Mahdi Zaman

I am an engineer with a rationally optimistic enterpreneurial mindset, experienced in robot vision, connectivity and transportation. Currently I do research on memory-efficient vision models and connected automated driving at CAVREL-UCF. I am seeking industry mentors and would love to work as an intern with you for Summer 2024. Please reach out to discuss ideas and projects that we can work on together.

Email / CV / Google Scholar / Github / LinkedIn / X

I am driven by the curiosity to explore our abilities as a species. Engaging in the field of machine intelligence can yield useful insights in this pursuit. I spend most of my time in developing algorithms and systems aimed at robot vision and learning; both at the level of individual agent and within larger systems. In my spare time, I enjoy delving into concepts on evolution, fitness, neuroscience, psychology and spirituality, often through hands-on experiences. Occassionally, I share concise reflections on my thoughts and personal experiences through my blog.

Research & Projects

I build algorithms and systems for robots. My research projects have been wonderful opportunities to learn about robot perception, remote driving (both automated and humandriven), scaling vehicular communication and writing systems for specific applications. Currently I am working on the highlighted projects.

Perception & Control for Autonomous Vehicles

Working on improving scene understanding in machine vision to make better decisions.

	Multi-scale Region Attention for Segmentation Mahdi Zaman, Md Mahfuz Al Hasan, Abdul Jawad project page / github Working on a novel multi-scale attention mechanism which currently achieves comparable performance on semantic segmentation with much lower computational cost than state-of-the-art models of similar size. Currently expanding the scope of the project to include classification, object detection and instance segmentation.
	Automated Vehicle Marshalling Mahdi Zaman, Ghayoor Shah, Yaser P Fallah project page Enabling remote driving in controlled terrain for manufacturing/warehouse/parking applications. Currently experimenting on synthetic scenarios generated in-house and plans for real-world testing are underway.
	Connected And Autonomous Vehicles In The Deep Learning Era: A Case Study On Computer-guided Steering Rodolfo Valiente, Mahdi Zaman, Yaser P Fallah, Sedat Ozer Handbook of Pattern Recognition and Computer Vision, Chapter 2.10: pp. 365-384, 2020
	Controlling Steering Angle for Cooperative Self-driving Vehicles utilizing CNN and LSTM-based Deep Networks Rodolfo Valiente, Mahdi Zaman, Sedat Ozer, Yaser P Fallah Intelligent Vehicles (IV) Symposium, 2019 paper/ bibtex / poster We present a novel neural network model to leverage local (from on-board sensors) and look-ahead (via V2X) perception for efficient steering maneuver. It empowers the host vehicle with enhanced safety and prior knowledge for navigating a wide range of road scenarios.

Infrastructure-assisted Tolling

An infrastructure-assisted transaction procedure is presented. Potential use-cases are: toll collection, road user charging, remote driving, automated valet parking etc. The application leverages high-speed communication via Cellular-V2X. Outcomes aim for development of SAE J3217 standard.

	On Batching Acknowledgements in C-V2X Services Mahdi Zaman, Md Saifuddin, Mahdi Razzaghpour, Yaser P Fallah, Jayanthi Rao 97th IEEE Vehicular Technology Conference (VTC), 2023 paper / bibtex
	Performance Analysis of V2I Zone Activation and Scalability for C-V2X Transactional Services Mahdi Zaman, Md Saifuddin, Mahdi Razzaghpour, Yaser P Fallah 96th IEEE Vehicular Technology Conference (VTC), 2022 paper / bibtex / poster

Scaling V2X

Vehicle-to-everything (V2X) communication enables vehicles to share their cognition and constitute a form of mass intelligence in partial or fully autonomous traffic environment to overcome the limitations of a single agent planning in a decentralized fashion. Specifically, our proposed methods enable the 3GPP C-V2X communication technology to handle thousands of vehicles in heavily congested environments.

	Addressing Rare Outages in CV2X with Time-Controlled One-shot Resource Scheduling Md Saifuddin, Mahdi Zaman, Yaser P Fallah, Jayanthi Rao IEEE TechRxiv, 2023 paper / bibtex
	Performance Analysis of Cellular-V2X with Adaptive & Selective Power Control Md Saifuddin, Mahdi Zaman, Behrad Toghi, Yaser P Fallah, Jayanthi Rao IEEE Connected and Automated Vehicles Symposium (CAVS), 2020 paper / bibtex

System Design & Modeling

	Predictive Model-Based and Control-Aware Communication Strategies for Cooperative Adaptive Cruise Control Mahdi Razzaghpour, Rodolfo Valiente, Mahdi Zaman, Yaser P Fallah IEEE Open Journal of Intelligent Transportation Systems, Vol. 4, pg 232-243, 2023 paper / arXiv / bibtex We leverage Model-Based Communication (MBC) and propose a solution that enables cooperative control of vehicle platoons under non-ideal communication scenarios.
	Finite State Markov Modeling of C-V2X Erasure Links For Performance and Stability Analysis of Platooning Applications Mahdi Razzaghpour, Adwait Datar, Daniel Schneider, Mahdi Zaman, Herbert Werner, Hannes Frey, Javad Mohammadpour Velni, Yaser P Fallah IEEE International Systems Conference (SysCon), 2022 paper / arXiv / bibtex We model the inter-vehicle links in a platoon with a first-order Markov model to capture the prevalent temporal correlations for each link.
	Control-aware Communication for Cooperative Adaptive Cruise Control Mahdi Razzaghpour, Rodolfo Valiente, Mahdi Zaman, Yaser P Fallah arXiv / bibtex We propose a combination of control-aware communication and model-based communication. Our proposed solution reduces communication overhead by ~47% while maintaining nearly the same level of efficiency (less than 1% speed deviation) in cooperative adaptive cruise control.
	Dynamic Object Map based Architecture For Robust CVS Systems Rodolfo Valiente, Arash Raftari, Mahdi Zaman, Yaser P Fallah, Syed Mahmud SAE Technical Paper, 2020 SAE Mobilus / bibtex We propose a modular architecture with separate subsystems for application and perception with a novel non-parametric Bayesian inference-based prediction method. We validate the architecture in conjunction with the prediction mechanism with real environment using Denso On-Board-Unit (OBU). The proposed system shows enhanced immunity to communication loss in V2X channel.
	A Maneuver-based Urban Driving Dataset and Model for Cooperative Vehicle Applications Behrad Toghi, Divas Grover, Mahdi Razzaghpour, Rajat Jain, Rodolfo Valiente, Mahdi Zaman, Ghayoor Shah, Yaser P Fallah IEEE Connected and Automated Vehicles Symposium (CAVS), 2020 paper / arXiv / bibtex We introduce a real-world maneuver-based driving dataset that is collected during our urban driving data collection campaign.

Patent

One-shot Transmission For V2X Messaging
Jayanthi Rao, Ivan Vukovic, Yaser P Fallah, Md Saifuddin, Mahdi Zaman
US 2023/0057331 A1
Details

We developed a novel 1-shot transmission scheme for Semi-Persistent Scheduling (SPS) that improves the latency and reliability of connected messages, independent of SPS-allocated resources.

Miscellanea

Instructor, Algorithms for Machine Learning

Spring 2023, University of Central Florida

Originally stolen from Jon Barron's amazing website (source code). Feel free to repurpose.