Posted on

Kaitlyn’s Status Report for 4/25/2026

What did you personally accomplish this week on the project?

  • Presented Final Presentation in class on Monday
  • Verified “Active Session” functionality all works
    • vibration command pipeline
    • calibration + exporting to csv
  • Refined “Active Session” UI so FPA data + feedback is more user-friendly

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

We are currently on schedule for our demo since the App is now fully functional with the device during gait retraining sessions.

What deliverables do you hope to accomplish in the next week?

  • Add “History” tab functionality
    • AWS storage for each active session summary
  • If time: add “Insights” tab functionality
    • allow users to set custom habits/goals
    • connect AWS data with an AI API to generate broad natural language recommendations
  • If time: set up multi-device usage of the app (ie. downloadable on Rhea and Lakshmi’s phone)
Posted on

Team Status Report for 04/25/2026

What are the most significant risks that could jeopardize the success of the project? How are these risks being managed? What contingency plans are ready?

  • The mobile app is working with communicating between the shank mounted LRAs and the foot mounted IMU, however it hasn’t been formally tested with the mocap system and the treadmill yet. This risk is being managed as we are going to be conducting another data collection session to test the functionality of the app during treadmill walking this upcoming week. If we run into any issues with the app during the experiment we will adjust the code as necessary. 

Were any changes made to the existing design of the system (requirements, block diagram, system spec, etc)? Why was this change necessary, what costs does the change incur, and how will these costs be mitigated going forward?

N/A

Provide an updated schedule if changes have occurred.

N/A

List all unit tests and overall system tests carried out for experimentation of the system. List any findings and design changes made from your analysis of test results and other data obtained from the experimentation.

FPA Accuracy: 

  • Compared IMU-based FPA with mocap ground truth 
  • Findings
    • Normal walking speed + Treadmill: RMSE is 2.24, which is within the acceptable error boundary for accurate vibration feedback
    • Fast speed (20% faster than normal) + Treadmill: RMSE is 11.93, 5x more than acceptable error
    • The FPA algorithm relies on heading measurement from the swing phase of walking, the faster one walks, the shorter their swing phase = less accuracy.

We now know the exact limits of our device, which is that we can only hold adequate FPA accuracy at the patient’s normal walking pace or slower. When we increase beyond the patient’s normal walking speed, error dramatically increases. This is completely fine for our use case, however it is good to know concrete limits of this device from testing.

 

Intuitive feedback testing: 

  • Compared FPA after receiving verbal instructions vs. FPA after receiving vibrotactile feedback 
  • Findings:
    • Without device: With only verbal instruction to point toes inward, patient was avg. 4.4° away from target FPA (-10 degrees from their baseline FPA
    • With device: With haptic feedback, patient was 0.1° away from target FPA

We saw that haptic feedback greatly improved patient ability to meet their target FPA goals during gait retraining, showing that the feedback was intuitive enough that the patient was able to make considerable progress towards getting their FPA to align with the recommended angle. With this in mind, we are able to confidently say that our device would greatly help patients train by themselves at home, since our data shows a marked improvement in using the device versus the alternative, which would be a reminder from a physician to a patient to point their toes more inward. 

Perceived Feedback Testing

To test if different levels of intensity of the vibrations were distinguishable while walking, we tested 3 different levels of vibrations: 100% intensity, 50% intensity, 20% intensity of pulsed vibrations. After asking the participant which level of intensity they were feeling on their shank, the participants were not able to determine any differences between the 3 intensity levels. Instead, they were only able to distinguish if the vibration was present or not. This could be due to the MCU only being able to drive 3.3V, so that the LRAs are not able to produce a strong enough vibration. This changed our device design such that we are no longer planning on implementing the scaled feedback based on the degree of error. If another MCU that could drive a higher voltage, then this could result in more distinguishable differences in the intensity levels to allow for scaled feedback. 

Intuitive UI Testing: 

To test our app’s UI, we asked participants to fill out a short survey (google form link: https://forms.gle/dZCPrsvuKGisoiJm7) locating and explaining information present on the interface. We’ve so far tested with one participant, and one change we made is ‘hiding’ the bluetooth connection pipeline from the user, and having it automatically start when the user presses ‘start’ and disconnect when the user presses ‘stop’. Furthermore, we separated the ‘calibrate’ and ‘export csv’ buttons to an admin section of the tab since they are not directly user-facing. Besides the active session workflow improvements, the participant accurately identified other elements of our UI such as data visualizations and recommendations. 

Posted on

Lakshmi’s Status Report for 4/25

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

  • Created the FPA accuracy and training effectiveness slides for the Final Presentation slides, added brief explanations for the why behind our testing results
  • Tested the portable treadmill for demo day with Rhea
  • Cleaned up the Github code and revised documentation for the firmware and the laptop bluetooth processing code for future PhD students to build on our device
  • Revised graphs and plotted correlation between mocap and IMU measured FPA for final meeting with Dr. Eni Hallilaj and Dr. Melissa Orta Martinez

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

On schedule.

What deliverables do you hope to complete in the next week?

  • Finish final report
  • Finish final poster
  • Finish final video
  • Do one complete run through of what we’re going to present to judges on demo day.
Posted on

Rhea’s Status Report for 04/25/2026

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

I made the surveys for the device usability and comfort, and collected responses from different participants to get an idea of whether or not the shank-mounted device met our use case requirement of being unobtrusive while walking. I also worked with Iqui to make more of the soft cases for the shank-mounted device for use during the demo – I fabricated 3 sets of cases just in case one of them rips during the demo.

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

My progress is on schedule; all that is left to do this week is final assignments (video, poster, paper). 

What deliverables do you hope to complete in the next week?

  1. Finish final poster
  2. Prepare for demo
  3. Finish final report
  4. Finish final video
Posted on

Kaitlyn’s Status Report for 4/18/2026

What did you personally accomplish this week on the project?

  • Added two device connection (for receiving FPA measurements and sending vibrations via the LRA) into the mobile app
  • Added calibration (pre-session) functionality for initializing the base FPA across all sessions
  • Added data logging feature everytime the FPA measurement data changes. Once session is complete, user will be able to export to CSV.

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

We are currently on schedule as the core functionality of the App is implemented and we’ve done multiple mocap device testing sessions.

What deliverables do you hope to accomplish in the next week?

  • Verify (and debug if necessary) calibration and data logging features
  • Add in the automatic vibration pipeline (sending vibrations based on the FPA)
    • Convert Lakshmi’s Python script to TypeScript
  • Align the FPA measurements with the UI — ie. make the data legible for the user
  • If time: implement AWS backend for storing session summary statistics to database (ie. DynamoDB) to be used for our History/Insights page

As you’ve designed, implemented and debugged your project, what new tools or new knowledge did you find it necessary to learn to be able to accomplish these tasks? What learning strategies did you use to acquire this new knowledge?

  • Mobile app development
    • New tools/knowledge: Expo, React Native, XCode/Apple Development
    • Learning strategies: reading documentation, searching through forums, prompting AI to explain confusing syntax and structure
  • Setting up an AWS project
    • New tools/knowledge: adding collaborators to project (IAM Identity Center), deploying via AWS CLI
    • Learning strategies: watching YouTube tutorials, reading AWS documentation, asking peers with AWS experience
Posted on

Lakshmi’s Status Report for 4/18/2026

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

  • Implemented scaled feedback dependent on the FPA angle
  • Changed Bluetooth connection workflow so that we no longer have to reset the wearables in between sessions
  • Programmed shank MCU to take in an adaptive encoding for vibration feedback so there is no need to reflash the MCU every time we want to send a different vibration pattern
  • Tested FPA accuracy in mocap lab
  • Plotted FPA accuracy graphs comparing IMU measured FPA with mocap measured FPA to get RMSE (2 degrees!)
  • Tested vibration feedback efficacy (toe-in + toe-out) in mocap lab

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

On schedule.

What deliverables do you hope to complete in the next week?

  • Get vibration feedback efficacy data parsed and graphed
  • Do more testing in mocap lab for vibration feedback efficacy
  • Conduct surveys for vibration effectiveness and device comfort.


As you’ve designed, implemented and debugged your project, what new tools or new knowledge did you find it necessary to learn to be able to accomplish these tasks? What learning strategies did you use to acquire this new knowledge?

We recognize that there are quite a few different methods (i.e. learning strategies) for gaining new knowledge — one doesn’t always need to take a class, or read a textbook to learn something new. Informal methods, such as watching an online video or reading a forum post are quite appropriate learning strategies for the acquisition of new knowledge.

  • I learned how to test documentation thoroughly after setting up the firmware code on multiple MCUs, and how to make the documentation understandable to a layperson (i.e. booting a new XIAO NRF from scratch, without forcing the user to look at the MCU forums) 
    • This was learned through experience in building it because I had to make it as easy as possible to set up the firmware for my teammates
  • I learned how to code and flash firmware onto an MCU
    • Mainly looking on forums to understand how to move from the Arduino IDE to VSCode, and setting up the workflow so that it was extremely similar to running a python file for inexperienced developers
  • I learned how to use Bluetooth UART protocols 
    • Mainly looking the wiki and the pinout to understand the specs for the XIAO NRF Sense MCU
    • Looking at forums for the laptop Bluetooth receiver code
      • Also learned how to use a queueing system for the receiver and transmission code so that you only need to connect once, rather than having the extra latency from connecting and disconnecting
  • I learned the algorithm for calculating foot progression angle, which required a shallow knowledge of kinematics and how to interpret the data from each of the IMU’s axes
    • To acquire this knowledge I conducted literature review over a couple of previous papers in foot progression angle/joint kinematics.
Posted on

Team Status Report for 04/18/2026

What are the most significant risks that could jeopardize the success of the project? How are these risks being managed? What contingency plans are ready?

  • The App can currently receive FPA measurements as well as send vibration commands, however we are still currently working on having those vibration commands automatically send based on the FPA. We will need to convert the Python script to TypeScript (like previous iterations), but we’ll need to debug and ensure the pipeline is functioning properly. Additionally, we still need to test that the calibration and data logging functions work (and debug if necessary). 
  • The FPA accuracy dependent components of the device, such as vibration feedback error range, need to be finalized while still staying in line with previous research error ranges (i.e. no vibration for correct FPA +/- 2 degrees). Currently, our error range is +/- 4 degrees to prevent “noisy” feedback for toe-out training, and +/- 2 degrees for toe-in training. We need to be more certain about this fluctuation in error range between toe-in and toe-out training through further testing.
    • The goal of our device is toe-in gait retraining, so we do have a good error range for this. 

Were any changes made to the existing design of the system (requirements, block diagram, system spec, etc)? Why was this change necessary, what costs does the change incur, and how will these costs be mitigated going forward?

N/A

Provide an updated schedule if changes have occurred.

 N/A

Posted on

Rhea’s Status Report for 04/18/2026

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

Finished fabricating cases for both the foot mounted and shank mounted components. These components are currently adhered to the user using tape, but the next iteration of the case will have a slot for a velcro strap for the foot mounted device. I also finished soldering the MCU/IMU component with the battery and on/off switch. I had to resolder the MCU for the shank mounted device since the battery was not soldered on the right pins to allow for charging capabilities through the MCU usb-c port. 

Started testing the device with Lakshmi, Kaitlyn, Vu, and Iqui. We conducted the following tests: 

  • FPA accuracy testing: 
    • Treadmill walking at baseline walking speed with the foot mounted device 
    • Treadmill walking at 20% slower than baseline walking speed 
    • Treadmill walking at 20% faster than baseline speed 
    • Overground walking 
  • Intuitive feedback testing: 
    • Treadmill walking at 20% slower speed, verbally instructed participant to walk with their toes pointed inward 
    • Treadmill walking at 20% slower speed, verbally instructed participant to walk with their toes pointed outward
    • Treadmill walking at 20% slower speed, participant walked with their toes pointed inward based on vibrotactile feedback 
    • Treadmill walking at 20% slower speed, participant walked with their toes pointed inward based on vibrotactile feedback 
  • Gait retention testing: 
    • Treadmill walking with toes pointed inward immediately after receiving vibration cues on how to walk toe in 
    • Treadmill walking with toes pointed outward immediately after receiving vibration cues on how to walk toe out 

The tests were done with the motion capture system as well – I preprocessed/labeled all of the motion capture data after each experimental session. After FPA accuracy testing, we compared the results from the device estimated FPA vs. the mocap ground truth. After intuitive feedback testing, we compared the FPA of the user without any feedback vs. receiving feedback to see if the vibrations were helpful to the user to learn how to adjust their walking. 

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

My progress is on schedule, as we have been conducting testing with the mocap system all of next week. 

What deliverables do you hope to complete in the next week?

  1. Conduct second round of testing with a new participant 
  2. Finish analysis of gait retention data 
  3. Finish slides for final presentation 
  4. Start working on final poster 

As you’ve designed, implemented and debugged your project, what new tools or new knowledge did you find it necessary to learn to be able to accomplish these tasks? What learning strategies did you use to acquire this new knowledge?

We recognize that there are quite a few different methods (i.e. learning strategies) for gaining new knowledge — one doesn’t always need to take a class, or read a textbook to learn something new. Informal methods, such as watching an online video or reading a forum post are quite appropriate learning strategies for the acquisition of new knowledge.

At the beginning of the semester, I wasn’t very comfortable with soldering (I had done it a few times before, but not as much as required for this project). So a lot of what I was learning (how to solder an on/off switch, how to solder a battery onto an MCU, etc.) were things I learned both through Youtube tutorials online as well as tutorials and suggestions online. 

The MCU for the shank component also ran into issues where it wasn’t being recognized as a device when I plugged it into a laptop. I realized that the MCU was bricked, and was able to find a forum post from 2020 where someone ran into a similar issue and was able to unbrick the MCU so that it could be recognized as a device to be programmed. 

This was also the first time I was making a soft case, so I learned the methodology of making a case using liquid silicone. With Iqui’s guidance, I learned how to use the centrifuge to mix the liquid silicone materials together to then cast it into a mold for the soft case. 

A lot of the learning strategies I used to acquire this knowledge involved how to look things up effectively with different keywords/phrasing for the questions to get the best results I am looking for. I also asked for a lot of help from mentors such as Vu and Iqui for guidance as they also had resources from previous experiences that could help me when I got stuck or had questions for design decisions. Most of what I was working on required a lot of trial and error. 

It was also necessary to learn the background information related to gait retraining and how vibrotactile feedback cues work/are perceived by humans. This required an extensive literature review to understand the fundamental background knowledge to be able to apply it to the project. I went through and read the recommended papers sent by Dr. Halilaj and also conducted some of my own literature reviews. 

Posted on

Lakshmi’s Status Report for 4/4/2026

What did you personally accomplish this week on the project? Give files or photos that demonstrate your progress. Prove to the reader that you put sufficient effort into the project over the course of the week (12+ hours).

  • Fixed Bluetooth processing code to include timestamp for synchronization when processing acceleration and gyroscope data
  • Fixed IMU sampling code to resample at 100 Hz for consistency rather than its max (~180 Hz)
  • Ported IMU-data-sending code from designated foot wearable MCU to secondary MCU for further development
    • Updated documentation to ensure smoother code portability (needed to add the external change for making Bluetooth packets 24 bytes instead of the default 22), reformatted as README in Github
  • Added code to connect to both MCUs at the same time (kept code in for receiving data from foot wearable MCU, now can connect to shank wearable IMU to send vibration commands)
  • During group meeting with PhD students: Discussed with Vu the details of testing “convergence”, or the number of steps needed to calibrate the FPA algorithm’s step detection mechanism. Currently, we have the number of steps at 8, but I tested in a small room where I would be turning often. Turning introduces error into the FPA algorithm, so we must now test the calibration while walking in a straight line via treadmill.

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

Progress is on schedule according to updated Gantt chart for demo.

What deliverables do you hope to complete in the next week?

  • Isolate mocap FPA analysis code for mocap testing use
  • Create script to port results into CSV for analysis during mocap testing
  • Determine calibration time length during mocap testing
  • Write scaled vibration command code (that is actually reactive to calculated FPA angle rather than hardcoded)
Posted on

Kaitlyn’s Status Report for 4/4/2026

What did you personally accomplish this week on the project?

    • Polished mock UI pages for interim demo within mobile app
    • Switched FPA integration to run on the mobile app directly rather than through AWS (due to latency and resource constraints)
      • Converted Lakshmi’s Python script to TypeScript to run on mobile device
      • Verified proper FPA integration (connecting + sending data properly in app)

Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

We updated our Gantt Chart prior to interim demo and based on our new schedule, we are essentially on track. We plan on conducting testing starting next week and the FPA integration on the mobile app just needs to be verified for accuracy.

What deliverables do you hope to accomplish in the next week?

  • Verify with Lakshmi that the FPA integration is accurately measuring step count, FPA, etc.
  • Implement AWS backend for storing session summary statistics to database (ie. DynamoDB) to be used for our History/Insights page