Inference Deployment

Inference deployment loads a trained model and connects the model output to the real robot control workflow.

First-time setup

Before running model inference for the first time, install the inference plugin. In the Model Runtime Information area on the right side of the Select Model page, click Check and follow the on-screen instructions to install or update the plugin. After the plugin status shows Installed, load the model and continue to hardware setup.

Select Model

The model selection step loads the local model files required for inference:

• Select the model type and load a local checkpoint directory.

  

Checkpoint directory requirements

Select the checkpoint root directory at the level shown in the figure. Do not select its parent directory or an individual file. The selected directory must directly contain inference_config.yaml, the model weight files, and stats.json. Selecting the wrong directory level may cause the model to fail to load.

Hardware Setup

Hardware setup connects model inputs with robot outputs:

• Scan and assign camera roles to make sure the inference view source is correct.
• Configure robot serial ports, robotic arm roles, and the primary control arm.
• After confirming the hardware connection, enter the inference control page.

Inference Control

Inference control runs the model online and shows the robot execution status:

• Start or stop online inference tasks.
• View runtime status, frame rate, action queue, and prediction results in real time.
• View robot feedback data such as joint angles and gripper status.
• Use emergency stop to interrupt robot motion immediately if an abnormal situation occurs.