This week I did a lot of work tuning the filtering process for the ellipse detection. I was able to get a 90% detection rate with no duplicate ellipses on any cups. This took less time than I expected so I was able to start modifying the things to build on the Jetson TK1 that I recently picked up from the school. This upcoming week I plan to continue testing the real time capturing with ellipse detection. Also I plan to start testing things with on the TK1 instead of on my laptop.
Logan Kojiro Weekly Status Report (3/13/21)
This week pending changes in hardware design I did further research into the Stanford ball shooting robots, the new parts we need for the DC motors, and got a lot of framing work done in software. I wrote the serial input function to the Arduino and placeholder functions that will probably need some tuning of values for angle and velocity adjustment. I also ran through my derivation of the kinematics equations again that I did a while back to double check they were right before anything got put in software. For hardware testing, I dug up an old Arduino and motors I had from the fun with robots StuCo to get a preliminary test setup. Plus, it would be nice if these motors worked for us so we don’t have to order anything extra. JP also pushed a bunch of code earlier in the week that I’ve been looking through to make sure I understand what he’s doing as well. I need to dig out my Dremel tomorrow but I plan on doing some testing with using PWM straight on these motors to see what kind of velocity we can get out of them. If we can eliminate the need for an additional external power supply and only have a single one powering the Jetson, powering the Arduino and the motors that would be ideal to reduce the final footprint of the electronics in our project. With a light week of other coursework next week after emerging from midterm season, I’m exited that that hardware is starting to come together and am looking forward to seeing the
Juan Pablo Status Report 3/5/21
Spent some time learning about the Jetson nano and the interactions with the Arduino. I have also been looking into how to best implement the UI and have made potential models that should be easy to interact with. The UI will ideally help the user correct any issues that occur and so my goal is to make it as accessible and useful as possible. I’ve also been thinking about a possible method of lining up shots that would not only be based on absolute coordinates, but also on relative distance to another cup that has already been made. Hopefully this could come into play if we encounter any accuracy problems in the future.