This week we have been working on some final fixes for all of our individual components. Currently, most components are looking good and we are conversing to make sure that there is an alignment between our components for the purpose of integration. We have also been discussing on how we want the interim demonstration to go and how we will design it.
Joe’s Status Report 29th March, 2025
This week I have managed to get most of the web application to be running. I’ve added some pictures of some of the web pages below. Right now the processing algorithm is still struggling a little bit so I’m continuing to work on that, hopefully getting it done by the interim demonstration. I have yet to complete integration with the ML model but it seems like this part should not be too difficult.
Team Status Report for 22nd March 2025
For this week, we have all been working individually on our components. Joe has managed to get basic web functionality up. Nicholas has finished checkpointing the ML model and has been working on integrating the ML model with a dummy processing algorithm (since the processing algorithm is in the works) for testing purposes. Lohith has been working on completing the camera unit so that by the end of next week we are ready for pipeline testing. We are planning to start integrating the ML model into the Jetson next week.
Joe’s Status Report for 22nd March 2025
This week I managed to get the web server to function with the desired functionalities so my hope is that by next week I will be able to begin hosting it on the Jetson and try to connect to it from a web device. Currently the processing algorithm is still in the works so I’m also hoping to finish that by next week. Hopefully I will also be able to get integrate the processing algorithm into the web server by then since integrating those should be fairly straightforward. After this week, I’m hoping to start overall pipeline testing.
Team Status Report for 15th March 2025
The team met together this week to discuss the comments on the report and how we could improve the design of our system based on the comments. We realized there were some ambiguities and holes in our design and articulation of our ideas and noted these for updating in the final report.
Currently work is going as planned and no major changes have been made to the schedule or the design of the system, albeit some additional low-level considerations during implementation. The most significant risk right now is whether or not we can tune the ML model sufficiently to reach the accuracy requirements, but currently based on literature this does not seem likely.
We have currently made some plans as well to work on part 3 and part 4 of the ethics assignment. Right now we have all individually started reading through it and will meet tomorrow to figure things out.
Joe’s Status Report 15th March, 2025
I spent quite a bit of time this week working on the ethics assignment and because I was back from Spring break, I spent quite a bit of time catching up with work I had left.
However, I have more or less been able to figure out the model being suggested by the paper and I’ve started implementing it correctly. I have been working together with Nico and managed to get the basic portions of the processing algorithm working, where we query a database for a certain formatted game state and modify it using some algorithm. We managed to make it quite simple and straightforward which is what we wanted.
We have been cross-collaborating quite a bit more this week due to hour heavy workloads. Nico and I also figured out how we might want to use TensorRT for our purposes after which he downloaded it onto the Jetson. I expect to continue working with him on this in a small capacity.
Joe’s Status Report for Feb 22, 2025
There were two main objectives for this week. First, I’ve been debugging the website and making sure that all the functionalities that I outlined in the design presentation were properly working. I simply placed some dummy information in the database and made sure that the pipeline between the web app and the DB was working fully. There were some bugs here and there so I’m still working on making this as airtight as possible.
The other thing I was hoping to work on was more or less formalizing the mathematics our processing algorithm and start implementing it. However, the paper had more material than I was initially anticipating and as such I’ve not managed to complete this, albeit crunching a substantial portion of this. I hope to finish this next week before Spring break and start implementing the basic components of our processing algorithm over the break and after.
Joe’s Status Report for February 15th, 2025
This week, I have more or less completed finalizing all the functionalities I will have in my application. I intend the application to provide the following information: 1) running count 2) true count 3) optimal action 4) deviations. The user will also be able to interact with the application by providing the history of bets they have placed and the action + outcome that just occurred. As of now I have set up the web server on my own IP just to test the functionalities of the application. I have set up the database for the app and the basic features I mentioned before. However, I intend to spend the next week setting up the server to run on the Jetson Nano and use the information provided from the ML pipeline. I haven’t managed to work on the processing algorithm too much this week as I have been working on the web app instead but now that I can soon get a prototype of the web server running, I will be formalizing and implementing the algorithm next week.
Team’s Status Report for 8th February 2025
It is possible that with the base Jetson Nano setup, we may not be able to meet the latency requirements. For this, our contingency plan is to use the CUDA kernels given to us and write optimized code to meet requirements. Also, we plan to use an FPGA to accelerate some of the ML operations in the Jetson, but if the I/O speeds prove to be too slow, and we meet specs without the FPGA, then we will simply not use it. We did not make any major modifications to our initial ideas this week; however we did brainstorm for additional functionalities that we might want to add if time and resources permit. The schedule has not been updated.
Joe’s Status Report for 8th February 2025
This week, I have been primarily working on developing the processing algorithm. Mainly, I have been reading literature on how cards are used to update the count, existing mathematical models on Blackjack so that I can decide how to provide suggestions for users to play. Additionally, I’ve spent some time setting up the scaffolding for the web application, outlining what are the functionalities that the web application should provide. As of now, some of these functionalities include: ability to toggle suggestions on and off, interface to start and set the game and players. Progress is going smoothly and according to plan. I intend to set up a basic version of the web application by next week, figure out whether the functionalities are sufficient, and spend the next few weeks improving the UI design and integrating it with the processing algorithm.