Curiosity, Passion, and Learning to Learn

My Journey in Robotics · From DIY Drone Hobbyist to Apple Robotics Lead

Curiosity, Passion,
and Learning to Learn

How building projects — drones, robots, RC trucks — can compound into a career.

The Foundation

Logic meets the physical world

Lego Mindstorms was my first real introduction to robotics. The realisation that logic could control physical things changed everything.

The Foundation

Taking things apart

I've been fixing electronics since I was a kid — opening things up just to see how they worked. That instinct was the seed of everything.

The Skills Behind the Projects

Every project I built was preparing me for the next.

The skills didn't come from a curriculum.
They compounded, one project at a time.

Lego Mindstorms

→

Electronics / Tinkering

→

Soldering

→

3D Printing

→

Custom Drones

The Expected Path

Meanwhile, I followed the expected path.

🎓

B.Sc. Electrical Engineering

The degree everyone said to get.

💍

Got Married

The milestone everyone expected next.

💼

Started Working in Industry

A real job at BMW. Stable. Predictable.

Nothing wrong with that.
But the curiosity didn't stop.
The side projects were just getting started.

BMW

The dream job.

The Work

Developing mild-hybrid alternators — now in most cars on the road. Test driving early prototypes like the BMW i8.

Not Actually Fulfilling

But the basement called
every weekend.

✅

On paper

Great company. Exciting technology. Good salary.
The job everyone wanted.

❌

In reality

Managing suppliers instead of doing the engineering. Status meetings. Not building.

Every weekend

Back in the basement. Drones. Electronics. Building things with my own hands.

When your hobby is more fulfilling than your job.
That's a signal worth listening to.

Starting Over

I quit.

BMW felt like the void. So I left — driven by instinct, not comfort. Managing suppliers wasn't why I studied engineering.

Decision 1

Left BMW

Desiring hands-on work over project management.

Then I started over.

↓

Decision 2

MS in EE Communications

Theoretical. Not applied. Still not quite right.

Started a Master's in Electrical Engineering, focused on communications theory. But it was not a great fit, and the next decision only took a few months.

↓

Decision 3

Changed Topic & Adviser

Computer Vision. Building. Following the passion.

Finding Computer Vision

Giving machines eyes to see

Computer vision — the idea that machines could see and interpret the world — instantly clicked. This was the direction worth chasing.

The hobby drones and the academic research were pointing at the exact same problem — deploying algorithms onto physical hardware.

This is where hobby and career started to become one.

The PhD Breakthrough

The tracks were merging.
Now I could run.

Deploying computer vision algorithms onto drones — research that only worked because of a decade of tinkering experience that preceded it. Personal projects and career were converging.

The PhD Breakthrough

From obsession to publication

We created UAV123 — the first large-scale dataset for tracking objects from drones. That was the moment I officially became a Robotics Researcher.

CV Algorithms + Hobby Drones → Research

A Career Built in the Margins

Two tracks running in parallel

THE CAREER TRACK

Bachelors (EE) → BMW (Project Mgmt) → MS/PhD [Computer Vision + Robotics]

THE HOBBY TRACK

Lego Mindstorms → Fixing Electronics → Custom Drones → Computer Vision + Robotics

The hobby track ran quietly alongside the career track — and eventually took over.

The Early Drone Days

The hobby that built the foundation

Long before drones were everywhere, I was building custom ones from cheap off-the-shelf parts — not for a grade or a job. Pure obsession.

Intel Internship

Fun with a budget

At Intel I proposed building a 1:5 scale RC truck retrofitted for autonomous driving research — industry money funding a hobby.

ICRA 2018

End-to-end Driving via Conditional Imitation Learning

1,669 citations

CoRL 2018

Driving Policy Transfer via Modularity and Abstraction

324 citations

OpenBot

Scaling the hobby

Once full-time at Intel, I started OpenBot — world-class autonomous robotics for under $50. It started as fun. It's now used in education worldwide.

OpenBot

From DIY to product

Injection-molded chassis, integrated electronics —
a polished platform ready for classrooms and research labs.

OpenBot · World-Class Robotics for $50

The brain + the body

The Brain

Your smartphone — powerful processor, full sensor suite, communications — in your pocket.

The Body

Inexpensive, customisable
3D-printed hardware.
Commodity parts under $50.

The Software

Block-based playground or raw Python/Jupyter notebooks. Autonomous navigation, obstacle avoidance, person following.

OpenBot in Action

OpenBot

A fun project took on a life of its own
and reached education worldwide.

The Takeaway

Each project unlocked the next.

Skills compounded.

The career became the canvas. Once the tracks merged, the resources of a career amplified what used to be a hobby. Getting paid to build the things you'd build anyway — that's the dream.

Drones

PhD research

→ UAV123 — first large-scale drone tracking dataset

RC Truck

Hobby project, industry budget

→ Highly cited paper · led to full-time offer at Intel

OpenBot

Personal passion, global scale

→ Used in education worldwide · $50 per robot

None of it was planned. All of it started as a fun project.

Avoiding the Prestige Trap

From builder to team lead and back

I led Intel's Embodied AI Research lab. Built strategy and managed teams. But I missed the technical work.

So I made a deliberate step: move to Apple as an Individual Contributor. Get my hands dirty again.

Team Lead at Intel

Strategy & teams. The void returns.

↓

IC at Apple

Hands-on. Cool technical problems.

↓

Organic Growth

2 people → small group → all robotics research

Leadership grew out of doing the work.

Lessons

Looking back and forward

Lessons from more than a decade of building —
and the shift that's rewriting the rules.

The Evolution of Engineering Value

From "How" to "What & Why"

Definition of Expert

Knowing the syntax of a tool

↓

Understanding the
whole system, end-to-end

Primary Value

Tool Mastery — How to build it

↓

Problem Framing
What & Why

The Risk

Obsolete when the tool changes

↓

Falling behind
if you stop learning

Tool-specific skills are outdated in years, not decades.

Future-Proof Engineering

The meta-skills
algorithms can't replicate

Learning Agility

The ability to learn, unlearn, and relearn quickly as the
landscape shifts.

Pattern Recognition

Making connections across domains — e.g., how a drone algorithm solves a problem in a warehouse or a car.

Critical Thinking

Assessing if an AI's output is actually right — or just sounds right.

Human Connection

Nurturing strong personal and professional networks for stability and collaboration.

AI is a force multiplier — be the force. Delegate execution, not understanding.

AI as Tool, Not Crutch

The AI interaction spectrum

Do It Yourself

Roll up your sleeves.
No AI.

✓ Learning, edge cases, high stakes

⚠ Autopiloting through the hard parts

Debate

Stress-test your view
with AI.

✓ After forming your own view

⚠ Before you've thought at all

Delegate

Hand off the work
that won't sharpen you.

✓ Mechanical, repetitive work

⚠ Work that sharpens you

Don't default to delegate.
AI as tutor extends you. AI as crutch replaces you.

Stop Consuming. Start Building.

You don't prepare for the opportunity.
Projects are the preparation.

Build

Build what excites you.
Ignore prestige.

Stretch

Aim beyond your current skill.
That's where growth lives.

Compound

Pick projects that
unlock the next.

Curiosity today. Opportunity tomorrow.
Build now. Be ready always.

The Builder's Resource Checklist

Tools worth your time

Paul Graham

Great essays, for example "How to Do Great Work" and "How to Do What You Love".

OpenBot

Deploy a neural network on physical hardware for $50.

Claude Code

Automate tedious syntax so you can focus on architecture and the "Why".

NotebookLM

Synthesise and learn complex new domains quickly. Scaffold, don't shortcut.

Final Thought

"The way to do great work
is to love what you do."

— Steve Jobs, Stanford Commencement, 2005

Get Ready. Start Now.

Get ready.

Follow your curiosity and passion. When the big opportunity comes, you won't have time to prepare — you need to be ready, and you are, because you've been building for years. Don't wait for a perfect plan.

Start now.

One More Thing

This presentation
was a project.

Before

PowerPoint. Keynote. Google Slides.

This time

Static HTML. Pure code. No slides app.

Built with

Claude Code — AI as collaborator, not crutch.

View online

Scan to open this presentation.

Stay curious. Find interesting projects. Never stop learning.