Users Manual

(continued from previous page)
"load
_
carriers": [
{
"id": "string",
"inner
_
dimensions": {
"x": "float64",
"y": "float64",
"z": "float64"
},
"outer
_
dimensions": {
"x": "float64",
"y": "float64",
"z": "float64"
},
"pose": {
"orientation": {
"w": "float64",
"x": "float64",
"y": "float64",
"z": "float64"
},
"position": {
"x": "float64",
"y": "float64",
"z": "float64"
}
},
"pose
_
frame": "string",
"rim
_
thickness": {
"x": "float64",
"y": "float64"
}
}
],
"return
_
code": {
"message": "string",
"value": "int16"
},
"timestamp": {
"nsec": "int32",
"sec": "int32"
}
}
Required arguments:
pose
_
frame: defines the output pose frame for the detected rectangles.
item
_
models: defines a list of rectangles with minimum and maximum size, with the minimum
dimensions strictly smaller than the maximum dimensions. At least one item
_
model is always
required. The dimensions should be given as precise as possible to avoid misdetections.
robot
_
pose: only if working in pose
_
frame="external" and the rc_visard is robot-mounted.
Optional arguments:
region
_
of
_
interest
_
id: delimits the volume of space where to search for the load carrier
or selects a volume which contains items to be grasped if no load
_
carrier
_
id is set. The
processing time for load carrier detection and grasp computation increases with the size of the
selected region of interest.
load
_
carrier
_
id: limits grasp computation to the content of the detected load carrier.
load
_
carrier
_
compartment: selects a compartment within the detected load carrier.
7.4. ItemPick and BoxPick 98