About

A summary of my background, research, and training. For the full record, see my CV (PDF).

I am a final-year Robotics & Mechatronics undergraduate working toward robot learning for locomotion across morphologies. My current research learns recovery policies for a wheeled Mars rover trapped in deformable granular terrain: mobility when contact is uncertain and no hand-designed escape recipe exists. This work was accepted to the Space Robotics Workshop at IEEE/RSJ IROS 2026.

I want to carry that problem from wheels to quadrupeds to bipeds, where richer contact and stricter balance make model-based controllers fail more sharply. I am drawn to reinforcement learning, learning-based control, and Sim2Real, and to putting simulation-trained policies on hardware. I am currently seeking a PhD, MS, or Research Assistant position in robot learning.

Education

2022 – 2026

B.Sc. in Robotics & Mechatronics Engineering

University of Dhaka

Fourth year (8th of 8 semesters), ongoing. CGPA 3.50 / 4.00. Expected October 2026.

2019 – 2021

Higher Secondary Certificate

Sylhet MC College

Sylhet, Bangladesh. Board rank 62 (Sylhet Board, 2021).

Research experience

Apr 2025 – Present

Undergraduate Researcher: MARVEL Lab

University of Dhaka · Supervisor: Dr. Sejuti Rahman

Lead author on DRL controllers that recover rover mobility in deformable Mars regolith. Designed yaw-projected reward shaping with entrapment-gated slip penalties (a safety-style constraint) and built large-scale, multi-GPU training and evaluation pipelines. The resulting paper, Escape Without a Recipe: Maneuver-Agnostic Mars Rover Recovery from Granular Entrapment, was accepted to the Space Robotics Workshop at IEEE/RSJ IROS 2026 (poster).

Aug 2025 – Present

Research Assistant (Remote)

University of Texas Rio Grande Valley

Building a digital-twin warehouse benchmark to evaluate Deep RL navigation policies (PPO, SAC, TD3) under realistic perception and localization noise.

Jan – Dec 2024

Undergraduate Research Student

North South University · Supervisor: Dr. Mahdy Rahman Chowdhury

Studied melanoma segmentation from pseudo-annotations under limited labels (weakly-supervised computer vision).

Leadership & engineering

Jul 2026 – Present

Embedded Engineer (Part-time)

Intelis Solution Ltd.

STM32-based autonomous drone platforms for maritime monitoring, robust firmware, hardened telemetry, weather-resistant sensing.

Jun 2025 – Aug 2025

ROS Development Intern

Karthikesh Robotics Pvt. Ltd., Chennai (Remote)

Developed autonomous robots for industrial and educational use with ROS2 navigation and perception stacks.

2025 – 2026

Project Lead: Mohakashchari Rover Team

Dhaka University

Proposed the concept at IEEE SB DU and led design, frame integration, and fundraising for a competition-ready rover platform.

2023 – 2026

Chair, IEEE Robotics & Automation Society

University of Dhaka (Chair 2025–2026; Student Activity Secretary 2023–2024)

Led chapter activities, events, and research collaborations promoting robotics and automation among students.

Technical skills

Reinforcement & robot learning

  • PyTorch, NVIDIA Isaac Lab
  • PPO · SAC · TD3
  • Reward shaping, domain randomization
  • Curriculum learning, Sim2Real

Robotics & simulation

  • ROS2, Gazebo
  • Nav2, MoveIt
  • SLAM, OpenCV

Programming & systems

  • Python, C / C++ (learning CUDA)
  • Bash, Git
  • Linux, Ubuntu, Arch, Kali

Hardware & CAD

  • STM32, Raspberry Pi
  • Fusion 360, ANSYS
  • PCB design

Awards

  • 8th place, DU AI Challenge (2025)
  • 4th, BD Astronomy & Astrophysics Olympiad (2021)
  • Rank 62, HSC 2021 (Sylhet Board)

Selected coursework

  • Artificial Intelligence; Intelligent Systems & Robotics
  • Advanced Robotics; Control Systems Design
  • Robot Vision & Image Processing; DSP
  • Linear Algebra; Probability & Statistics