講座主題：基于大規(guī)模仿真平臺和人工智能的需求響應(yīng)出行服務(wù)運營策略
時間：2023年7月22日 9:30~10:30
地點：大連理工大學(xué)厚興樓（三號實驗樓）405
報告人：柯錦濤 博士，助理教授
Title: A large-scale simulation platform and artificial intelligence based operational strategies for on-demand ride services
Abstract:
On-demand ride services or ride-sourcing services, offered by transportation network companies like Uber, Lyft and Didi, have been experiencing fast development and steadily reshaping the way people travel in the past decade. Various mathematical models and optimization algorithms, including reinforcement learning approaches, have been developed in the literature to help ride-sourcing platforms design better operational strategies to achieve higher operational efficiency. However, due to cost and reliability issues (implementing an immature algorithm for real operations may result in system turbulence), it is commonly infeasible to validate these models and train/test these optimization algorithms within real-world ride sourcing platforms. Acting as a useful test bed, a simulation platform for ride-sourcing systems will thus be very important for both researchers and industrial practitioners to conduct algorithm training/testing or model validation through trails and errors. While previous studies have established a variety of simulators for their own tasks, it lacks a fair and public platform for comparing the models/algorithms proposed by different researchers. In addition, the existing simulators still face many challenges, ranging from their closeness to real environments of ride-sourcing systems, to the completeness of different tasks they can implement. To address the challenges, we propose a novel multi-functional and open-sourced simulation platform for ride-sourcing systems, which can simulate the behaviors and movements of various agents (including drivers and passengers) on a real transportation network. It provides a few accessible portals for users to train and test various optimization algorithms, especially reinforcement learning algorithms, for a variety of tasks, including on-demand matching, idle vehicle repositioning, and dynamic pricing. In addition, it can be used to test how well the theoretical models, developed in the literature for equilibrium analysis and strategic planning, approximate the simulated outcomes. Evaluated by experiments based on real-world datasets, the simulator is demonstrated to be an efficient and effective test bed for various tasks related to on-demand ride service operations.
在過去十年中，由Uber、Lyft和滴滴等交通網(wǎng)絡(luò)公司提供的需求響應(yīng)出行服務(wù)或網(wǎng)約車服務(wù)經(jīng)歷了快速發(fā)展，并穩(wěn)步重塑了人們的出行方式。包括強化學(xué)習(xí)方法在內(nèi)的各種數(shù)學(xué)模型和優(yōu)化算法已在文獻中得到開發(fā)，以幫助網(wǎng)約車平臺設(shè)計更好的運營策略，實現(xiàn)更高的運營效率。然而，由于成本和可靠性問題（在實際運營中實施不成熟的算法可能會導(dǎo)致系統(tǒng)紊亂），在現(xiàn)實世界的乘車外包平臺中驗證這些模型和訓(xùn)練/測試這些優(yōu)化算法通常是不可行的。因此，作為一個有用的測試平臺，網(wǎng)約車的仿真平臺對于研究人員和工業(yè)從業(yè)人員通過跟蹤和錯誤進行算法培訓(xùn)/測試或模型驗證都是非常重要的。盡管之前的研究已經(jīng)針對各自的任務(wù)建立了多種模擬器，但缺乏一個公平、公開的平臺來比較不同研究人員提出的模型/算法。此外，現(xiàn)有的模擬器仍然面臨著許多挑戰(zhàn)，從它們是否接近真實的網(wǎng)約車系統(tǒng)環(huán)境，到它們所能實現(xiàn)的不同任務(wù)的完整性。為了應(yīng)對這些挑戰(zhàn)，我們提出了一個新穎的多功能、開源的乘車網(wǎng)約系統(tǒng)仿真平臺，它可以模擬真實交通網(wǎng)絡(luò)中各方（包括司機和乘客）的行為和動作。它為用戶提供了多個接口，用于訓(xùn)練和測試各種優(yōu)化算法，特別是強化學(xué)習(xí)算法，以完成各種任務(wù)，包括按需匹配、閑置車輛重新定位和動態(tài)定價。此外，它還可用于測試文獻中開發(fā)的用于平衡分析和戰(zhàn)略規(guī)劃的理論模型與模擬結(jié)果的近似程度。通過基于真實世界數(shù)據(jù)集的實驗評估，該模擬器被證明是與按需乘車服務(wù)運營相關(guān)的各種任務(wù)的高效和有效的測試平臺。
Short Bio:
Dr. Jintao Ke is an Assistant Professor in the Department of Civil Engineering at the University of Hong Kong (HKU). Dr. Ke received his B.S. degree (2016) in civil engineering from Zhejiang University, and his PhD degree (2020) in Civil and Environment Engineering from Hong Kong University of Science and Technology. Prior to joining HKU, he was a research assistant professor in the Hong Kong Polytechnic University. His research interests include shared mobility on demand, transportation big data analytics, multimodal intelligent transportation systems, transportation pricing, short-term travel demand forecasting, etc. The vision of his research is to develop novel models, algorithms, and conduct data-driven quantitative analyses to better manage, operate, and regulate shared mobility and other emerging mobility services. He has published over 30 SCI/SSCI indexed research papers in top-tier journals in the field of transportation research and data mining, such as Transportation Research Part A-E, IEEE Transactions on Intelligence Transportation System, IEEE Transactions on Knowledge and Data Engineering. He was awarded the Honorable Mention of HKSTS Outstanding Dissertation Award in 2020. He serves as an Advisory Board Member of Transportation Research Part C, guest editors of two Special Issues of Transportation Research Part C and Travel Behavior and Society, and referees for a few top transportation journals.
柯錦濤博士是香港大學(xué)土木工程系助理教授?？虏┦坑?/span>2016年獲得浙江大學(xué)土木工程學(xué)士學(xué)位，并于2020年獲得香港科技大學(xué)土木與環(huán)境工程博士學(xué)位。在加入香港大學(xué)之前，他是香港理工大學(xué)的研究助理教授。他的研究興趣包括共享出行、交通大數(shù)據(jù)分析、多式聯(lián)運智能交通系統(tǒng)、交通定價、短期出行需求預(yù)測等。他的研究興趣是開發(fā)新型模型和算法，并進行數(shù)據(jù)驅(qū)動的定量分析，以更好地管理、運營和規(guī)范共享交通和其他新興交通服務(wù)。他在交通研究和數(shù)據(jù)挖掘領(lǐng)域的頂級期刊上發(fā)表了30多篇SCI/SSCI收錄的研究論文，如《Transportation Research Part A-E》、《IEEE Transactions on Intelligence Transportation System》、《IEEE Transactions on Knowledge and Data Engineering》等。他于2020年獲得香港科技學(xué)會優(yōu)秀論文榮譽獎。擔(dān)任《Transportation Research Part C》顧問委員會成員，《Transportation Research Part C》和《Travel Behavior and Society》兩本專刊的客座編輯，并擔(dān)任多家頂級交通期刊的審稿人。
