On the job
It learns while it works.
A brain can acquire useful skills through initial experience, then keep those skills while it acts and learns from further outcomes.
Pragma Research / Robotics
Give your robot a brain that learns from experience.
Cadence is a novel real-time AI modeled after animal and human brains. It learns from live experience, on the robot, while the robot works.
We are looking for robot makers and integrators with one concrete problem: a robot that has to adapt or recover when conditions change.
The difference
A frozen model cannot learn from the field.
A typical deployed transformer keeps its learned weights fixed during use. Cadence explores a continuing equilibrium brain that can learn from actual outcomes.
A robot in the field meets wear, new loads and new places. Bootstrap useful body knowledge, retain it during operation, and compare predicted motion with actual motion. Cadence's target is local repair of failed expectations while preserving familiar skills. Routine cost, recovery and retention need separate measurements on the robot.
Why a learning brain
Built like a brain. Made for a body.
Six things a robot gains from a brain that learns from experience.
Changed conditions
It adapts when things change.
A worn motor, a heavier load or a different floor changes what the robot senses. The design goal is to repair the affected knowledge while retaining useful skills.
On the machine
It learns on the robot itself.
Connections can change from local neural activity, without a backward computation graph. Whether learning fits a robot's compute budget is measured on that body.
Memory
It remembers.
A short-term memory carries the last few moments and a long-term memory keeps what mattered. Something experienced once can shape the next decision.
Settled answers
It checks whether its answer settled.
Cadence checks the whole neural graph before issuing an action and refuses if it cannot settle. A settled answer can still be wrong about the world; actual outcomes test it.
Inspection
You can see what it is doing.
The activity of every part of the brain can be read while it runs. The brain can also try out a response in imagination before the body commits to it.
Shown in simulation today in Rover Lab, Patch World and the Atari Arcade. Cadence is experimental research software, and a physical robot evaluation is the next test.
Rover Lab / Working simulation
Change the body. Watch it adapt.
Weaken a simulated rover's wheel without telling it. The brain works out what changed from its own motion.
The rover learns how its wheel commands turn into motion from driving alone. When a wheel weakens, the live brain relearns its body within seconds and keeps reaching its targets. A frozen copy of the same brain falls behind.
Rover Lab is a simulation that runs in your browser. A physical robot evaluation is the next test.
A paid evaluation
Test one problem worth solving.
A motor that responds differently, a changed payload or a recurring recovery task makes a useful starting point. Choose a failure your team can reproduce and a result it can measure.
01
Define the task
Name a technical sponsor and agree what the robot senses, what experience it gets and what counts as success.
02
Connect the brain
Connect Cadence to your simulator or robot. Agree which decisions it makes and time the full path from sensing to command.
03
Measure useful work
Compare with your existing stack. Measure completed tasks, operator interventions, time to recover, retained skills and compute cost.
04
Choose deployment
Review the results together. Useful results can lead to production integration and a recurring license.
Work with Pragma Research
Bring a body and a problem worth learning.
Tell us the robot, the recurring problem and how you measure success. We can demonstrate the software and scope a paid evaluation with your technical team.
Cadence is built from small self-reading patches. Each one holds its own state, listens to its neighbours, keeps records of experience and corrects itself through feedback. Together they settle on one answer, and experience changes how they are connected.