Carnegie Mellon ECE Capstone, Spring 2025: MM Demangone, Taylor Koda, Aneesha Bhattacharjee
This week, I worked on testing the smallest pill compartment to reach the 95% accuracy threshold. Currently, it’s at 83%, so I’m still working on that. I also did additional hardware testing and readjusted our design further to accommodate accurate pill dispensing by adding funnels to the top and covering the discs on the front to prevent the pills from flying out. Same as was in the presentation, conducted 59 trials on the smaller compartment.
This week I continued debugging some of the software features like the healthcare provider view. I helped with the hardware components as well. Since the pill dispensing wasn’t the best for pills of the different sizes, I resized the slots in the discs so the right dose would fall out each time and added tubes to help with the jamming. I also made a CAD for 2 fillers for the discs. I am also preparing for the final presentation.
This week I have focused on doing a lot of integrated testing. MM and I were working on the load cell amplifier, which is not working as intended so i shifted my focus on running tests for the pill dispensing functionality. Initially the design was not working for all the pill sizes, so Taylor helped me resize and readjust some of the components so they work for the different pill. I 3D printed a small CAD model that Taylor made to fill two of the smaller discs. After that I have conducted 59 trials for each compartment with the different pill types, which we got from the equation in our design to ensure accurate pill dispensing of >95% . In doing so, I adjusted and stabilized the device as I went. I also added a slide-like structure so the pills fall into a central location. I also did slides for the final presentation and over the next week will continue testing and getting the hardware components ready for presentation and try to get the load cell working.
I have been working on fixing and testing the dispensing functionality on the device. To ensure the correct dosage is dispensed, I have adjusted the height of the servos and added more stability to the structure, and I am testing with multiple kinds of pills. I have also been working with MM on the load cell although we are running into issues with measuring an accurate weight as there is too much noise and we need our weights to be very precise. We are continuing to troubleshoot this and we will then add it to our structure. I will also work on updating the dashboard based on the weight sensing. We once again corrupted the SD card on our RPi so I reflashed it and redid some of the servo set up, but this was only a minor setback.
This week we accomplished a lot on both the hardware and the software end. For software, Taylor added some additional APIs and did some more testing on the web app. We then purchased a domain and deployed our app. MM and Aneesha worked on the hardware to get the servos and the websocket connection working, so we can use the dispense button on the web app to signal a servo to move. The device housing was built and the hardware components were mounted, and we are testing their movement and the dispensing of the pill. MM also got the speaker connection via Bluetooth working,g but we still need to work on that more, but it will not be a part of our interim demo. Overall, we are on track and at a good spot for the demo.
This week I spent time working with MM to get the servo motors working. We figured out the issue we had with the servo motors not turning 180 degrees since we were not resetting the angle each time we moved them. Since that was working via Bluetooth, we then tested the websockets to make sure that once deployed, we were able to send a signal from our web app to move the right servo and that was successful. Then I spent the rest of the week building our device. I had some issues with the materials we were using, but that got resolved, and I build the structure that holds the pill compartments and the rotating discs and tested the servo motion when attached to the disc. Although some goals got shifted over the previous weeks, I am on track for where we need to be for the interim demo.
This past week we have made significant progress on our project, both on the hardware and software side. The majority of the tasks associated with the web application have been completed with Taylor taking on some extra tasks due to issues with the hardware that Aneesha and MM have been working on. Initially, there were some delays in 3D printing which have been resolved with the folks at FabLab and all the components have been printed. The hardware connection between all the devices has been established and they are working, particularly, connecting to the RPi via Bluetooth and sending the signal to move the 6 servos which work at a primitive level. There needs to be additional testing done with the deployed web app and connection via websocket. We are also in the process of physically constructing the device, connecting the funnels and the discs to the housing and hardware, so by next week we should have the end-to-end dispensing functionality working and we will also get started on installing the load cell. Although some tasks have been shifted around and unexpected issues had arisen, we are still on track for the interim demo. There are multiple commits from all 3 of us on the GitHub tracking the progress we have made with the web app and hardware/software connection.
This week I have been focusing on the hardware components as well as building the device. Last Sunday, the RPi5 required reflashing due to a corrupted SD card, which MM and I worked to set up again, after which I worked on setting up the Bluetooth to Rpi to servo connection via I2C. I used client/server code, which we have been using as a basis for our Bluetooth connection and I was able to send a signal to move the servos. Then we soldered the PWM driver and connected the 6 servos to test if all of them worked. In order to do this, I added more code to get all 6 servos moving using an I2C module that allows the client to pick which servo to move. When we tested with 1 servo, it moved 180 degrees, but when we tested with all 6, they only moved about 90 so I have been spending some time troubleshooting that. When MM sshed into the RPi from her device, the servos did not move at all, but when I tried from my device they did, so we need to figure out what kind of issues can come from that. With all of the 3D printing components printed and the hardware connection established, I have started to build our device and its housing. The backing that I designed initially is too large to be 3D printed, so I am using other materials to fit the exact specifications of our design. I will also continue working with MM over the course of next week on using the WebSocket to move our servos via the deployed application and once we get that working we will test the dispensing functionality in our device.
This week we have made significant progress, both on the software and hardware ends of our project. Taylor and MM worked on the web application setting up the UI. Most of the pages that we need have been set up. MM and Aneesha started working on the Bluetooth connection between the web app and the Raspberry Pi which is working. We have also started working on sending the signal from the web app to the servos so we can start assembling our device. The 3D printing took a little longer than anticipated because there were more requests for 3D printing at the FabLab. We are on schedule for our work even though some aspects we have been a little behind on but it is only because they require more time then we initially thought, however, we are still on schedule.
This past week I have been working on code for the pill dispensing. I worked with MM to get the Bluetooth connection between the Raspberry Pi and the web app working and after that, I have been working on getting the web app to send the dispense signal to the servo motors to move the discs. This has been a little challenging since the Raspberry Pi 5 does not use the same GPIO hardware as older models and there is little documentation out there for the RPi 5, but I have gotten the servos to work locally where I send a signal from the RPi and the next step would be to use the Bluetooth to dispense. Next week I will be working on assembling the device by mounting the servos to the 3D printed components.