| |
| |
基本信息：
于新莲，博士，讲师，硕士生导师，交通学院交通运输系
办公地点：东南大学九龙湖校区交通学院大楼1004室
联系电话：18262634846
88038威尼斯的联系方式：
于新莲，东南大学交通学院交通运输系教师。综合运用运筹与管理科学、机器学习、强化学习、行为科学等理论方法，对交通出行、物流运输等领域的数字化平台协作化运营和管理、公共交通网络设计与动态管控优化、多模式交通与物流网络规划设计等问题开展研究。
目前主持国家自然科学基金青年基金项目1项目，江苏省自然科学基金青年基金项目1项。参与美国能源部高级研究计划1项，美国交通部、国家科学基金（smart and connected communities）、新英格兰地区交通管理局、马萨诸塞公路管理局等机构资助的多项研究项目。在多个国际学术会议如informs年会，世界交通运输大会（wtc）、cota国际交通科技年会（cictp）等进行学术报告等。现担任tr part b/c/e，transportation，ieee transactions-its等交通领域重要国际期刊审稿人。
欢迎对科研有深入兴趣，有交通工程、运筹学、统计学、机器学习等方面基础（或者愿意深入学习）的同学报考硕士研究生。
研究方向：
n 方法：动态规划，混合整数规划， 强化学习/机器学习，行为决策科学等
n 应用：交通出行/物流运输数字化平台协作化运营管理，公共交通网络设计与动态管控优化，多模式交通与物流网络规划设计等
教育经历：
2014/09 - 2019/02, 马萨诸塞大学阿默斯特分校, 交通工程, 博士
2014/09 - 2018/05, 马萨诸塞大学阿默斯特分校, 统计学, 硕士
2011/09 - 2014/06, 南京大学, 管理科学与工程, 硕士
2007/09 - 2011/06, 东南大学, 管理学, 学士
工作经历：
2019/03 - 2020/08, 明尼苏达大学双城分校助,博士后研究员
2020/10 - 今, 东南大学, 交通学院, 讲师
科研项目：
[1].国家自然科学基金青年项目，考虑供需交互变化的网约车非短视动态调度优化研究，2023-2025，主持
[2].江苏省自然科学基金青年项目， 面向耦合需求的网约车订单匹配与巡游路径优化研究, 2021-2024，主持
[3].zhang z. (lead pi). leveraging autonomous shared vehicles for greater community health, equity, livability, and prosperity (help). standard grant (nsf). sep.2018-aug.2022. 参与
[4].ben-akiva, m. (lead pi) and gao, s. (umass pi). mobility electronic market for optimized travel (memot). advanced research projects agency-energy (arpa-e), department of energy. nov. 2015 - sep. 2018. $3,990,128. umass portion. 参与
[5].gao, s. (pi). routing policy choice models in stochastic time-dependent networks: the stockholm case study. us department of transportation through new england university transportation center.参与
[6].gao, s. (pi). an optimal adaptive routing algorithm for large-scale stochastic time dependent networks. us department of transportation through new england university transportation center. 2015.参与
代表性论文：
[1].xinlian yu; alireza khani; jingxu chen; hongli xu; haijun mao. real-time holding control for transfer synchronization via robust multi-agent reinforcement learning, ieee transactions on intelligent transportation systems, 2022 (forthcoming, doi 10.1109/tits.2022.3204805)
[2].yuhao wang#; hongli xu; xinlian yu; jing zhou. heuristic feeder-bus operation strategy considering weather information: a chance-constrained model.international transactions in operational research, 2022 (forthcoming)
[3].xinlian yu*; song gao. a batch reinforcement learning approach to vacant taxi routing, transportation research part c: emerging technologies, 139(2022):103640
[4].yanqiu cheng#; xianbiao hu; kuanmin chen; xinlian yu; yulong luo. online longitudinal trajectory planning for connected and autonomous vehicles in mixed traffic flow with deep reinforcement learning approach, journal of intelligent transportation systems, 2022 feb 24:1-5.
[5].tien mai; xinlian yu*; song gao; emma frejinger. routing policy choice prediction in a stochastic network: recursive model and solution algorithm, transportation research part b: methodological, 2021, 151: 42-58
[6].xinlian yu; song gao; xianbiao hu; hyoshin park. a markov decision process approach to vacant taxi routing with e-hailing, transportation research part b: methodological, 2019, 121:114-134
[7].xinlian yu; song gao. learning routing policies in a disrupted, congestible network with real-time information: an experimental approach, transportation research part c: emerging technologies, 2019, 106: 205-219
[8].徐红利; 于新莲*; 周晶. 诱导信息下考虑路段容量退化的流量演化研究,管理科学学报,2015,(07):39-47
(*通讯，#学生合作者)
近期会议报告：
[1].xinlian, yu; vehicle routing in mobility-on-demand systems via a batch reinforcement learning approach, the 22nd cota international conference of transportation professionals (cictp 2022), changsha, china, virtual meeting, july 8-11, 2021
[2].xinlian yu; song gao; optimal routing of multiple vacant taxis: a policy gradient method with endogenous state transition probabilities, the 100th annual meeting of transportation research board compendium of papers. virtual meeting, jan.25-29, 2021
[3]. xinlian yu; alireza khani; real-time transit control for transfer synchronization with deep reinforcement learning transportation research board, the 100th annual meeting of transportation research board compendium of papers. virtual meeting, jan. 25-29, 2021
[4].xinlian yu; song gao; a model-free batch reinforcement learning approach for vacant taxi routing with e-hailing, the 24th international conference of hong kong society for transportation studies, hong kong, dec.14-16, 2019
[5]. xinlian yu; alireza khani; operation of shared autonomous vehicle systems: optimal fleet sizing and depot deployment, 2019 informs annual meeting, seattle, oct.10-23, 2019
[6]. xinlian yu; song gao; optimizing vacant taxis routing decisions: model-based and model -free approaches, the 98th annual meeting of transportation research board compendium of papers., washington, dc, jan.13-17, 2019
其他：
[1]. 指导本科生获2022年第七届江苏省交通科技大赛三等奖
[2]. 指导研究生获2021年第十八届中国研究生数学建模竞赛二等奖
[3]. travel award, the international association for travel behavior research (iatbr)，2018.07
[4]. the 2nd place finalist, the north american regional science council (narsc) graduate student paper competition，2017.11
