Engineering Notebook, Volume 04. Muhammad Salaar Butt, Honors in Computing Science.

Engineering notebook

Muhammad Salaar Butt / portfolio

I train modelsand buildthe softwarethat shipsthem.

Robotics research, privacy-sensitive AI products, and the software that carries models into the physical world.

Honours Computing Science
University of Alberta · 2027
Case file / 01

FR3 robot learning

From human demonstration to guarded execution on a physical robot.

Domain
Robotics / learned behavior
Period
2026—present

Context

Learned policies do not arrive at hardware ready to run. Demonstrations, observations, controller timing, calibration, and safety all have to agree; a failure at any seam changes what the policy can actually do.

Contribution

Built the path from Apple Vision Pro teleoperation and synchronized episode capture through VLA policy adaptation to interpolated, safety-constrained execution on a Franka Research 3. The work spans data collection, training inputs, and deployment rather than one isolated model step.

Evidence

The complete path runs on physical hardware. The controller’s 1 kHz requirement is treated as an operating constraint—not a result—and bridged from slower policy inference with smoothing and runtime checks.

Learn more about this project

Experience

Research Assistant
Robotics ML · University of Alberta

Physical robot deployment, teleoperation, synchronized data collection, VLA adaptation, controller integration, calibration, and runtime safety.

Mobile Software Engineer
Applied AI · Jarillo Consulting (client project)

Offline-first field workflows, speech and LLM pipelines, structured validation, encrypted storage, authenticated APIs, and audit logging.

Systems archive

CHIP-8 emulatorC · SDL2 · execution · timers · input · audioMultilingual RAGVertex AI · Gemini · FAISS · Streamlit