强化学习等先进算法提升交通系统的智能化水平。重点内容包括：基于深度学习的实时交通流预测与动态调控技术，强化学习在自适应信号控制中的应用，网联自动驾驶车队的协同路径规划，以及公交资源的智能优化配置。研究同时关注数字孪生技术在交通基础设施健康监测中的创新应用，以及面向低碳目标的多目标交通优化方法。通过案例分析和技术探讨，本专题旨在展示AI技术如何有效解决交通拥堵、资源分配和可持续发展等关键挑战，为未来智能交通系统的发展提供新思路。
Submission Deadline: 2025.10.15