Team A2: ServeSense

Carnegie Mellon ECE Capstone, Spring 2026: Mario Cruz, David Hershenson, Geronimo Carom

Category: Status Report

Geronimo’s Status Report 4/25
Posted by : gcarom Geronimo's Status Reports, Status Report

This week I made some great progress on adding some new aspects to the app to help amplify the user experience. I added gamifying components that include, challenges, progress trackers, and ways to compare how you are doing compared to other users. I also incorporated an LLM that gives you feedback on specific aspects of your game. I also was able to incorporate a new aspect to the ML Model and now it can also classify differences in levels of players. This was mostly for proof of concept so that later on we can categorize players based on their UTR.

One thing that I need to continue to do is collect data of more swings, and different types. I also need to continue working on the swing visualization and add a couple of components to it.

Currently I do not have an blockers.

Team Status Report 4/18
Posted by : gcarom Status Report, Team Status Reports ,

Our team made strong progress this week in many aspects of the project. First, we improved the hardware design for the racket attachment. The new prototype is smaller and fits the key components better than the old version. We still need to make more progress on the PCB, so that’s one thing we are working on. Second, we made great progress on data collection and the ML pipeline. We collected a large amount of swing data from many players, improved the bluetooth flow to make collection more reliable, and built a model that can classify stroke types with high accuracy. We also continued working on swing visualization, and we still need to improve its accuracy. Third, we improved the app experience by adding an AI coach and a profile section that gives users summaries and feedback on their progress.

In order to mitigate risk 1, we will keep iterating on the hardware design so it fits well on the racket and does not negatively effect the user experience. We will also keep working on a final version of the PCB and overall attachment design.

In order to mitigate risk 2, we will continue collecting more data, improving the model, and testing the accuracy. This will help us incorporate more swing types and improve consistency across users.

In order to mitigate risk 3, we will keep working on the swing visualization and continue checking the reliability of our firmware, bluetooth transmission, and sensor data. We want the full system to stay stable during real use.

We also made progress outside the core prototype. We prepared for an upcoming pitch competition by working on the BOM, user guide, market research, unit economics, logo design, and presentation script. Overall, the team had a productive week and we do not have any large blockers right now, but our main focus next week will be final hardware design, better visualization, more data collection, and further improvement of the ML model and AI coach.

Geronimo Status Report 04/18
Posted by : gcarom Geronimo's Status Reports, Status Report

This week I was able to make a few good strides on the project. I was able to gather data with my team and then create an ML model that would classify stroke types correct >95% of the time. I also incorporated an AI coach that gives users feedback based on their focuses and their sessions. I also added a My Profile section to the app that gives the player summaries on what they have done and how they are improving.

There are a few things I was not able to get to such as more types of swings in classification.

There are currently no blockers.

My goal is to continue collecting data, improving the model, and improving the AI coach

Mario’s Status Report 04/18
Posted by : macruz Mario's Status Reports, Status Report

Since last status report, I have updated our microcontroller firmware to be as consistent and robust as possible. I moved bluetooth transmission to after IMU sampling in order to keep the data collection as in tact as possible despite bluetooth blips. I also finished a script for cleanly collecting swing data and have spent several hours collecting hundreds of swings from at least a dozen players. I have worked on the visualization of the tennis swing as well and that will continue to be a focus this week.

Progress was good this week. I do not have any significant blockers this week.

My goal for this coming week is to get visualization to be more accurate, collect more data for swing categorization, and get feedback from tennis coaches to get better insights into future work. 

Team Status Report April 4
Posted by : gcarom Status Report, Team Status Reports ,

Our team is making steady progress on all fronts with regards to calibration testing of the IMU, the design to hold the IMU, and visualization of data. Our biggest priority now is data collection for fine tuning a model that will categorize different swings. This will allow us to make large strides in our project.

To accomplish this goal properly we need to both collect enough data and collect data from a variety of player levels. Once this is done we will be able to then fine tune the model and test its accuracy.

After this is complete we will also be testing the device during a proper session to see how it holds up and making sure the data for sessions is being organized and displayed properly.

Geronimo Carom Status Report April 4
Posted by : gcarom Geronimo's Status Reports, Status Report

This past week I worked closely with Mario to improve the swing path generation. We made great progress and the swings to be generating consistently with some reoccurring issues that are being debugged. I also did some research on how we would be planning on training the model for the project and found a pre-trained model we can use that interprets IMU data. All we need to feed it is labeled data from out IMU

Progress this week was good but we unfortunately were not able to record some data. We worked on making sure the data incoming from the IMU was accurate to make sure the data we were going to feed the model is correct.

We’re a few days behind on data collection because varsity tennis reserved the courts this weekend for a weekend tournament they had.

For this coming week I am looking to collect some data and start the training process of categorizing swings

Team Status Report 03/28
Posted by : macruz Group Status Report, Status Report, Team Status Reports

As of now our team sees a few potential risks/blockers for achieving MVP. Firstly is the design of the case for our embedded system. We are currently iterating on different approaches for attaching our system to the handle of the racket without impeding on the user’s experience. This may or may not take longer than 3 weeks to get in an acceptable range. Secondly is designing the ML pipeline for this system. We have done substantial outside research to give us confidence that our design can succeed. However, we will undoubtedly need to make changes to some parameters as is reasonable with our own hardware and data flow. Lastly and newly, we are a bit concerned with how often we may need to be calibrating our IMU to have it work consistently for as long as possible. 

In order to mitigate risk 1: we will be constantly iterating our design to minimize user impact. We will be reaching out to collegiate tennis players that we know in order to get feedback on our ideas and implementation as we go. 

In order to mitigate risk 2: we will be working on creating a baseline pipeline that works structurally the same but with less expected accuracy. We want to uncover unexpected issues as quickly as possible to make needed changes. We will additionally be doing testing and verification of our data flow to ensure data integrity as it goes through our ML pipeline. This will be pivotal in ensuring accurate results when testing the ML.

In order to mitigate risk 3: we will be working with filters and doing our best to calibrate the IMU to the fullest before making decisions as to integrate more sensors or change up our approach.

We have made successful transition from collecting data to the computer via bluetooth to actually being able to use the IOS application to collect data. This is great for the demo and great for our future progress. We have also made improvements to the IMU gyroscope and accelerometer readings by applying filtering to the sample data.

Geronimo’s Status Report 03/28
Posted by : gcarom Geronimo's Status Reports, Status Report

This week I worked on connecting the IMU to the app through bluetooth. The first step was to upload the app on my phone and not work on xcode anymore. After that I had to work with Mario to connect the IMU via bluetooth and be able to read the data. Currently we have base functionality when connecting and reading data.

Progress this week was steady and we focused on preparing for the demo.

My goal for this upcoming week is to keep working on the device reading of sessions and also some work with the type of swing reading.

I haven’t started the training for determining types of swings yet which puts me a bit behind, but I am sure I will be able to catch up on this.

Mario’s Status Report 03/28
Posted by : macruz Mario's Status Reports, Status Report

This week I have been working on integrating bluetooth communication between the iphone and the microcontroller with Geronimo. I also worked on calibrating the Gyro scope and Accelerometer with David before he took that over.

Progress was good this week. We have been preparing for the demo and we believe to have hit our target goals.

My goal for this coming week is do a successful demo and continue to clean up IMU data using filtering and other techniques so that we can start to collect data for our models. 

Team Status Report 03/21
Posted by : macruz Group Status Report, Status Report

As of now our team sees no greatly significant risks to achieving our MVP, having not really changed since last week. We still have a couple potential blockers or issues to tackle in the next weeks. Firstly is the design of the case for our embedded system. We are currently iterating on different approaches for attaching our system to the handle of the racket without impeding on the user’s experience. This may or may not take longer than 3 weeks to get in an acceptable range. Secondly is designing the ML pipeline for this system. We have done substantial outside research to give us confidence that our design can succeed. However, we will undoubtedly need to make changes to some parameters as is reasonable with our own hardware and data flow.

In order to mitigate risk 1: we will be constantly iterating our design to minimize user impact. We will be reaching out to collegiate tennis players that we know in order to get feedback on our ideas and implementation as we go. 

In order to mitigate risk 2: we will be working on creating a baseline pipeline that works structurally the same but with less expected accuracy. We want to uncover unexpected issues as quickly as possible to make needed changes. We will additionally be doing testing and verification of our data flow to ensure data integrity as it goes through our ML pipeline. This will be pivotal in ensuring accurate results when testing the ML.

We made successful improvements to the application to make the user experience better. This weeks work largely involved continuing to improve the things we started last week. We further streamlined data capture this week for example. Next week we will be connecting all parts of the system including the application to be ready for interim demo. We should have surface level data analytics ready and swing path visualization for the demo, including our 3rd iteration of the physical attachment.