Our team continues to make steady progress toward our MVP and currently sees no major risks to completion. This week we continued progress on hardware development, embedded systems, and the application. We had a couple iterations on the hardware attachment that attaches the device to the tennis racket. On the embedded side, we updated the controller code to use SPI instead of I2C and successfully read IMU data packets at 500 Hz while transmitting data via BLE. On the software side, we began integrating the IMU data stream into the app and started implementing calculations to approximate ball velocity.
One potential challenge that carried on from last week is finalizing the physical hardware design. The attachment must be securely mounted to the racket while avoiding movement during play. When we begin collecting real swing data, we may also need to adjust parts of the data pipeline or processing steps to ensure the data is reliable and can be used for our specific use cases consistently.
To mitigate hardware risk, we will continue iterating on the attachment design and finalize the prototype so we can begin collecting swing data. We will also finalize component selection and place an order for a PCB.
To mitigate data and ML risks, we first need to establish a working end-to-end pipeline before focusing on model accuracy. We will collect sensor data via BLE, run basic analytics on the laptop, and begin preparing the dataset for model training. We will also continue adapting the app so it can interpret the incoming IMU data and compute metrics accordingly.
We do not have an updated schedule.
Our focus next week will be continuing to work on the physical prototype, collecting initial swing data, integrating the IMU data pipeline into the app, and beginning early model training for stroke classification.
