主题：Optimal Driving for Vehicle Fuel Economy under Traffic Speed Uncertainty 随机车流速度下的节能驾驶策略
主讲人：香港理工大学叶洪波助理教授
主持人：英国威廉希尔公司肖峰教授
时间： 2022年6月10日（周五）14:00
举办地点：腾讯会议，ID:589 360 599
主办单位：英国威廉希尔公司人工智能与管理科学研究中心科研处
主讲人简介：
Dr Hongbo Ye is a Research Assistant Professor in the Department of Electrical Engineering at Hong Kong Polytechnic University. He received BEng in Automation from University of Science and Technology of China and PhD in Civil Engineering from The Hong Kong University of Science and Technology. Previously, he worked in University of Leeds as Research Fellow and University of Liverpool as Lecturer. Dr Ye’s research includes transportation network modelling and optimisation, autonomous vehicle operation and control, and railway management. He has published papers in leading transportation journals (such as Transportation Science and Transportation Research Part B) and prestigious transportation conferences.
叶洪波博士现任香港理工大学研究助理教授。他分别于中国科学技术大学和香港科技大学获得自动化工学学士和土木工程博士学位，并曾在英国利兹大学和利物浦大学工作。叶博士的研究方向包括交通系统建模和优化，无人车控制和运营，以及铁路系统管理。他在交通领域顶级期刊（Transportation Science，Transportation Research Part B等）上发表多篇文章。
内容简介：
This paper uses stochastic optimization techniques to minimize the fuel consumption of a vehicle under uncertain traffic speed. Minimizing the fuel consumption of a moving vehicle can be formulated as an optimal control problem that determines the speed profile that the vehicle should follow. The fuel consumption is affected by speed, acceleration, and external parameters such as road grades and speed limits. In addition, surrounding traffic conditions, and in particular traffic speed, may prevent the vehicle from following the optimal speed profile and consequently affect the fuel economy and the journey time. Uncertainty in the traffic speed will affect the optimization of fuel-economical speed profiles, which has seldom been investigated in the literature. This paper describes stochastic optimization models with chance constraints for minimizing the fuel consumption of a vehicle traveling over a given stretch of road under a given time limit, where the traffic speed is assumed to be random and follow a certain probability distribution. Computational results are presented to evaluate the performance of the proposed models and assess the impact of traffic speed uncertainty on the desired speed profiles. The results affirm that uncertainty in traffic speeds can significantly increase the fuel consumption and the journey time of the speed profiles created by deterministic model. Such impact can be mitigated by incorporating the stochasticity at the planning stage using the stochastic optimization models described in this paper.
节能驾驶问题通过优化车辆的速度曲线来减小车辆在给定路段上的油耗。这一问题通常可以用最优控制模型来建模并求解。车辆的油耗与车辆的实时速度和加速度相关，并且受驾驶环境（如道路坡度、道路限速等）的影响。此外，周围车辆的速度（或路面车流速度）会限制车辆节能驾驶速度曲线的实施，进而影响车辆的油耗和行程时间。路面车流速度通常具有随机性，因此，在决策节能驾驶速度曲线时考虑车流速度的随机性，具有现实意义，但目前鲜有文献对此进行研究。为了计算随机车流速度下的节能速度曲线，本文假设车流速度是随机的并且服从某种概率分布，据此建立带机会约束的随机优化模型来最小化车辆的期望油耗。数值实验验证了随机优化模型的有效性，以及车流速度的随机性对节能速度曲线的影响：随机车流速度不仅增加了车辆的油耗，而且延长了行程时间；随机优化模型计算出的节能速度曲线能有效地降低随机车流速度的影响。
