Train

Train models on your robots’ own data.

Start with data capture from any camera, sensor, or arm, and record demonstrations as sequences with one command. Train detectors and classifiers in the app; train a robot policy with your own Python script on Viam’s cloud GPUs; or pull a training script or pre-trained model from the Module Registry. However you train, Viam is the harness between the model and the hardware: each model deploys to one machine or the whole fleet, versioned like any other config, and runs within the limits you set.
Try it free
Try it free
CAPTURE

Record episodes

Every camera stream and every joint reading, captured on one clock at the rate you declare, synced and uploaded without a logging rig of your own. Teleoperate the arm, mark the episode, and the dataset builds itself.

  • Config-driven capture from any camera, sensor, or arm, synced to the cloud continuously or on demand

  • Declared capture: which resources, which methods, what rate, one clock

  • Teleop with a leader arm or a controller; episodes saved as sequences

  • Export LeRobot-compatible datasets

Train

Train a model in Viam’s cloud

Every machine captures the images and readings you declare, syncs them to one dataset, and the app labels, trains, and evaluates a detector or classifier on them. The trained model deploys back to the machines as a config line. When the fleet sees something new, the next version trains on that too.

  • Config-driven capture from any camera or sensor, synced per fleet

  • Label and train detectors and classifiers in the app; bring your own training script

  • Deploy the model to one machine or the fleet through the ML model service; versioned, revertible

  • Retrain on production data as it accumulates

Deploy

Deploy and run on your robot

Fine-tune a vision-language-action model on your sequences, or pull a checkpoint straight from Hugging Face, and the policy comes back to the machine as one more declaration: a service in config, driving the arm through the same API, under the same limits as everything else. Async chunked inference keeps the arm smooth while the model thinks.

  • Run a learned policy as a Viam service, with any checkpoint: yours, the Registry's, or Hugging Face's

  • Inference on the robot's own compute (a Jetson is enough)

  • Delta and joint-limit clamps enforced below the policy

Train a policy, then watch it run.

Record demonstrations on an SO-101, fine-tune a VLA in Viam’s cloud, and deploy it to the arm. Training is free, and there’s no code to write.
Start the SO-101 course
Start the SO-101 course

Build robots like you build software.

Start free
Start free
‍