Posted on

Team Status Report for 03/11/23

One of our current risks is that the Jetson AGX Xavier will require more power than the 12V car outlet can provide. This week we will take initial measurements to determine how much power the Jetson is consuming when on and play some music through the speaker to get a better idea of whether 12V will be sufficient. If our Jetson ends up consuming too much power, we can mitigate this by borrowing a different Jetson from the ECE department that has lower power consumption but slower computation abilities (such as a Jetson Nano). Another risk is that the audio-guided calibration process will be unclear to the user. To address this, we will conduct testing of the calibration process with at least 3 users that aren’t one of us and get their feedback on how easy the process is to follow.

We had 2 main changes to the design of the system since last week. First, we decided to use a cellular dongle instead of a WiFi dongle to send data from the Jetson to our web application. This change will allow us to connect directly from the Jetson to the internet without requiring any additional efforts from the user (such as setting up their own hotspot for the Jetson to connect to).  The second change was that we added a logs page to the web application that will allow for a user to view a record with more detailed reasoning for each of the instances that triggered feedback from their DriveWise device. The most current page layout for the web application is below:

We are on track with our Gantt chart and our overall schedule has not been changed. 

After establishing our subsystems, we have determined that the main tools we will need to be able to learn how to use will be OpenCV DNN and Firebase. OpenCV DNN will be used for the CV/ML subsystem and Firebase will be used to enable login/registration capabilities on the web application. 

Posted on

Elinora’s Status Report for 03/11/23

Earlier in the week, Sirsha and I set up the initial structure of our web application in React over VSCode LiveShare. We programmed the frontend basics for the login and stats pages and tested that we could access these pages by clicking different buttons on the web app (like the “Login” button leading from the login page to the stats/home page). We also decided to add an additional page to our UI design in which users can access the individual log for each time that feedback is triggered from their device. Viewing this page provides users with more detail regarding the kind of inattention that they exhibited and the layout of the page is included in this week’s team status report. I spent the rest of my time this week working on the design report with Yasser and Sirisha. More specifically, I was assigned the introduction, use-case requirements, architecture, and parts of the implementation and design trade studies sections. I also briefly tested the speaker that we ordered and confirmed that it played sound clearly from a .wav file when connected to my computer. 

I am pretty much on schedule with our Gantt chart. After we decided to use a cellular data dongle instead of a WiFi dongle to send data from the jetson to the web application, we wanted to conduct more research before ordering a particular cellular dongle. Since transmitting the data to the web application is not scheduled in the Gantt chart until 2 weeks from now, I will hold off on submitting the order until we are sure. Otherwise, I am on schedule with my tasks.  

For my deliverables next week, I am scheduled to assemble the hardware components of the device and test power consumption. I also want to research different cellular data dongles and decide on one by the end of the week. For the web application, I will more fully flesh out the login and registration pages this week and potentially set up Firebase for the actual login/registration capabilities of these pages.