icp_registration
Align a data point cloud to a reference model cloud using Iterative Closest Point (ICP). Computes transformation matrix and final RMS error for accurate registration.
Instructions
Register a 'data' cloud onto a 'model' cloud using the Iterative Closest Point (ICP) algorithm. Returns the transformation matrix and final RMS error.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"model_path": "<model_path>",
"data_path": "<data_path>",
"output_path": "<output_path>"
},
"name": "icp_registration"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model_path | Yes | Absolute path to the fixed reference cloud. | |
| data_path | Yes | Absolute path to the cloud to be aligned. | |
| output_path | Yes | Absolute path for the aligned cloud. | |
| overlap | No | Expected overlap percentage between clouds (10–100). Default 100. | |
| iterations | No | Maximum ICP iterations. Default 20. | |
| random_sampling_limit | No | Number of points used during ICP (speeds up large clouds). Default 50000. |