Simulation and real-world data collection are not contradictory; they operate in a data flywheel where physics-based simulation provides initial structure and consistency for robot training, then real-world data accumulation shifts toward more learning-based modeling over time.
Yunu Guo explains that simulation and real-world data collection are complementary, not contradictory. The process starts with more physics-based simulation for consistency, then as real-world data accumulates through client collaboration, the modeling transitions toward more learning-based approaches, combining the best of both geometry/consistency and data/compute. ✦ AI generated
Yunu Guo · a16z Podcast · 2026-07-28 · original ↗
starts at this moment · 18:19
“I've heard other researchers say simulation will always eventually deviate from the physical world and real world data collection is absolutely critical. So maybe talk a little bit about the viability of this approach where simulation is a cornerstone.”
They don't contradict with each other. Simulation is essentially trying to predict how the environment is going to change when you apply the actions—this is a model of the world. It doesn't necessarily have to be pure physics. It can be a combination of both physics and learning. We are collecting real world data. We will be using those real world data. It just at different stages of this data flywheel. At the very beginning we have stronger emphasis on physics to make sure we have the right consistency and right structure for us to train the robot policies. But as we accumulate more and more data both through data collection and through the collaboration with our clients, we'll have the data that will be moving towards more learning-based modeling of the environments. This kind of transition and data flow is really an enabling factor of getting the best of both physics and geometry and consistency as well as all the power and magic from data and compute.
verbatim transcript · starts at 18:19
18:19will always eventually deviate from the physical world and real world data collection is absolutely critical. And so maybe talk a little bit about like the viability of this approach where simulation is a cornerstone as opposed to some other approach. >> So they don't contradict with each other. So if you think about the simulation, simulation is essentially trying to predict how the environment is going going to change when you apply the
18:45actions and this is essentially a model of the worlds. It doesn't necessarily have to be pure physics. It can be a combination between both physics and also learning. We are collecting real world data. We will be using those real world data. It just at different stages of this like a data fly. Maybe at the very beginning we have stronger emphasize on we have more physics to making sure we have the right
19:06consistency and right structure for us to learn the uh the the worlds for us to train the robot policies. But as we accumulate more and more data both through data collection and also through the collaboration with our clients we'll have the data that will be moving towards more towards more learning based like modeling of the environments. So this kind of transition and also this kind of data flow is really an enabling
19:29factors of both getting the best of both physics and the and and geometry and consistency as well as all the power and magics from the data and compute. >> I want to add to this and be slightly philosophical here is there isn't a a binary choice between simulation or no simulation. All this come um in together um to to make robotics work. Think about human intelligence. We do a lot of
19:59simulation in our head. You know why? There's a very important role simulation plays that real world data doesn't play which is counterfactual reasoning is that you play out events that c hasn't happened or cannot happen or you don't have enough data to make it happen in real world. And while you play it out, you learn how to act in it. Humans do this all the time. We probably don't,