Author: nmesacuc

The demo went well, but we ran into some issues with fixing the camera angle, so I have retrained the model on less epochs and started working on some testing, both with the current model and looking for possible alternate datasets, to try and improve the vision algorithms improvement in more difficult scenarios. Lohith also re-flashed the Jetson and now we can load a version of the model on it, so I will continue testing and working with the ML model and then I will move to Jetson tests throughout the week.

I successfully trained the model. However, the data fidelity was not what we wanted, so we are exploring various data augmentation options, and possible alternative datasets, to get the model working the way we intend it to.  This issue has caused the expected output of the ML Model to be different than what we anticipated, so for the Interim demo’s, we will not be integrating with the Processing Algorithm. I am also currently working with Lohith to get a version of the model on the Jetson so we can start working on using video feed instead of just images.

The model has almost finished checkpoint training. Due to various issues we encountered, we had to restart training, and have trained our model 7/8ths of the way (roughly as of writing this) and will finish it during this week. I have also been working together with Joe to start integrating the expected output of the ML Model with the Processing Algorithm. Even though the model is not done training, the scaffolding needed for it to interact with the Processing Algorithm is something I was able to focus on and finish up this week.

I have began checkpoint training of the ML Model, and have trained our model 1/4th of the way. I have a rough plan of how I will work with TensorRT for this model, and have downloaded TensorRT onto the Jetson Nano, and will focus on optimizing the model with it after I have finished checkpointing. We also focused on the ethics component of our project this week, and have outlined some additions to align our project a bit better with the ethical expectations of engineers. I have also been working together with Joe and managed to help get the basis of the processing algorithm written. I specifically assisted with the database querying and game state formatting, as well as simplifying the logic.

As a team, we finished writing the Design Document. We kept working individually on the components we had been working on before, but we also organized to get a simpler Camera to use instead of the Oak-D Pro. As mentioned, this camera has far more features than we need, so we just got a simple USB camera off Amazon, and will put the order in after Spring Break. Development is proceeding smoothly for the most part, which we are happy about. We do not have any significant schedule changes or block diagram changes currently. The most significant risks would be an issue with model training, which could delay integration progress, so Nico will be taking the week after break to get the model up and running so we don’t have to worry about that possibility.

This week was focused on the finishing the debugging and finishing reading and understanding the algorithms described in the papers.

For the website, I was able to fix most of the bugs, but one bug that has remained illusive is with having multiple people connect to the website at the same time, so I’m still trying to debug that. The web app and the DB are connected properly though, so I was happy to fix that bug.

The formalization the paper described was a bit complicated, so I spent some time speaking with Nico understanding it, and I think I now understand this fully enough to start implementing it. However, we ironed all these issues and understandings out right before Spring Break, so we will finish it after the break.

For the past two weeks, I have been working on an improved design for the angling of the camera in the Blackjack Buddy mechanism. I have started to create a CAD model for the product, and hope to finish it by the time the next status report is written. I have also continued to work on the algorithm for betting strategies with Joe. The idea is that we will have a module that acts as a function for this algorithm, and the goal is to make this module as portable as possible so that an integration into the entire design will be as seamless as possible.