Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Binary file modified assets/images/people/ehsan-marjani.jpg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
104 changes: 85 additions & 19 deletions src/people/ehsan-marjani.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,35 +5,101 @@ title: Postdoctoral Fellow
photo: ehsan-marjani.jpg
short_bio: A soccer player who built soccer-playing robots — now researching multi-agent perception with event-based vision.
supervisor: Giovanni Beltrame
tags: [Multi-Agent Perception, Event-Based Vision, Cooperative Localization]
tags: [Robotic Perception
Event-Based Vision,
Swarm Robotics,
Cooperative Localization,
Multi-Agent Systems]
email: ehsan.marjani@polymtl.ca
scholar: ""
linkedin: https://www.linkedin.com/
scholar: 4OsTRVIAAAAJ
orcid: 0000-0003-3139-6063
linkedin: https://www.linkedin.com/in/seyed-ehsan-marjani-bajestani/
order: 2
---

Seyed Ehsan Marjani Bajestani is a Postdoctoral Fellow at the MIST Lab. He
started in robotics by building a line-follower robot in high school, went on to
a B.Sc. in Electrical Engineering and an M.Sc. in Mechatronics Engineering, and
became deeply involved in multi-agent robotics as a member of the Mechatronics
Research Laboratory and an executive committee member of the RoboCup Middle Size
soccer robot League.
Seyed Ehsan Marjani Bajestani is a Postdoctoral Fellow at the MIST Lab,
Polytechnique Montréal. He received his B.Sc. in Electrical Engineering and
M.Sc. in Mechatronics Engineering before joining the MIST Lab as a Ph.D.
student in Computer Engineering at Polytechnique Montréal, where he conducted
research on event-based perception and robotic vision. He later joined the
MIST Lab as a Postdoctoral Fellow.

His research spans swarm robotics, multi-agent systems, robotic perception, and
embedded systems. Throughout his career, he has combined academic research with
hands-on engineering, contributing to projects ranging from autonomous robotic
exploration and search-and-rescue systems to event-based perception, embedded
medical devices, and large-scale robotic coordination. He has also been actively
involved in the [RoboCup community](https://www.robocup.org/) for over a decade.
After competing in the RoboCup Middle Size League from 2014 to 2017 and contributing
to multiple international championship-winning teams, he went on to serve as
a Technical Committee Member and later as an Executive Committee Member until
2024, supporting the league’s technical and organizational development.

## Current Work

Ehsan's research interests are in multi-agent perception — cooperative
localization, tracking, and formation strategies. He currently focuses on
cooperative tracking using event-based vision, across environments ranging from
structured soccer fields to fully unknown terrain.
Ehsan’s research focuses on swarm robotics, multi-agent systems, and robotic
perception. He is currently working on the Swarm Orchestra project, investigating
how large groups of autonomous robots can coordinate expressive collective
behaviors through decentralized control, perception, and interaction.

## Previous Projects at MIST Lab

### Event-Based 3D Perception
During his Ph.D. at Polytechnique Montréal, Ehsan developed novel high-speed 3D
sensing methods using event cameras and structured light. His system used a DLP
projector to rapidly project coded color patterns, while a monochrome event-based
camera captured the resulting events to reconstruct both object color and depth
at very high temporal resolution, enabling low-latency robotic perception.

### Portiloop v2
Designed the embedded hardware and [custom PCB](https://github.com/Portiloop/portiloop-hardware)
system for a portable closed-loop EEG stimulation device.

### Search and Rescue with Swarm Robotics
Designed and implemented decentralized search, distributed mapping, and
communication relay strategies that enable autonomous robot swarms to operate
effectively under sparse and intermittent network connectivity.

### IGLUNA
Contributed to autonomous robotic systems for planetary exploration scenarios
and field robotics applications.

## Teaching
- Instructor, Swarm Intelligence, Polytechnique Montréal (Winter 2026)
- Teaching Assistant, Swarm Intelligence, Polytechnique Montréal (Winter 2023)

## Selected Awards
- World Champion, RoboCup 2015, Middle Size League Technical Challenge (Hefei)
- 1st Place, IranOpen 2017 RoboCup, Middle Size League (Tehran)
- 3rd Place, RoboCup 2016, Middle Size League Technical Challenge (Leipzig)

- 1st place, RoboCup 2015, Middle Size League Technical Challenge (Hefei)
- 1st place, IranOpen 2017 RoboCup, Middle Size League (Tehran)
- 3rd place, RoboCup 2016, Middle Size League Technical Challenge (Leipzig)
## Selected Publications
- **Seyed Ehsan Marjani Bajestani** and Giovanni Beltrame.
["Event-based RGB sensing with structured light."](https://doi.org/10.1109/WACV56688.2023.00542)
2023 IEEE/CVF Winter Conference on Applications of
Computer Vision (WACV). IEEE, 2023.
- Ulrich Dah-Achinanon, **Seyed Ehsan Marjani Bajestani**, Pierre-Yves Lajoie,
and Giovanni Beltrame.
["Search and rescue with sparsely connected swarms."](https://doi.org/10.1007/s10514-022-10080-7)
Autonomous Robots 47, no. 7 (2023): 849-863.
- Milo Sobral, Hugo R. Jourde, **S. Ehsan M. Bajestani**, Emily BJ Coffey, and
Giovanni Beltrame.
["Personalizing brain stimulation: continual learning for sleep spindle detection."](https://doi.org/10.1088/1741-2552/adebb1)
Journal of Neural Engineering 22, no. 4 (2025): 046016.
- **Seyed Ehsan Marjani Bajestani** and Giovanni Beltrame.
["Event-Based Vision for Robot Soccer."](https://doi.org/10.1007/978-3-031-85859-8_26)
Robot World Cup. Cham: Springer Nature Switzerland, 2024. 309-317.
- **Seyed Ehsan Marjani Bajestani** and Arsham Vosoughinia.
["Technical report of building a line follower robot."](https://doi.org/10.1109/ICEIE.2010.5559826)
2010 International Conference on Electronics and Information Engineering.
Vol. 1. IEEE, 2010.

Off the clock, Ehsan is a big fan of soccer — and still plays.
## Research Vision
Ehsan is interested in developing autonomous robotic systems that can perceive,
learn, and collaborate in dynamic environments. His long-term goal is to bridge
robotic perception, collective intelligence, and human-robot interaction to enable
teams of robots to operate effectively in real-world applications ranging from
exploration and environmental monitoring to creative and interactive experiences.

## Contact

Reach Ehsan at [ehsan.marjani@polymtl.ca](mailto:ehsan.marjani@polymtl.ca).
Reach Ehsan at [ehsan.marjani@polymtl.ca](mailto:ehsan.marjani@polymtl.ca) or on [LinkedIn](https://www.linkedin.com/in/seyed-ehsan-marjani-bajestani).