I build intelligent systems that bring AI, computer vision, robotics, and machine learning into the real world.
INPUT
stereo + IMU
MODEL
ORB-SLAM3
OUTPUT
map / act
HAMDAN / 2026I'm an Artificial Intelligence undergraduate at NUST, focused on building intelligent systems that can perceive, learn, reason, and act.
My interests include:
I learn best by building, experimenting, and turning ideas into working systems. My goal is to develop practical, capable, and increasingly autonomous intelligent systems that can solve real-world problems.
Start with the environment, not the algorithm.
Choose baselines and metrics people can inspect.
Move from notebook to a system that can respond.
Detection, segmentation, visual inspection, and the discipline of working with imperfect images.
Multimodal modelling, evaluation, medical imaging, and interpretable baselines.
ROS2, mapping, controls, sensor fusion, and systems that have to act in real time.
A ROS2 autonomous-navigation stack for a DJI Tello: monocular ORB-SLAM3 visual SLAM with Depth Anything V2 for active metric scale recovery, plus 3D occupancy mapping and exploration planning layers in active development.
A two-model system combining a ResNet U-Net for multi-class brain tumor segmentation with a conditional diffusion model that synthesizes 4-modality MRI scans from masks. Led as a two-person project and trained on TPU.
A real-time gesture-recognition pipeline controlling a DJI Tello in flight. Built on a self-collected dataset of 5,000+ hand-landmark samples, a feature-engineered classifier, and temporal smoothing for reliable control.
An MPU6050-driven glove that maps hand orientation to real-time servo control on a 4-DOF robotic arm — connecting embedded sensing directly to actuation.
An open-source video-based detection pipeline across 52 animal classes, combining RT-DETR and YOLO through a mixture-of-experts approach for robust performance across varied conditions.
A LAN chat and file-transfer application in C++ with a Qt GUI, custom asynchronous UDP transport, peer auto-discovery, and chunked file transfer.
An open-source conversational agricultural AI combining dual foundation models (fine-tuned Llama 3.2 3B and Llama 3.1 8B), multi-stage RAG, live web search, and an LLM router engineered specifically to prevent hallucinations and false guidance.
Practical engineering and research internships focused on robotics, machine learning, data science, and applied systems.
Intern, Robotics
Completed an internship at NUST's Educational Robotics Lab as part of an international collaboration with the Eureka Robotics Centre at Cardiff Metropolitan University. Gained exposure to robotics research, engineering practice, and academic collaboration.
View certificateIntern, Data Science
Worked in the Data Science track on Urban Guard, an applied computer vision and AI project by ZEMT Innovations in collaboration with NUST's Educational Robotics Lab. Gained practical experience in data pipelines, analysis, and applied AI within a real engineering project context.
View certificateIntern, Robotics
Successfully completed a two-month internship on robotics at Al-Khwarizmi Robotics Lab, Quetta, under the leadership and direction of Engr. Hameed Khan (Founder & Director).
View certificateIntern, Volunteer Management Department
Completed a 6-week hybrid internship under the Volunteer Management Department as part of the Alkhidmat Summer Internship Program 2025, receiving the program Achievement Award.
View certificateBeyond university labs and codebases, I actively participate in initiatives that bring robotics, computer vision, AI, and aerial systems into schools and communities—fostering curiosity and practical skills in the next generation.
Core Outreach Pillars
2nd Namal Agribusiness School 2026
In collaboration with Nisar Aziz AgriTech Center, Eureka Robotics Centre & British Council
Demonstrated applied drone, computer vision, and AI systems at the 2nd Namal Agribusiness School to explore how intelligent technologies can address productivity, water-stress assessment, and precision agriculture in rural communities.
Event Photography:
3 PhotosPIE Project · Educational Robotics Lab (NUST SEECS)
Supported by Eureka Robotics Centre, Cardiff Metropolitan University & British Council
Conducted an interactive robotics workshop for students at Gulhouse International School System under the PIE Project, introducing young learners to robotics, humanoid platforms, and creative problem-solving.
Event Photography:
2 PhotosPIE Project · Educational Robotics Lab (SEECS NUST)
Supported by STEMWomenPK, Eureka Robotics Centre, Cardiff Met & British Council
Conducted an intensive 5-day hands-on robotics training workshop for students of APS Humayun Road, Rawalpindi. Guided students through humanoid robot programming, sensor integration, autonomous flight control, and team robotics challenges under the PIE Project.
Event Photography:
2 PhotosFormal technical certifications and specialized workshop credentials verifying competencies across artificial intelligence, neural architectures, and biomedical engineering systems.