Skip to main content
Welcome to the Hello GRID tutorial! This guide walks you through setting up and running your first GRID session using the GRID Enterprise platform.
By default, all commands target the local machine. For remote machines, use the @<machine_name> syntax.

​
What You’ll Learn

In this tutorial, you will:
  • Initialize the GRID Enterprise platform
  • Start a simulation session using AirGen
  • Access the simulation, notebook, and visualization interfaces
  • Capture and visualize sensor data
  • Run an AI model on captured images
  • Clean up your environment

​
Setup and Initialization

1

Ensure Prerequisites

Before starting, ensure GRID Enterprise is installed on your machine. If not, follow the installation guide.You should also have your license.json and resource_config.json files configured in ~/.grid/.
2

Launch the GRID CLI

Open your terminal and start the GRID CLI:
grid

 .d8888b.  8888888b.  8888888 8888888b.
d88P  Y88b 888   Y88b   888   888  "Y88b
888    888 888    888   888   888    888
888        888   d88P   888   888    888
888  88888 8888888P"    888   888    888
888    888 888 T88b     888   888    888
Y88b  d88P 888  T88b    888   888  .d88P
 "Y8888P88 888   T88b 8888888 8888888P"

General Robot Intelligence Development Platform - Enterprise version
General Robotics Technology, Inc.

Type help for list of commands.

GRID #
3

Initialize the Containers

Authenticate with the registry and start the containers:
login @local
init airgen @local

GRID # login @local
Logging in to General Robotics – GRID registry...
Login successful!

GRID # init airgen @local
Initializing assets …
Assets initialized.
Starting airgen on local …
Checking container statuses...
grid_core: ✓
grid_server: ✓
grid_sim_airgen: ✓
Containers are active.
First-time initialization downloads container images and may take several minutes.

​
Starting Your First Session

1

Start a Session

Launch a session with a sample configuration:
session start hello_grid

GRID # session start hello_grid
Using sample config at /home/grid/.grid/sample_session_airgen.json
Starting session hello_grid on node local …
Status: Initializing session...
Status: Downloading content...
Status: Session has been started successfully
Session started successfully.
Since no config file was specified, GRID generates a sample configuration automatically.
2

Open the Simulation

View the simulation in your browser:
open sim @local
Simulation running in browser
3

Open the Notebook Interface

Access Jupyter notebooks:
open nb @local
Notebook interface
4

Open Visualization

Launch the Rerun visualization interface:
open viz @local
Rerun visualization
5

Check Active Sessions

Verify your session is running:
session list

+------------+-------+------------------------------+
| Session    | Node  | Last active                  |
+============+=======+==============================+
| hello_grid | local | 2024-09-10T23:42:51.674976+00|
+------------+-------+------------------------------+

​
Data Capture and Visualization

With your session running, create a new notebook from the Jupyter interface and try capturing sensor data.

​
Capture an Image

from grid.robot.wheeled.airgen_car import AirGenCar
robot = AirGenCar()

import airgen
image = robot.getImage("front_center", "rgb")

# Visualize in Rerun
from grid.utils.logger import log
log("rgb_image", image)
Captured image visualized in Rerun

​
Run an AI Model

Use a pre-trained object detection model on your captured image: 
from grid.model.perception.detection.owlv2 import OWLv2

det_model = OWLv2(use_local=True)
det_model.run(image.data, "ball")
Object detection results
GRID includes dozens of pre-trained models for detection, segmentation, depth estimation, VLMs, and more. See the AI Models documentation.

​
Cleanup

1

Stop the Session

session stop hello_grid

Stopping session hello_grid on node local …
Session stopped.
2

Terminate the Containers

When finished for the day, shut down the containers:
terminate @local

Checking container statuses...
grid_core: ✗
grid_server: ✗
grid_sim_airgen: ✗
Containers stopped successfully.

​
Congratulations!

You’ve completed the Hello GRID tutorial! You successfully:
  • Initialized GRID containers
  • Started a simulation session
  • Accessed simulation, notebook, and visualization interfaces
  • Captured sensor data and ran an AI model
  • Cleaned up your environment

​
Next Steps

GRID CLI Reference

Learn all available commands including update assets and update samples.

VS Code Integration

Develop directly inside the GRID container with VS Code.

AirGen Simulator

Explore AirGen’s features for aerial and ground robots.

AI Models

Discover all available AI models for perception and control.