Are brain waves the next unlock for physical AI?
Companies building robot brains are turning to new sources of data, including brain waves, to train their models. Encord, a startup, is manufacturing data for robotics companies, including egocentric video and brain wave data.
Intelligence analysis by Llama
Encord is building a business around manufacturing data for robotics companies, including brain wave data, to train their models. This is a new approach to solving the robotics data bottleneck.
Imagine you're playing a game where you have to pick up blocks and put them in a box. A robot is trying to do the same thing, but it's not very good at it. To help the robot learn, we're using special headsets that measure the robot's brain waves. This is like a special kind of training data that will help the robot get better at picking up blocks.
Analysis
The Robotics Data Bottleneck
The frontier of physical AI is a Jenga game in a warehouse in San Leandro, California. That warehouse is occupied by Encord, a company that builds data tooling used to train AI models. Andrew Ceja is a pilot—the company's term for its robotic trainers—and he's carefully pulling wooden blocks from a tottering tower while wearing a headset with a camera that tracks what he sees. That alone is fairly common for collecting robot training data, but this headset includes sensors that measure his brain waves as he carefully disassembles the block tower.
Encord is one of a small but growing number of startups betting that the next real constraint on humanoid and warehouse robotics won't be model architecture but instead the sheer scarcity of real-world physical training data. Rather than just helping robotics companies manage the data they have, Encord is building a business around manufacturing the data they don't.
The Brain Wave Headset
The brain wave headset Ceja is wearing was built by Zander Labs, a German neuroscience startup that's betting measuring brain activity—to deduce mental states like error, intent, and surprise—can create a more useful data set to train models. Encord's work with Zander is currently a trial run; Encord says the goal is to build an initial brain wave-tagged data set, run it through customer robotics models, and evaluate whether it actually improves performance before deciding whether to scale it up.
The Robotics Data Bottleneck
Lucas Gehrke, a Zander neuroscientist supervising the work, says that the amount of brain activity used at any point during a given task offers clues for model builders trying to figure out when they need to deploy their highest-effort models. This is the
Key points
- Encord is manufacturing data for robotics companies, including brain wave data, to train their models.
- Brain wave data can provide clues for model builders to determine when to deploy their highest-effort models.
- Generating physical training data is a costly and time-consuming process.
- The quality of the data may not be sufficient to achieve significant improvements in robot performance.
If brain wave data can be successfully used to train robots, it could unlock new possibilities for physical AI, enabling robots to learn and adapt more effectively. This could lead to breakthroughs in areas such as warehouse automation and household tasks.
However, generating physical training data is a costly and time-consuming process, which may limit the scalability of this approach. Additionally, the quality of the data may not be sufficient to achieve significant improvements in robot performance.
