This week I worked more on the trajectory prediction, with the ping pong balls, I finished the filtering of unrealistic trajectories and am now considering working on getting the trajectory that traveled the most distance. I don’t think that this component will be strictly necessary since filtering out unrealistic trajectories already works quite well. I also need to think about how to test this component of the system as well.
I thought a lot about cup detection this week because it feels harder to do than ball detection. I am going to try mapping the 3d point cloud into a 3d “pixelated” space and then go layer by layer searching for circles. Alternatively, if that doesn’t work I could use a computer vision model to detect the cups based on the rgb vision rather than LIDAR vision, but I’m trying to get LIDAR vision to work properly.
I’m almost done with the first iteration of the launching subsystem, I only need to obtain a 2 liter soda bottle to use as a pressure chamber and hook that up to our current pressure system.
Next week I think I’m just going to focus on trying to get as much as I can done with the computer vision subsystem and I might ask one of my groupmates to look for/buy the pressure container (a 2 liter soda bottle).
This puts me around where I expect to be on the schedule.
