首页 >> 新闻动态

Master Student Omar Hassanen Successfully Defends硕士研究生Omar Hassanin顺利通过答辩

发表时间:   阅读次数:

Omar Hasssanin, enrolled in September 2019, Master Degree, Egyptian.

留学生Omar Hassanin,于2019年9月入学同济大学,就读交通运输工程专业,硕士学位,国籍为埃及。

 

Campus Experience/校园生活:

I was living in Jiading campus, and I liked it so much. The natural sceneries in Jiading campus is so beautiful. One of my hopes was to go for a walk in the campus for an hour or more.  I also joined some festivals with Chinese students, and I was playing piano with them. I enjoyed going to the lab 409 and meet my teammates. The food in the Halal canteen was so delicious because they offer vast of different vegetable dishes, noodles, and meat. They clean the tables and chairs regularly.

Omar住在同济大学嘉定校区,热爱嘉定校区美丽的自然风景。即使在毕业后依旧希望能在校园里散步一小时或更长时间。在校生活期间,Omar参加了许多中国的节日活动,还和中国学生一起弹钢琴。Omar很喜欢去实验室和团队成员一起学习。此外,清真食堂的食物十分美味,食堂不仅提供大量不同的蔬菜、面条和肉类,工作人员还会定期清理桌椅保持环境整洁。在校学习期间,共发表了3篇期刊论文和3篇会议论文,并参与了2个项目的工作。

September 2019 with advisor Prof. Xuesong Wang

2019年9月与导师王雪松教授合影

 

August 2020 with the research group

2020年8月与课题组合影

 

October 2021 with friends

2021年10月与同学合影

 

Projects/参与科研项目:
[1]Evaluation of Roadway Infrastructures Readiness for Autonomous Vehicles, funded by Intel, from 2018 to 2022. Most of my thesis work was related to “Evaluation of Roadway Infrastructures Readiness for Autonomous Vehicles” project. I was responsible for designing and testing several algorithms of the automated vehicle, especially longitudinal controls.
中国特色道路环境的自动驾驶适驾性仿真与评估,资助方为英特尔公司,2018年-2022年。硕士论文与该项目有关,其中主要负责设计和测试自动驾驶汽车的几种算法,特别是纵向控制。
[2]Societal Level Impacts of Connected and Automated Vehicles, funded by EU Horizon 2020, from 2019 to Present. I was gathering some materials related to the automated vehicle in “LEVITATE” project.
Societal Level Impacts of Connected and Automated Vehicles,资助方为EU Horizon 2020,2019年-至今。在该项目中主要负责收集与自动驾驶汽车有关的一些材料。

 

Thesis Defense/毕业论文答辩:

Road crashes kill more than 1.25 million people worldwide each year, and rear-end collisions are responsible for about 32.5 percent of all car accidents in 2019 in the United States. Fortunately, automated vehicles (AVs) have their potential to enhance transportation safety and save people lives, by preventing human driver errors. Therefore, the main objective of the thesis is to design several longitudinal controls to allow AVs to drive safely during car following to prevent rear-end collisions. AVs Longitudinal controls need to have collision-avoidance strategies to generate acceleration/deceleration according to the safety rules. Many collision-avoidance systems and strategies have been developed recently; however, most of these systems and strategies cannot yet assure collision-free driving, but the Responsibility-Sensitive Safety (RSS) model, developed by Intel Mobileye, shows potential to enhance AV safety.

全世界每年有超过125万人死于道路交通事故,而在2019年美国的所有车祸中,追尾碰撞约占32.5%。幸运的是,自动驾驶汽车(AVs)有其潜力,可以通过防止人类驾驶错误,提高交通安全,拯救人们的生命。因此,本论文的主要目的是设计几个纵向控制策略,使AV在跟车过程中安全行驶,防止追尾碰撞。AV纵向控制需要包含避撞策略,根据安全规则输出加速度、减速度。近年来,许多避撞系统和策略被提出,然而这些系统和策略大多还不能完全保证驾驶中无碰撞发生,但英特尔Mobileye开发的责任敏感安全(RSS)模型显示了提高AV安全性的潜力。

Therefore, the thesis mainly uses the RSS longitudinal safe distance model and embeds it into several longitudinal controls, such as Intelligent Driver Model (mathematical model), Model Predictive Control (controller), and Deep Deterministic Policy Gradient Model (deep reinforcement learning model). Moreover, the RSS model and the other mentioned longitudinal controls are further modified to improve their performance and safety. In order to test the designated longitudinal controls, simulations were conducted using car-following scenarios extracted from Shanghai Naturalistic Driving Study dataset. The results evaluation process is divided into performance and safety, using AV performance and Surrogate Safety Measurements (TTC, TIT, and TET). It is found that the RSS model and the designated longitudinal controls can enhance the automated driving significantly.

因此,本论文主要使用RSS纵向安全距离模型,并将其嵌入到几个纵向控制中,如智能驾驶员模型(数学模型)、模型预测控制(控制器)和深度确定型策略梯度模型(深度强化学习模型)。此外,RSS模型和其他提到的纵向控制被进一步修改以提高其性能和安全性。为了测试指定的纵向控制,使用从上海自然驾驶研究数据集中提取的跟车场景进行了模拟。结果评估过程分为性能和安全性,使用AV性能和安全替代指标(TTC、TIT和TET)。研究发现,RSS模型和指定的纵向控制可以显著提高自动驾驶的性能。

Omar Hassanin, Master student in the class of 2019, defended his Master's thesis and successfully passed it on 21 January 2022.

2019级硕士研究生Omar Hassanin于2022年1月21日进行了硕士毕业论文答辩,并顺利通过。

Omar Hassanin introduced master's thesis《Calibrating, Developing and Evaluating Responsibility-Sensitive Safety Using Shanghai Naturalistic Driving Study》
Omar Hassanin介绍硕士论文《基于上海自然驾驶数据标定、构建和评估责任敏感安全模型》

 

Journal Papers/期刊论文:
[1]Xu X, Wang X, Wu X, Hasssanin O, et al. Calibration and Evaluation of the Responsibility-Sensitive Safety Model of Autonomous Car-Following Maneuvers Using Naturalistic Driving Study Data. Transportation Research Part C: Emerging Technologies, vol. 123, pp. 1-17, Jan. 2021.
[2]Liu S, Wang X, Hassanin O, et al. Calibration and Evaluation of Responsibility-Sensitive Safety (RSS) in Automated Vehicle Performance During Cut-In Scenarios. Transportation Research Part C: Emerging Technologies, vol. 125, pp. 1-15, Mar. 2021.
[3]Qin D, Wang X, Hassanin O, et al. Operational Design Domain of Automated Vehicles for Crossing Maneuvers at Two-Way Stop-Controlled Intersections. Accident Analysis & Prevention, vol. 167, March. 2022.

 

Conference Papers/学生会议论文:
[1]Sun P, Wang X, Hassanin O, Zhu M.  Modeling Car-following Behavior on Freeways Considering Driving Style. Transportation Research Board 100th, Oct. 2020.
[2]Hassanin O, Wang X, Wu X, Xu X. Performance and Safety Evaluation of Responsibility-Sensitive Safety in Freeway Car-Following Scenarios Using the Intelligent Driver Model and Model Predictive Control. Transportation Research Board 100th, Oct. 2020.
[3]Qin D, Wang X, Hassanin O, et al. Operational Design Domain of Automated Vehicles for Crossing Maneuvers at Two-Way Stop-Controlled Intersections. Transportation Research Board 101th, Oct. 2021.

 

 


 

©CopyRight 2003-2012   同济大学交通运输工程学院

备案号:沪ICP备13005359号-1