S. (Saeed) Rahmani

S. (Saeed) Rahmani

Contact

Room: 23.HG 4.02

Profile

Biography

Saeed is a PhD candidate in the Department of Transport and Planning at the Faculty of Civil Engineering and Geosciences at Delft University of Technology. After receiving his master’s degree in Transportation Engineering in 2017, Saeed joined Traffic Research Laboratory at IUST as a traffic engineer and contributed to several projects in the transportation domain, such as Iran’s Transportation Masterplan Studies, Travel Pattern Discovery using Anonymized Mobile Phone Data in Tehran, and Tehran’s Taxi Fleet Management Study.

In 2022, Saeed joined the Department of Transport and Planning at TU Delft as a PhD candidate participating in HiDrive, a flagship EU-funded project, that aims to make driving automation robust and reliable by taking intelligent vehicle technologies to conditions and scenarios neither extensively tested nor demonstrated earlier in European and overseas traffic. Saeed is using microsimulation tools to study the complex interactions in a mixed flow of automated vehicles (AVs) and human-driven vehicles in order to assess the impacts of AVs on traffic flow and transportation network efficiency and safety.

Expertise

Saeed's expertise is mainly in traffic simulation. At TU Delft, he is to develop a control logic for automated vehicles that can reproduce diverse driving styles and strategies and execute complex maneuvers in simulation tools. This control logic could be applied to 1. assess the impact of automated vehicles on traffic flow efficiency and safety in complex environments and 2. evaluate the applicability and safety of currently developed motion planning models by providing a more realistic simulation environment. To achieve that, he aims to develop a generic framework that can learn from data continuously, but at the same time, can benefit from theory physics rules.


Projects

Hi-Drive: Hi-Drive addresses a number of key challenges, which are currently hindering the progress of developments in vehicle automation. Our key aim is to advance the state of the art of Automated Driving (AD) technologies. We focus on testing, demonstrating, and evaluating robust high automation functions in a large set of traffic environments, not currently achievable:
  • Complex interaction with other road users in normal traffic
  • Automated vehicles traveling in challenging conditions covering variable weather and traffic scenarios
  • New information about user preferences and reactions including comfort and trust – and eventually, enabling viable business models for AD

Read more

Expertise

Publications

Prizes

  • 2023-9-28

    Best Student Paper Runner-up Award (IEEE ITSC 2023)

    Won the Best Student Runner-up Award at 26th IEEE International Conference on Intelligent Transportation Systems ITSC 2023
    26th IEEE International Conference on Intelligent Transportation Systems, ITSC 2023

    Read more Best Student Paper Runner-up Award (IEEE ITSC 2023)

Ancillary activities

Contact

Room: 23.HG 4.02