Introduction to Physical AI: Getting Started with Intelligent Robots

Physical AI is quickly becoming one of the most exciting areas in AI, but it can be difficult to know where to begin. This talk is an introduction for anyone who wants to understand what Physical AI is, how these systems work, and how to start building them.

Rather than being a theory-heavy session, this will be a hands-on introduction to Physical AI with live demonstrations. The session will feature LeRobot, Reachy Mini, and OpenDuck Mini, along with the hardware used to build and train them, allowing attendees to experience these systems in action rather than through videos or slides.

I'll share my experience of building and training these robots from scratch, explaining the complete Physical AI workflow from hardware and sensors to data collection, model training, and deployment. Along the way, I'll simplify the core concepts behind Physical AI using real-world examples and practical demonstrations.

My goal is to make Physical AI approachable for beginners, makers, and AI enthusiasts. By the end of the session, attendees will have a clear understanding of the Physical AI ecosystem, the open-source tools available today, and how they can start building and experimenting with Physical AI on their own.

Live Demonstration Robots

Talk Breakdown

1. Why Physical AI? (3–4 mins)

1. What is Physical AI?
2. Why is everyone talking about it?
3. How it differs from Generative AI and traditional robotics.
4. Why this is the next frontier of AI.

2. The Physical AI Ecosystem (5 mins)

1. The anatomy of a modern Physical AI system.
2. Hardware, sensors, actuators, cameras, and compute.
3. The role of open-source robotics.
4. Introduction to LeRobot, Reachy Mini, and OpenDuck Mini.

3. Building a Physical AI Robot (8–10 mins)

1. How I built these robots from scratch.
2. Hardware assembly and software setup.
3. Collecting demonstrations using teleoperation.
4. Training robot policies.
5. Running inference and deploying models on the robot.
6. Lessons learned and common pitfalls.

4. Live Robot Demonstrations (8–10 mins)

1. Live demonstrations using LeRobot, Reachy Mini, and OpenDuck Mini.
2. Walk through the hardware.
3. Show teleoperation, perception, and task execution.
4. Explain what is happening behind the scenes as the robots perform tasks.

5. Getting Started with Physical AI (3–4 mins)

1. Open-source tools and learning resources.
2. Recommended hardware for beginners.
3. A practical roadmap for building your first Physical AI project.
4. Q&A (time permitting).

1. Understand what Physical AI is and why it is emerging as the next frontier of AI.
2. Learn the end-to-end workflow of a Physical AI system, from hardware and sensors to data collection, model training, and deployment.
3. Experience live demonstrations of open-source robots, including LeRobot, Reachy Mini, and OpenDuck Mini, along with the actual hardware used to build them.
4. Explore how open-source robotics frameworks are lowering the barrier to building intelligent robots.
5. Discover the tools, resources, and learning roadmap needed to start building your own Physical AI projects.
6. Leave with the confidence to build your first Physical AI application, whether you're an AI engineer, student, maker, or robotics enthusiast.