# Robotics: when models meet the physical world

A pack of 8 talks from the AI Engineer YouTube channel, in the order to watch them. 2h 23m of video.
Page: https://aietalks.com/packs/robotics

A robot policy can understand the scene and still fail because its training data is thin, its controller is late or its motors cannot keep up. Physical Intelligence's PI0.5 and NVIDIA's GR00T N1 establish how vision, language, robot state and fast action fit together. Waymo's EMMA planner tests end-to-end control where a plausible mistake is dangerous, before K-Scale moves the same concerns into an open humanoid stack. CloudChef brings the system into a hot, variable workplace where thermal sensing and human recovery matter as much as the model. A control-systems case traces bad motion through stale sensor data and logging pauses. Voice comes only after that machinery is visible. Scout's stage fall makes the limit plain: a clean language interface can choose a policy, but it cannot repeal physics.

## This pack is for you if

- Your multimodal model understands a scene, but you still need to turn that understanding into a safe physical action.
- Your robot works in simulation and behaves strangely once timing, sensors and people enter the loop.
- You are deciding where a real deployment needs a general policy, task-specific perception or human recovery.

## The talks, in order

### 1. Robotics: why now?

Quan Vuong & Jost Tobias Springenberg, Physical Intelligence | 18:07 | AI Engineer World's Fair 2025
Video: https://www.youtube.com/watch?v=cGLa8DsOYdk
Summary: https://aietalks.com/talks/robotics-why-now.md

Why first: Vuong and Springenberg define the problem behind the rest of the pack. Language and vision are not enough when a model must produce fast physical actions. They also put the less glamorous constraint first: before architecture or deployment, someone has to build the robot-data operation.

### 2. What Is a Humanoid Foundation Model? An Introduction to GR00T N1

Annika Brundyn & Aastha Jhunjhunwala, NVIDIA | 17:47 | AI Engineer World's Fair 2025
Video: https://www.youtube.com/watch?v=mWKYvT9Lc50
Summary: https://aietalks.com/talks/what-is-a-humanoid-foundation-model-an-introduction-to-gr00t-n1.md

Why second: Vuong and Springenberg explain why a language model needs an action layer. Brundyn and Jhunjhunwala open that layer up: a slow planner, a fast controller and a decoder for each robot body. Their data pyramid also answers the scarcity problem the first talk introduces.

### 3. Waymo's EMMA: Teaching Cars to Think

Jyh Jing Hwang, Waymo | 17:28 | AI Engineer World's Fair 2025
Video: https://www.youtube.com/watch?v=iS9YFW28XyM
Summary: https://aietalks.com/talks/waymos-emma-teaching-cars-to-think.md

Why here: Brundyn and Jhunjhunwala describe a general architecture. Hwang puts the same idea into autonomous driving, where a plausible action is not enough. EMMA makes intermediate decisions visible, then uses generated weather and lighting changes to test the planner under conditions that are hard to collect safely.

### 4. Your Personal Open-Source Humanoid Robot for $8,999

Jingxiang Mo, K-Scale Labs | 19:26 | AI Engineer World's Fair 2025
Video: https://www.youtube.com/watch?v=BS92RdBvI90
Summary: https://aietalks.com/talks/your-personal-open-source-humanoid-robot-for-8-999.md

Why here: Hwang shows why simulation matters when a bad decision is dangerous. Mo makes simulation the developer's entry point. KS Sim and the physical robot share an interface, so moving a controller onto the hardware means changing its target rather than rewriting it.

### 5. Robots as Professional Chefs

Nikhil Abraham, CloudChef | 18:58 | AI Engineer World's Fair 2025
Video: https://www.youtube.com/watch?v=MBWGiWJDlSo
Summary: https://aietalks.com/talks/robots-as-professional-chefs.md

Why here: Mo gives developers a general robot stack. Abraham shows what changes when one enters a particular workplace. Cooking needs thermal sensing, recipe state and a person ready for the odd case. General hardware becomes useful through evidence about this job, not through generality alone.

### 6. Challenges in High Performance Robotics Systems

Rishabh Garg, Tesla Optimus | 12:43 | AI Engineer World's Fair 2025
Video: https://www.youtube.com/watch?v=bCGbuyv8PMk
Summary: https://aietalks.com/talks/challenges-in-high-performance-robotics-systems.md

Why here: Abraham separates good perception from slower physical execution. Garg explains how the same gap can make a sound policy look broken. Stale sensor data, queued commands, logging pauses and kernel scheduling all turn correct computation into bad motion.

### 7. Reachy Mini: the $300 open source robot you can actually hack

Andres Marafioti, Hugging Face | 21:16 | AI Engineer Europe 2026
Video: https://www.youtube.com/watch?v=0jeZfjJMfmo
Summary: https://aietalks.com/talks/reachy-mini-the-300-open-source-robot-you-can-actually-hack.md

Why here: Garg shows that a few milliseconds can change physical behavior. Marafioti applies that lesson to the person facing the robot. Reachy Mini combines repairable hardware, partial transcription and faster speech generation so the interaction begins while a remote model would still be waiting.

### 8. Tell the Robot What You Want

Sandhya Subramani, AWS | 17:22 | AI Engineer World's Fair 2026
Video: https://www.youtube.com/watch?v=S6aSoQ6_u5A
Summary: https://aietalks.com/talks/tell-the-robot-what-you-want.md

Why last: Marafioti makes conversation with a robot faster. Subramani shows what conversation can and cannot control. Her agent chooses an existing policy, while the policy decides the movement. Scout falling over on stage is the useful ending: a clean language interface does not remove the physical system underneath it.