Smash Notes

Back to Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics, with Jason Ma.

What Limits Hour-long Robot Jobs?

Jason Ma says the bottleneck for doing an hour-long full job on any task is data and hardware. A laundry demo takes one hour to finish the whole loop, and the longest duration a robot can do a full job is already in the hour range.

For some tasks, such as setting up a space, a robot might need more than a parallel jaw gripper, something dexterous like a human hand. Training a model on a hand is then bottlenecked by hardware stability. The best dexterous hands today are still not durable enough and overheat pretty quickly. A hardware limit slows everything, because knowing whether progress is real on any task eventually has to happen on the hardware. Without eval that is spontaneous and fast, research progress is limited, including how to collect the right data for an extremely complex job like setting up a studio. Most data today is vision-based: video streams and some encoding of hand motion where the robot joints are.

Transcript

Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics ·

Latent Space: The AI Engineer Podcast

More from this episode

  1. What Is a World-action Model?Jason Ma says a world-action model predicts the future video of the world and also turns that prediction into actions a robot can execute.
  2. Why Does Dyna 2 Use a Diffusion Transformer?Jason Ma says the Dyna 2 world action model is a diffusion transformer.
  3. How Does Dyna Robotics Generate Synthetic Robot Data?Jason Ma says his team generates synthetic robot data with frontier models that build synthetic environments and with a world action model that makes its own…
  4. Why Must a Robot Model Run on the Device?Jason Ma says a robot model has to run on the device because the robot must infer fast enough to act. A language model or a coding agent can wait.
  5. Why Does Dyna Robotics Size Robots Like People?Jason Ma says the robot's proportions are measured against real people because the team pre-trains on human data and treats the match as the transfer path…
  6. What Is a Semi-humanoid Robot?Jason Ma describes the robot as a semi-humanoid: the upper body is like a humanoid, and the lower body is wheels.
  7. Why Does the Dyna Robot Lean Its Torso?Jason Ma gave the Dyna robot a torso that can lean because people use the waist and back for ordinary tasks, and a body that only travels up and down cannot…
  8. Why Did Din Tai Fung Put Robots in Many Restaurants?Jason Ma says Din Tai Fung put Dyna robots in many United States restaurants because the chain decided the robots create enough value to roll out across…
  9. How Can a Robot Work Alone for an Hour?Jason Ma says a robot can work alone for an hour when a hierarchical agent harness sits around the world-action model and strings short skills into one…
  10. Why Did People Think AI Would Never Solve Go?Jason Ma thinks people, before AlphaGo, treated Go as one of the games that AI would never solve, because the search space is larger than the total number of…

People

More answers like this

The other side

More with Jason Ma

More with Shawn Wang

Related episodes

Plays from this note through the rest of the episode.

Weekly highlights

One letter a week.

The notes worth hearing, with the minute they were said.