Keynote Speaker Ⅰ
Lixing Yang
Beijing Jiaotong University, China
Brief Biography: Lixing Yang is the Dean of School of Systems Science, Beijing Jiaotong University. His current research interests include traffic and transportation planning, railway traffic management and control, intelligent transportation systems, uncertain theory and optimization, etc. Prof. Yang has published more than 200 papers on some prestigious journals and conferences. A number of published papers are selected as the “Highly Cited Papers” or “Hot Papers” in Web of Science. Prof. Yang is a Fellow of the Asia Pacific Industrial Engineering and Management Society. He was selected as the council members for several societies in China, including the Society of Management Science and Engineering of China, Systems Engineering Society of China, Operations Research Society of China, etc. He was selected as “Highly Cited Chinese Researchers” by Elsevier in 2020-2024. Prof. Yang is an Editorial Board Editor of Transportation Research Part B: Methodological, an Associate Editor of Urban Rail Transit, and an Associate Editor of Journal of Management Science and Engineering. He also served as the Guest Editors for several prestigious journals, including Computers & Industrial Engineering, International Journal of Intelligent Systems, International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems.
Speech Title: Energy-Efficient Operation of Urban Rail Transit—Models and Methods
Abstract: The urban rail transit system in China has experienced rapid expansion, with significant growth in operational mileage, network scale, and passenger volume. However, this progress has also led to large energy consumption, placing immense pressure on energy supply systems. Consequently, designing better train scheduling strategies to reduce operational energy use and costs—achieving energy conservation, emission reduction, and green mobility—has become a critical focus for urban rail transit operators. This talk addresses energy efficiency in urban rail transit through mathematical optimization approaches, presenting three effective methods for energy-efficient train operations: speed profile optimization, energy-saving timetable design, and rolling stock utilization optimization. Corresponding models and algorithms are developed for each problem, with case studies demonstrating their applicability and effectiveness through numerical experiments. Finally, potential directions for future research are identified.
Keynote Speaker Ⅱ
Pengpeng Jiao
Beijing University of Civil Engineering and Architecture, China
Brief Biography: Dr. Pengpeng Jiao is a professor of transportation engineering at Beijing University of Civil Engineering and Architecture. He got the BS and PhD degrees in Civil Engineering from Tsinghua University, China, and worked as JSPS (Japan Society for the Promotion of Science) research fellow at the University of Tokyo for 2 years. His research mainly focuses on intelligent transportation systems, transportation planning and traffic management.
Dr. Jiao has published 4 monographs and over 100 peer-reviewed journal papers. He has worked as a principal investigator for 3 projects funded by the National Natural Science Foundation of China (NSFC) and more than 10 provincial or ministry level projects. He has won more than 10 provincial and ministry level awards, such as Beijing municipal science and technology award. He has been selected as the Youth Beijing Scholar (青年北京学者), the Great Wall Scholar (长城学者), and Beijing Novo Program (北京市科技新星).
Speech Title: Bilateral Control Model for Autonomous Vehicles Based on Deep Reinforcement Learning
Abstract: Traffic oscillations degrade efficiency, increase safety risks, and lead to excessive energy consumption. To address this, we propose the Bilateral Control Model with Deep Reinforcement Learning (BCM-DRL), integrating Deep Reinforcement Learning (DRL), specifically the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm to suppress oscillations and enhance stability. Using the I-80 Next Generation Simulation (NGSIM) dataset, BCM-DRL is trained and evaluated against Bilateral Control Model (BCM) and Car-Following Model with Deep Reinforcement Learning (CFM-DRL). Simulation results show that BCM-DRL reduces the cumulative damping ratio by 75%, decreases fuel consumption by 21.6%, and achieves near-zero Time-to-Instability (TIT) values, significantly improving stability and efficiency. These findings validate BCM-DRL as an effective approach to mitigating traffic oscillations and optimizing vehicle control.
Keynote Speaker Ⅲ
Daxin Tian
Beihang University, China
Brief Biography: 田大新，长江学者特聘教授，IEEE Fellow，北京航空航天大学科研院副院长兼前沿创新处处长，“科学探索奖”获得者，国家优青、青年长江、牛顿高级学者、中国工程院首届“中国工程前沿杰出青年学者”，担任中国指挥与控制学会无人系统专委会主任、中国电子学会智能交通信息工程分会副主任、中国计算机学会智能汽车分会副主任、车路协同与安全控制北京市重点实验室主任。发表学术论文100余篇，出版专著7本、教材2本、译著2本，授权发明专利51项；主持国家重点研发计划“揭榜挂帅”重点专项、国家自然基金重点项目等国家项目12项；获国家科技进步奖二等奖等科技奖15项，国家教学成果奖一等奖等教学奖5项。
Speech Title: 复杂环境下的全自动驾驶技术
Abstract: 自动驾驶的终极目标，是让AI系统真正代替人类，实现对复杂环境中驾驶任务的完全自主执行。不同于封闭、可控的任务环境，自动驾驶需持续应对动态、开放、强耦合的交通系统，对其泛化能力、交互理解与自主决策水平提出了更高要求。本报告聚焦车辆自主认知与决策智能，围绕知识获取、联想预判与持续进化三大核心能力，探索融合多模态认知、因果推理与生成学习的端到端自动驾驶系统架构。同时，报告将介绍在多源感知融合、自主决策控制与鲁棒轨迹生成等方面的最新技术进展，为实现面向复杂环境的高智能自动驾驶系统提供思路支撑与方法基础。