Author: afodonne

Abigael Status Report (4/12/25)

Abigael Status Report (4/12/25)

This week I worked on several things regarding the boat with the team, including the planning for finishing up our project and waterproofing the boat. Additionally, I worked on making the output of the ML algorithm more usable/interpretable for a scientist working on the coral 

Team Status Report (4/12)

Team Status Report (4/12)

Team Status Report Our waterproof motors arrived this week! This allowed us to remove the makeshift motor mounting system that we had developed (rip stem kit 🙏) and work on integrating these instead. Additionally, we set a goal of having an operational boat – out 

Abigael Status Report (3/29/25)

Abigael Status Report (3/29/25)

This week, I spent most of my time working with the team to prepare for the interim demo. As our current motors are not waterproof and our new ones will not be in for the demo, we had to come up with a way to use our current motors with the boat. We were able to find a material to extend our motor axles (so that the propellors will be underwater) and I 3D printed a part to friction connect the original axle of the motor to the extended axle. This was fun for me because I have not used any type of CAD software before. I also helped with waterproofing the boat and general preparation for the demo.

For the ML software, I added training data to the model and am working on preparing a testing/validation metric for the interim demo. The testing is slightly behind where I would like to be but I think we are in a good place for the demo. I believe I am on schedule as most of the work I have left will be integration which I can do while improving the model and assisting the team in other ways. My next step will be integrating the temp/pH sensor into our project.

Maddie Status Report (3/29/25)

Maddie Status Report (3/29/25)

This week, most of my time was spent working on the general boat structure in preparation for our interim demo. Our propeller motors ended up not being waterproof and all of the waterproof motors that we could purchase were either too expensive or wouldn’t come 

Team Status Report (3/29/25)

Team Status Report (3/29/25)

This week, our team made the discovery that our propeller motors – which were marketed as waterproof – are, in fact, not waterproof and cannot be submerged in water as we planned. As a team, we researched new motors and other solutions, ultimately landing on 

Emma Status Report (3/29/25)

Emma Status Report (3/29/25)

This week, I spent time getting ready for the interim demo. Last week, I had finished a majority of my subsection, but I refined some of it to improve functionality, and thought about what there is left to do before the final demonstration. First, I worked on the live stream subsection. I was able to get the stream of images to save to a file on my computer, which will then be used in the image stitching algorithm to make a map of the landscape. I also improved the interface so that the user will write what they want to name the folder before they survey an area, and I made a special folder that saves images when the user wants to make a “screenshot.” The user will press the S key, and then the image being processed at that time will go to a predefined folder called “User Saved Photos.” This folder is not overwritten between runs. I also added instructions to the interface. 

 

I also updated the motor control system. I realized that the motor driver works a little differently than I thought it did. The ‘in’ pins control the direction of spinning, and the ‘enable’ pins control the motors being on or off. I had only wired the IN pin for the direction that I wanted to be logic high, rather than both, which was making the motor spin even when the enable was off. I then wired the other IN pins and adjusted the code so that these pins were always set, and the enable pins control the motors motion. I also wanted the user to be able to control the speed of the boat for turns. So I changed the enable pins to be PWM, the variables to be an integer rather than a boolean, and changed the dashboard to have a slider that controls the power going to the motors, and thus control the speed of the boat. I had to do quite a bit of debugging, but now the user can control the motor’s speed. 

 

Video of motors operating at a specific speed: Video 

 

I was also able to test whether my WiFi hotspot will be able to withstand both the Arduino and Raspberry Pi on it, which it does. Both the video stream and the motor control can happen at the same time. As a team, I helped build the boat with supplies from TechSpark to prepare for the interim demonstration. 

 

The next steps for me after the interim demonstration will be to improve the GUI of the live stream to be more professional looking, and to have better control of starting the live stream after stopping. I am also looking to integrate the XY motors I have with Maddie’s stepper motor into one Arduino and put it in the same Cloud dashboard. We also will be soldering our circuits together next week. I am currently working on schedule and do not see any risks ahead. 

Team Status Report (3/22/25)

Team Status Report (3/22/25)

This week, we dedicated our lab lesson on Monday to building the structure of the boat using a plastic bowl and foam board. As mentioned last week, while we were originally planning on starting with a foam raft and later implementing a foam board boat, 

Abigael Status Report (3/22/25)

Abigael Status Report (3/22/25)

This week, our group focused on starting to build out our boat model. Based on suggestions from Prof Gloria, we decided to use a plastic base in order to create a first prototype that will be stable in the water, rather than going with our 

Abigael Status Report (3/15/25)

Abigael Status Report (3/15/25)

This week I continued to work on the ML model, however I am behind where I would like to be. To counter this, I plan to devout a significant period of Sunday and Monday to capstone work. I have been working with the python library pillow for image processing, and now I need to implement classification part using a KNN model. I also need to finalize the way in which the images are fed into the code to be processed as depending on the number of images extracting for the camera and sent for processing, this could be a lot of data to run. I have designed a KNN model before, so I am confident I can get this working within the next two days. My next plan of action after that is to work with Emma to transfer the images from the camera to a laptop for processing and help the team to build the boat and integrate our parts for our mini demo deadline of this upcoming Friday.

Team Status Report (3/15/25)

Team Status Report (3/15/25)

This week, our team has set a goal of being able to combine the subsystems so we have end to end operation, even if there are some bugs, by the end of next week (Friday the 21st). In order to realistically achieve this goal, we’ve