To build generalist robots, the most effective approach is pre-training foundation models on internet-scale video datasets, not just simulation or tele-operated data. This vast, diverse data provides a deep, implicit understanding of physics and object interaction that is impossible to replicate in controlled environments, enabling true generalization.

Figure is observing that data from one robot performing a task (e.g., moving packages in a warehouse) improves the performance of other robots on completely different tasks (e.g., folding laundry at home). This powerful transfer learning, enabled by deep learning, is a key driver for scaling general-purpose capabilities.

For physical AI systems like robots, data quality hinges on diversity, not just quantity. A robot trained to make a bed in one specific lighting condition may fail completely if the lighting changes or the bed is moved. This brittleness highlights a key challenge: training data must capture a wide variety of contexts and edge cases to enable real-world generalization.

A flashy robot demo typically uses a highly controlled, pristine environment tailored to one task. True progress lies in a robot performing a mundane task reliably in any novel situation—a feat of generalization that is much harder to showcase visually and less exciting to a layperson.

Robotic intelligence has two components. "Reasoning," which involves creating a plan, is quickly being solved by AI. The other, harder part is "movement"—the robot's physical dexterity to execute that plan reliably in a complex environment without tripping or failing.

Simply collecting more data from a deployed robot isn't enough to create a powerful learning flywheel. If the tasks are repetitive (e.g., a million car welds), the model won't generalize. Data must be diverse, acting more like an 'education program' than a fungible commodity to drive real capability growth.

Robots have become so capable at low-level physical tasks that the primary bottleneck has shifted to "mid-level reasoning"—interpreting a scene and choosing the correct next action. This means improvement can come from high-level language-based coaching, not just more physical demonstration data, which is a major breakthrough.

Self-driving cars, a 20-year journey so far, are relatively simple robots: metal boxes on 2D surfaces designed *not* to touch things. General-purpose robots operate in complex 3D environments with the primary goal of *touching* and manipulating objects. This highlights the immense, often underestimated, physical and algorithmic challenges facing robotics.

Moving a robot from a lab demo to a commercial system reveals that AI is just one component. Success depends heavily on traditional engineering for sensor calibration, arm accuracy, system speed, and reliability. These unglamorous details are critical for performance in the real world.