In my project, I’m using UR5 to get the good tools that the camera classifies with AI.
Running out of ideas on how to combine UR5 and AI.
I need advice where to start.
Is the only way to do this is to use ROS?
Are there any ways to do this without ROS as I’m not familiar with that?
my question is if the camera classifies the tools are good, how can I send a signal to the robot to understand that it will move the tools to the correct output positions??
Can this be done simply by connecting the camera as an input to the robot’s microcontroller and getting an output as a signal for the robot to move?
use actions and trigger an action for example to find elements in a scene usin computer vision tasks
Hey issaiass,
your answer is related to KI, but my question is if the camera classifies the tools are good, how can I send a signal to the robot to understand that it will move the tools to the correct output positions??
Ah ok.
- Probably if you detect the element (let’s talk about it to do not confuse with the robot tool) and wait for 500 ms to validate that is not a false positive for example. and finally sent a signal (an action client signal to the server) to start the next process…
- Next use the TF of the detected element and the TF of the Robot tool to approach in two steps, 1 near and the other to grasp.
- Finally you must know the TF of the position of the robot to leave the element in the position that you want.
This topic was automatically closed 10 days after the last reply. New replies are no longer allowed.