Special Session Ⅺ
Application of Artificial Intelligence in Transportation System
(人工智能技术在交通系统中的应用)
| Chair: | Co-chairs: | |
|
|
|
Zhihong Li | Xianyu Wu | Deqi Chen |
Beijing University of Civil Engineering and Architecture, China | Beijing Jiaotong University, China | Northeast Forestry University, China |
Keywords: | Topics (including but not limited to): |
· Artificial Intelligence (人工智能) · Traffic Management (交通管理) · Autonomous Vehicles (自动驾驶车辆) · Predictive Analytics (预测分析) · Smart Transportation (智能交通) | · AI-Powered Traffic Prediction & Congestion Management (人工智能驱动的交通预测与拥堵治理系统) · Autonomous Vehicles and AI-Driven Transportation Systems (自动驾驶与AI驱动的智能交通系统) · Smart Traffic Control Using Reinforcement Learning or LLM (基于强化学习/大语言的智能交通控制系统) · AI for Public Transit Optimization (公共交通优化中的人工智能技术应用) · Computer Vision in Traffic Monitoring & Safety (计算机视觉在交通监测与安全领域的应用) · Predictive Maintenance of Infrastructure with AI (基于AI的交通基础设施预测性维护) · AI-Based Systems for Sustainable Transportation Planning (可持续交通规划中的智能决策系统) · AI in Traffic Safety Analysis and Accident Prevention (人工智能在交通安全分析与事故预防中的应用) |
Summary:
· The rapid advancement of artificial intelligence (AI) has brought transformative changes to transportation systems, enhancing efficiency, safety, and sustainability. This session explores key applications of AI in modern transportation, focusing on intelligent traffic management, autonomous vehicles, and predictive analytics. Machine learning algorithms, particularly deep neural networks and reinforcement learning, enable real-time traffic flow prediction and dynamic congestion management, significantly reducing urban traffic delays. Computer vision technologies, such as object detection and video analytics, improve traffic monitoring and accident prevention through automated incident detection and behavior analysis.
In autonomous transportation, AI integrates multi-sensor data (LiDAR, cameras, radar) to enable precise navigation and collision avoidance, while vehicle-to-everything (V2X) communication optimizes route planning. Public transit systems benefit from AI-driven demand forecasting and scheduling optimization, ensuring resource efficiency. Additionally, AI-powered predictive maintenance analyzes infrastructure data (e.g., road conditions, bridge health) to prevent failures and reduce costs.
Despite these advancements, challenges persist, including data privacy concerns, algorithmic bias, and the need for robust regulatory frameworks. Future directions emphasize explainable AI (XAI) for transparent decision-making and the integration of AI with smart city initiatives. By addressing these challenges, AI can further revolutionize transportation systems, supporting global goals of carbon neutrality and intelligent mobility.
· 人工智能（AI）的快速发展为交通系统带来了革命性变革，显著提升了运行效率、安全性和可持续性。本专题深入探讨AI在现代交通中的关键应用，重点聚焦智能交通管理、自动驾驶车辆和预测分析三大领域。机器学习算法（尤其是深度神经网络和强化学习技术）实现了实时交通流预测和动态拥堵管理，大幅降低了城市交通延误。计算机视觉技术（如目标检测和视频分析）通过自动化事件检测和行为分析，有效提升了交通监控与事故预防能力。
在自动驾驶领域，AI通过整合多传感器数据（激光雷达、摄像头、雷达等）实现精准导航和碰撞规避，而车联网（V2X）通信技术则优化了路线规划。公共交通系统受益于AI驱动的需求预测和调度优化，显著提升了资源利用效率。此外，基于AI的预测性维护通过分析基础设施数据（如道路状况、桥梁健康状态），有效预防故障并降低成本。
尽管取得显著进展，该领域仍面临数据隐私保护、算法偏见治理和健全监管框架构建等挑战。未来发展方向将强调可解释人工智能（XAI）的透明决策机制，以及AI与智慧城市建设的深度融合。通过应对这些挑战，AI将进一步推动交通系统变革，助力实现碳中和与智能出行的全球目标。
Submission Deadline: 2025.10.15