# Execute AI model inference with `qrb_ros_nn_inference`
[qrb_ros_nn_inference](https://github.com/qualcomm-qrb-ros/qrb_ros_nn_inference) is a ROS2 package for performing neural network model, providing AI-based perception for robotics applications.
- It provides the following functionalities:
- - Model inference API which supports three model formats:
- `.tflite`
- `.so`
- `.bin`
- Model inference acceleration based on Qualcomm platforms
## Pipeline flow
Here comes the pipeline for `qrb_ros_nn_inference`:
**Figure : `qrb_ros_nn_inference` pipeline**
## ROS topics used in the `qrb_ros_nn_inference` pipeline
| ROS topic | Message type | Published/Subscribed by | Description |
| --- | --- | --- | --- |
| `/qrb_inference_input_tensor` | `qrb_ros_tensor_list_msgs::msg::TensorList` | Subscribed by `qrb_ros_nn_inference` | Subscribes to the input tensor for model inference. |
| `/qrb_inference_output_tensor` | `qrb_ros_tensor_list_msgs::msg::TensorList` | Published by `qrb_ros_nn_inference` | Publishes the output tensor of model. |
## ROS node parameters used in the `qrb_ros_nn_inference` pipeline
| Node parameter | Type | Default value | Description |
| --- | --- | --- | --- |
| `backend_option` | `string` | `""` | Hardware acceleration option for model inference. For valid values, see [qrb_ros_nn_inference documentation](https://github.com/qualcomm-qrb-ros/qrb_ros_nn_inference/blob/main/qrb_inference_manager/Documentation.md#2.1). |
| `model_path` | `string` | `""` | Indicates the path of the model file. |
## Prerequisites
- You have **Set up the device** according to [Set up the environment for running sample applications](https://docs.qualcomm.com/doc/80-70023-265/topic/quick_start.html#setup-demo-qs).
- You have downloaded the model from [QC AI hub](https://aihub.qualcomm.com).
- You have prepared the preprocess node and postprocess node according to the [qrb_ros_nn_inference example](https://github.com/qualcomm-qrb-ros/qrb_ros_nn_inference/tree/main/test).
## Run out-of-the-box `qrb_ros_nn_inference`
**Steps**
1. Start one terminal, and run the following commands to set up QIR SDK and ROS2 environment on the device.
Value range of `ROS_DOMAIN_ID`: [0, 232]
ssh root@[ip-addr]
(ssh) mount -o remount,rw /usr
(ssh) source /usr/share/qirp-setup.sh
(ssh) export ROS_DOMAIN_ID=xx
Copy to clipboard
2. Launch three nodes: preprocess node, `qrb_ros_nn_inference` node and postprocess node.
(ssh) ros2 launch model_inference.launch.py
Copy to clipboard
## Build and run `qrb_ros_nn_inference`
**Steps**
1. Build `qrb_ros_nn_inference` provided by the QIR SDK on the host.
cd
source setup.sh
cd qirp-samples/platform/qrb_ros_nn_inference
colcon build --merge-install --cmake-args ${CMAKE_ARGS}
Copy to clipboard
2. Push `qrb_ros_nn_inference` to the device.
Note
Ensure that the QIR SDK is installed on the device.
cd qirp-samples/platform/qrb_ros_nn_inference/install
tar czvf qrb_ros_nn_inference.tar.gz include lib share
scp qrb_ros_nn_inference.tar.gz root@[ip-addr]:/opt/
ssh root@[ip-addr]
(ssh) mount -o remount,rw /usr
(ssh) tar --no-overwrite-dir --no-same-owner -zxf /opt/qrb_ros_nn_inference.tar.gz -C /usr/
Copy to clipboard
3. Start one terminal, and run the following commands to set up QIR SDK and ROS2 environment on the device.
Value range of `ROS_DOMAIN_ID`: [0, 232]
ssh root@[ip-addr]
(ssh) mount -o remount,rw /usr
(ssh) source /usr/share/qirp-setup.sh
(ssh) export ROS_DOMAIN_ID=xx
Copy to clipboard
4. Launch three nodes: preprocess node, `qrb_ros_nn_inference` node and postprocess node.
(ssh) ros2 launch model_inference.launch.py
Copy to clipboard
## Limitation
For the latest limitations, see [qrb_ros_nn_inference](https://github.com/qualcomm-qrb-ros/qrb_ros_nn_inference) on GitHub.
Last Published: Dec 29, 2025
[Previous Topic
Evaluating performance of ROS2 components with](https://docs.qualcomm.com/bundle/publicresource/80-70023-265/topics/qrb_ros_benchmark.md) [Next Topic
Develop applications using the QIR SDK](https://docs.qualcomm.com/bundle/publicresource/80-70023-265/topics/develop_application_with_qirp_sdk.md)