Hi! I am Sadman. I am a second-year PhD student in the Center for Resilient Autonomous Systems (RISE) at UCI, advised by Professor Mohammad Abdullah Al Faruque. I got my Masters from University of Wisconsin-Madison in 2024. My research focuses developing autonomous robots for real-world applications. In my recent projects, I have worked on 3D navigation in unknown environments, wrist-design for dexterous hands and identifying task primitives in human demonstrations. I am currently working on dexterous manipulation for domain-specific tasks. My work combines classical control algorithms with learning-based approaches for autonomous operation.

Before starting my PhD, I worked briefly at Meta focusing on networking for AI training/inferenece. I also had the opporunity to intern at HPE in Summer 2023 and at Meta in Summer 2024, working on AI/HPC systems. Before coming to UW-Madison, I obtained my undergraduate major in Computer Science from Bangladesh University of Engineering and Technology and my undergraduate thesis was on Interpretable CNN .

For UCI students: If you are a Master's, or undergraduate student at UCI, and interested in working with me, please reach out. Our lab is equipped with humanoid, quadruped, manipulator arms and drones, and good computing resources. Feel free to email me if you want to learn more about my current research projects.

Interests

  • Robot Autonomy
  • Dexterous Manipulation
  • Navigation and Exploration

Education

  • Doctor of Philosophy in Computer Engineering (2025 - 2029)

    University of California, Irvine

  • Masters of Science in Computer Sciences (2022 - 2024)

    University of Wisconsin-Madison

  • Bachelor of Science in Computer Science (2017 - 2022)

    Bangladesh University of Engineering and Technology




Projects

 
 
 
 
 

Taxonomy of Construction Task Activities

IROS 2026 Future of Construction Workshop

July 2026 - Sep 2026

Developed a taxonomy of construction task activities by analyzing O*NET data and instructional construction task videos. The taxonomy identifies primitive actions for a robot worker to perform construction tasks. The primitives can be composed into skills and in different combinations to facilitate complex construction tasks. [Arxiv] [PDF] [Data] [Demo]

 
 
 
 
 

Wrist Design for Tendon-Driven Hands

IROS 2026 Sensors and Actuators for Dexterous Manipulation Workshop

Jun 2026 - Sep 2026

We designed a 2-DoF wrist extension for a tendon-driven hand (CRAFT hand) that does not require any modifications to the existing hand structure. Our concentric design allows for a compact wrist with minimal axial depth. [Arxiv] [PDF] [Website]

 
 
 
 
 

Near-ground Target Search with UAV

In Review

Oct 2025 - Sep 2026

Proposed a balanced exploration-exploitation strategy in both horizontal and vertical directions for a UAV to search for a target near the ground. The UAV follows a set route and opportunistically explores when it gets stuck to find flight corridors avoiding large and wide obstacles.



Experience

Production Engineer

Meta

Worked on reliability and performance of AI/GPU networking infrastructure and devices.

Production Engineering Intern

Meta

Worked on InfiniBand fabric for AI/HPC clusters

Platform Engineering Intern

Hewlett Packard Enterprise

Contributed to Linux kernel drivers for HPE Slingshot networking devices. Designed and implemented kernel-module API across multiple drivers.




Publications

A Taxonomy of Construction Task Activities for Robot Workers. In IROS 2026 5th Workshop on Future of Construction.
A Direct Rigid Transmission 2-DoF Wrist Extension for Tendon-Driven Hand In IROS 2026 Sensors and Actuators for Dexterous Manipulation Workshop.
Balancing Exploration and Exploitation for Near-Ground Target Search with UAVs. In Review.


Contact