feat(GPSR): object properties (count/weight/size) #151
Conversation
jws-1
changed the title
There was a problem hiding this comment.
Great job and first contribution! I also saw a working demo of this.
Sorry that this has taken me so long to review, I kept forgetting about it 😆.. I've left some comments, mostly relating to moving your work into lasr_skills and removing comments/print statements etc, but feel free to disagree! But after that, we can get this merged straight in!
skills/config/demo.yaml
Outdated
There was a problem hiding this comment.
I think this would be better off in skills/src/lasr_skills/, and would mean we can delete the files that I've marked :)
tasks/gpsr/find_object/setup.py
Outdated
There was a problem hiding this comment.
I think we can remove this now too, since I saw everything working on the robot!
tasks/gpsr/find_object/package.xml
Outdated
| # userdata.detections_3d = [(detection, point),(detection, point),(detection, point)] | ||
| # the detection includes the size of the bounding box and the center point of the box |
There was a problem hiding this comment.
| # userdata.detections_3d = [(detection, point),(detection, point),(detection, point)] | |
| # the detection includes the size of the bounding box and the center point of the box |
| # got the area dic of the detected objects | ||
| # rank the size of each object |
There was a problem hiding this comment.
| # got the area dic of the detected objects | |
| # rank the size of each object |
| def execute(self, userdata): | ||
| # got the area dic of the detected objects | ||
| # rank the size of each object | ||
| print("we're doing size") |
There was a problem hiding this comment.
| print("we're doing size") |
| area_dict = self.property_size_calculation(detections_types, userdata.detections_3d) | ||
| sorted_size = sorted(area_dict.items(), key=lambda item: item[1], reverse = True) | ||
| userdata.sorted_size = sorted_size | ||
| print(sorted_size) |
There was a problem hiding this comment.
| print(sorted_size) |
| smach.StateMachine.__init__( | ||
| self, | ||
| outcomes=["succeeded", "failed"], | ||
| output_keys=["detections_3d"], |
There was a problem hiding this comment.
I think we should also have the various object properties in the output_keys, so that we can utilise them later on
Co-authored-by: Jared Swift <[email protected]>
add the object detection script to the gpsr task