The Blanket
Technology
Robots are powerful, but they are still hard to deploy reliably. Traditional automation takes months because every step has to be programmed by specialists. AI-driven approaches, while faster to deploy, require training on large datasets. Both break when the world changes.
We are building the reasoning layer that lets robots adapt, streamlining robot deployment.
The core of our platform is built around Active Inference, a bio-inspired decision-making framework. Our artificial brain for robots generalises efficiently by reasoning at the right level of abstraction, so that a shared understanding enables robots to adapt to changing conditions, apply reusable skills, recover autonomously from failures, and actively flag what they don't know.
Robots that think before they act.
auto·motion
We are building auto·motion, our platform for robot automation that requires zero programming, and is operational within hours.
Talking to teams in the field, two major cost drivers stand out: 1) frequent reprogramming, resulting in downtime and often requiring external specialists, and 2) the need to engineer environments around robot limitations. Instead of adapting environments to robots, auto·motion makes robots adapt to real-world environments.
Interact with the interface
Operator demonstrates the task, or uploads design file.
Plan & Execute
auto·motion breaks the task down in stages and starts acting.
Query when needed
When uncertain, the system queries an operator for targeted input
human-in-the-loopLearn & Adapt
The system adapts online, self-calibrates, recovers from errors, and improves with use.
Contact
If you have dealt with the cost and complexity of automation, whether you've deployed it and struggled, or never been able to justify the investment, we'd love to understand your experience.
If you're an investor focused on robotics infrastructure or frontier AI, we'd love to talk.
Reach out at contact@theblanket.ai.