> This page is for version Release 2.3.
> For other versions, use one of these documentation indexes:
> - Release 3.0 (default): https://docs.nvidia.com/isaaclab/3.0/llms.txt
> - Release 2.3: https://docs.nvidia.com/isaaclab/2.3/llms.txt
> - Release 2.2: https://docs.nvidia.com/isaaclab/2.2/llms.txt
> - Release 2.1: https://docs.nvidia.com/isaaclab/2.1/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/isaaclab/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/isaaclab/_mcp/server.

# Creating an empty scene

This tutorial shows how to launch and control Isaac Sim simulator from a standalone Python script. It sets up an
empty scene in Isaac Lab and introduces the two main classes used in the framework, `app.AppLauncher` and
`sim.SimulationContext`.

Please review [Isaac Sim Workflows](https://docs.isaacsim.omniverse.nvidia.com/latest/introduction/workflows.html) prior to beginning this tutorial to get
an initial understanding of working with the simulator.

## The Code

The tutorial corresponds to the `create_empty.py` script in the `scripts/tutorials/00_sim` directory.

```python
# Copyright (c) 2022-2025, The Isaac Lab Project Developers (https://github.com/isaac-sim/IsaacLab/blob/main/CONTRIBUTORS.md).
# All rights reserved.
#
# SPDX-License-Identifier: BSD-3-Clause

"""This script demonstrates how to create a simple stage in Isaac Sim.

~~~bash
# Usage
./isaaclab.sh -p scripts/tutorials/00_sim/create_empty.py
~~~

"""

"""Launch Isaac Sim Simulator first."""

import argparse

from isaaclab.app import AppLauncher

# create argparser
parser = argparse.ArgumentParser(description="Tutorial on creating an empty stage.")
# append AppLauncher cli args
AppLauncher.add_app_launcher_args(parser)
# parse the arguments
args_cli = parser.parse_args()
# launch omniverse app
app_launcher = AppLauncher(args_cli)
simulation_app = app_launcher.app

"""Rest everything follows."""

from isaaclab.sim import SimulationCfg, SimulationContext

def main():
    """Main function."""

    # Initialize the simulation context
    sim_cfg = SimulationCfg(dt=0.01)
    sim = SimulationContext(sim_cfg)
    # Set main camera
    sim.set_camera_view([2.5, 2.5, 2.5], [0.0, 0.0, 0.0])

    # Play the simulator
    sim.reset()
    # Now we are ready!
    print("[INFO]: Setup complete...")

    # Simulate physics
    while simulation_app.is_running():
        # perform step
        sim.step()

if __name__ == "__main__":
    # run the main function
    main()
    # close sim app
    simulation_app.close()
```

## The Code Explained

### Launching the simulator

The first step when working with standalone Python scripts is to launch the simulation application.
This is necessary to do at the start since various dependency modules of Isaac Sim are only available
after the simulation app is running.

This can be done by importing the `app.AppLauncher` class. This utility class wraps around
`isaacsim.SimulationApp` class to launch the simulator. It provides mechanisms to
configure the simulator using command-line arguments and environment variables.

For this tutorial, we mainly look at adding the command-line options to a user-defined
`argparse.ArgumentParser`. This is done by passing the parser instance to the
`app.AppLauncher.add_app_launcher_args` method, which appends different parameters
to it. These include launching the app headless, configuring different Livestream options,
and enabling off-screen rendering.

```python
import argparse

from isaaclab.app import AppLauncher

# create argparser
parser = argparse.ArgumentParser(description="Tutorial on creating an empty stage.")
# append AppLauncher cli args
AppLauncher.add_app_launcher_args(parser)
# parse the arguments
args_cli = parser.parse_args()
# launch omniverse app
app_launcher = AppLauncher(args_cli)
simulation_app = app_launcher.app
```

### Importing python modules

Once the simulation app is running, it is possible to import different Python modules from
Isaac Sim and other libraries. Here we import the following module:

* `isaaclab.sim`: A sub-package in Isaac Lab for all the core simulator-related operations.

```python
from isaaclab.sim import SimulationCfg, SimulationContext
```

### Configuring the simulation context

When launching the simulator from a standalone script, the user has complete control over playing,
pausing and stepping the simulator. All these operations are handled through the **simulation
context**. It takes care of various timeline events and also configures the [physics scene](https://docs.omniverse.nvidia.com/prod_extensions/prod_extensions/ext_physics.html#physics-scene) for
simulation.

In Isaac Lab, the `sim.SimulationContext` class inherits from Isaac Sim's
`isaacsim.core.api.simulation_context.SimulationContext` to allow configuring the simulation
through Python's `dataclass` object and handle certain intricacies of the simulation stepping.

For this tutorial, we set the physics and rendering time step to 0.01 seconds. This is done
by passing these quantities to the `sim.SimulationCfg`, which is then used to create an
instance of the simulation context.

```python
# Initialize the simulation context
sim_cfg = SimulationCfg(dt=0.01)
sim = SimulationContext(sim_cfg)
# Set main camera
sim.set_camera_view([2.5, 2.5, 2.5], [0.0, 0.0, 0.0])
```

Following the creation of the simulation context, we have only configured the physics acting on the
simulated scene. This includes the device to use for simulation, the gravity vector, and other advanced
solver parameters. There are now two main steps remaining to run the simulation:

1. Designing the simulation scene: Adding sensors, robots and other simulated objects
2. Running the simulation loop: Stepping the simulator, and setting and getting data from the simulator

In this tutorial, we look at Step 2 first for an empty scene to focus on the simulation control first.
In the following tutorials, we will look into Step 1 and working with simulation handles for interacting
with the simulator.

### Running the simulation

The first thing, after setting up the simulation scene, is to call the `sim.SimulationContext.reset`
method. This method plays the timeline and initializes the physics handles in the simulator. It must always
be called the first time before stepping the simulator. Otherwise, the simulation handles are not initialized
properly.

> **Note**
>
> only plays the timeline and does not initializes the physics handles.

After playing the simulation timeline, we set up a simple simulation loop where the simulator is stepped repeatedly
while the simulation app is running. The method `sim.SimulationContext.step` takes in as argument `render`,
which dictates whether the step includes updating the rendering-related events or not. By default, this flag is
set to True.

```python
# Play the simulator
sim.reset()
# Now we are ready!
print("[INFO]: Setup complete...")

# Simulate physics
while simulation_app.is_running():
    # perform step
    sim.step()
```

### Exiting the simulation

Lastly, the simulation application is stopped and its window is closed by calling
`isaacsim.SimulationApp.close` method.

```python
# close sim app
simulation_app.close()
```

## The Code Execution

Now that we have gone through the code, let's run the script and see the result:

```bash
./isaaclab.sh -p scripts/tutorials/00_sim/create_empty.py
```

The simulation should be playing, and the stage should be rendering. To stop the simulation,
you can either close the window, or press `Ctrl+C` in the terminal.

![result of create\_empty.py](/isaaclab/_fern-img/733c41a099f8dfb826375da7eb577434474e8ca4dd28d9ed33511d1540f53740.webp)

Passing `--help` to the above script will show the different command-line arguments added
earlier by the `app.AppLauncher` class. To run the script headless, you can execute the
following:

```bash
./isaaclab.sh -p scripts/tutorials/00_sim/create_empty.py --headless
```

Now that we have a basic understanding of how to run a simulation, let's move on to the
following tutorial where we will learn how to add assets to the stage.