RTX Sensor Annotators#

The isaacsim.sensors.rtx extension uses Omniverse Replicator to provide Annotators for RTX Lidar and Radar data collection. Annotators can be attached to render products, attached to OmniSensor prims (eg. OmniLidar or OmniRadar); for example, when run in Script Editor, the following snippet creates an OmniLidar prim at /lidar, a render product for the sensor, and attaches an IsaacExtractRTXSensorPointCloudNoAccumulator Annotator to the render product.

import omni
import omni.replicator.core as rep
from pxr import Gf

# Create an OmniLidar prim at prim path /lidar
_, sensor = omni.kit.commands.execute(
    "IsaacSensorCreateRtxLidar",
    translation=Gf.Vec3d(0.0, 0.0, 0.0),
    orientation=Gf.Quatd(1.0, 0.0, 0.0, 0.0),
    path="/lidar",
)

# Create a render product for the sensor.
render_product = rep.create.render_product(sensor.GetPath(), resolution=(1024, 1024))

# Create an annotator
annotator = rep.AnnotatorRegistry.get_annotator("IsaacExtractRTXSensorPointCloudNoAccumulator")

# Attach the render product after the annotator is initialized.
annotator.attach([render_product.path])

Annotators#

Each isaacsim.sensors.rtx Annotator is associated with a specific isaacsim.sensors.rtx OmniGraph node; refer to that documentation for more information on the annotator’s outputs. This section details assumptions and limitations for each annotator.

Note

In Isaac Sim 5.0, several existing isaacsim.sensors.rtx Annotators were removed in favor of simpler Annotators that can handle output from the new OmniLidar or OmniRadar prims, in addition to the deprecated Camera-prim-based workflows. See Deprecated Annotators for details.

Warning

If the Lidar rotation rate is slower than the frame rate, data from Annotators for accumulated Lidar scans will contain returns from multiple frames. If the Lidar prim moves between frames, or objects move in the scene, the buffer may contain returns from before the Lidar or object(s) moved, causing points to appear as though they are “dragging” behind objects when viewed with the DebugDrawPointCloud or DebugDrawPointCloudBuffer writers.

Warning

isaacsim.sensors.rtx Annotators rely on the GenericModelOutput AOV from the OmniLidar prim being provided on device. If --/app/sensors/nv/lidar/outputBufferOnGPU or --/app/sensors/nv/radar/outputBufferOnGPU is set to false, the Annotators will not function correctly.

IsaacCreateRTXLidarScanBuffer#

The IsaacCreateRTXLidarScanBuffer node accumulates frames of data from an OmniLidar prim into a single scan, and provides the accumulated scan data as outputs. By default the node outputs a 3D Cartesian point cloud, and can optionally the following data if the user sets the corresponding input flag on the node to true.

Note

The node outputs data as pointers to buffers, and the table below specifies the data type of each buffer.

Output

Type

Description

Notes

data

float3

3D Cartesian point cloud.

Always provided.

azimuth

float

Azimuth of each return, in degrees.

Provided if outputAzimuth is set to true.

elevation

float

Elevation of each return, in degrees.

Provided if outputElevation is set to true.

distance

float

Range of each return, in world units (by default, meters).

Provided if outputDistance is set to true.

intensity

float

Intensity of each return, normalized as described here.

Provided if outputIntensity is set to true.

timestamp

uint64

Timestamp of each return, in nanoseconds since the start of the simulation.

Provided if outputTimestamp is set to true.

emitterId

uint

ID of the emitter that emitted the return.

Provided if outputEmitterId is set to true, and omni:sensor:Core:auxOutputType is set to BASIC on the OmniLidar prim.

materialId

uint

ID of the material of the object that generated the return.

Provided if outputMaterialId is set to true, and omni:sensor:Core:auxOutputType is set to EXTRA on the OmniLidar prim.

objectId

uint

ID of the object that generated the return.

Provided if outputObjectId is set to true, and omni:sensor:Core:auxOutputType is set to EXTRA on the OmniLidar prim.

normal

float3

Normal to the surface of the object that generated the return.

Provided if outputNormal is set to true, omni:sensor:Core:auxOutputType is set to FULL on the OmniLidar prim, and --/app/sensors/nv/lidar/publishNormals=true is set.

velocity

float

Velocity of the object that generated the return.

Provided if outputVelocity is set to true, and omni:sensor:Core:auxOutputType is set to FULL on the OmniLidar prim.

Note

Enabling nonzero normal output by setting --/app/sensors/nv/lidar/publishNormals=true will increase VRAM usage and may negatively impact performance.

Warning

In Isaac Sim 5.0, the normal and velocity outputs are not populated correctly by the IsaacCreateRTXLidarScanBuffer node. Users should instead use the GenericModelOutput AOV (see below). This issue will be fixed in a future release.

IsaacComputeRTXLidarFlatScan#

IsaacComputeRTXLidarFlatScan extracts depth and azimuth data from an accumulated 2D RTX Lidar scan.

Note

The IsaacComputeRTXLidarFlatScan Annotator does not support RTX Radar.

Warning

If the annotator is attached to a 3D Lidar (defined as having emitters at nonzero elevation angles), the annotator will not return any data.

Warning

Even if --/app/sensors/nv/lidar/outputBufferOnGPU=true is set, IsaacComputeRTXLidarFlatScanSimulationTime output data will be on host memory.

IsaacExtractRTXSensorPointCloudNoAccumulator#

The IsaacExtractRTXSensorPointCloud node extracts the GenericModelOutput buffer’s point cloud data into a Cartesian vector data buffer for each frame.

The IsaacExtractRTXSensorPointCloudNoAccumulator Annotator provides the node outputs via an Annotator.

Reading Data from the GenericModelOutput Buffer#

Note

Isaac Sim 4.5 included the OgnIsaacReadRTXLidarData node, which provided an example of reading data from the GenericModelOutput buffer in Python. This node has been removed as of Isaac Sim 5.0 and replaced by the utility module and functions described below.

The isaacsim.sensors.rtx.generic_model_output Python module provides APIs for inspecting the GenericModelOutput buffer, generated by the GenericModelOutput annotator.

For more information on the GenericModelOutput buffer, see the API documentation..

For an example of reading data from the GenericModelOutput buffer from Isaac Sim, checkout the standalone example located at standalone_examples/api/isaacsim.sensors.rtx/inspect_lidar_metadata.py.

Warning

The objId field returns a 128-bit stable unsigned integer corresponding to the prim path of the object that generated the return. This field is provided as a numpy array of dtype np.uint8, and is only populated if --/rtx-transient/stableIds/enabled=true is set. There are two known issues in Isaac Sim 5.0 regarding objId output. First, the map from objId to prim path is not exposed to end-users, and the objId field is populated with 1/16th of the necessary values. Second, the objId field is not populated for OmniLidar prims. Both issues will be fixed in a future release.

Deprecated Annotators#

Several Annotators have been removed and/or replaced by the Annotators described above, as of Isaac Sim 5.0.

New Annotator outputs are not guaranteed to be the same as the outputs of the deprecated Annotators, gmoBufferPointer the table below describes affected Annotators and how to replace them.

Deprecated Isaac Sim 4.5 Annotator

Replacement

Details

IsaacComputeRTXLidarFlatScanSimulationTime

IsaacComputeRTXLidarFlatScan

The new annotator outputs the same data as the old annotator.
To get an associated timestamp, use the IsaacReadSimulationTime annotator.

IsaacComputeRTXLidarFlatScanSystemTime

IsaacComputeRTXLidarFlatScan

The new annotator outputs the same data as the old annotator.
To get an associated timestamp, use the IsaacReadSystemTime annotator.

RtxSensorCpuIsaacComputeRTXLidarPointCloud

IsaacExtractRTXSensorPointCloudNoAccumulator

The new annotator outputs the same data as the old annotator, excluding azimuth, elevation, and range.
These values can be computed from the Cartesian data buffer. The new annotator also automatically supports
CPU or GPU output based on the --/app/sensors/nv/lidar/outputBufferOnGPU and --/app/sensors/nv/radar/outputBufferOnGPU
settings, rather than Annotator type.

RtxSensorGpuIsaacComputeRTXLidarPointCloud

IsaacExtractRTXSensorPointCloudNoAccumulator

See above.

RtxSensorCpuIsaacComputeRTXRadarPointCloud

IsaacExtractRTXSensorPointCloudNoAccumulator

See above.

RtxSensorGpuIsaacComputeRTXRadarPointCloud

IsaacExtractRTXSensorPointCloudNoAccumulator

See above.

IsaacReadRTXLidarData

isaacsim.sensors.rtx.read_gmo_data utility.

See Reading Data from the GenericModelOutput Buffer for details.