Deploying a Model
Run an existing model on your Anvil robots
Get the repository
Requirements
Python 3.12+
Connect inference machine
Connect the inference machine to your local network, so that it can communicate with the Anvil Devbox running your robots. Due to the bandwith requirements of observation data and the latency requirements of real-time control, relying on a wireless connection isn't practical, and it's recommended to connect the machines via Ethernet.
Using a router and network switch to connect these can make it easier to manage IP addresses, but is not strictly necessary.
On the Anvil Devbox
When running distributed inference, we switch our middleware system to CycloneDDS. In your .env.config (inside anvil-loader on your Devbox), set:
and indicate the IP of your inference machine with this field:
You also need to assign a ROS_DOMAIN_ID so that traffic can flow across your network. Keep in mind you'll need to use this same ID on the inference machine.
To be safe, you should make sure Quest teleoperation is disabled:
Finally, set the ARMS_CONTROL_CONFIG_FILE to the config included for inference:
On the inference machine
To facilitate CycloneDDS moving data at high speeds across the machines, you need to raise the max network buffer sizes:
Copy the .env.example file from the repo root to a .env file:
Set your ROS_DOMAIN_ID to the same value that you set on the Anvil Devbox:
Set MODEL_PATH to point to the directory location of the model you want to use:
Run inference
Make sure the robots are up and ready to go (see Starting Robot Operation), then run inference via our container with one simple command:
Last updated