Posted on

Kushaan’s Status Report for 2/15

This week I looked into the Raspberry Pi more in-depth, and also into thermal camera imaging. I looked into benchmarks regarding different inference frameworks, and their benefits. I settled on using PyTorch to begin with, as it is the easiest to proof-of-concept with. Then, I will try using more advanced parallelism frameworks. I also looked into some depth-estimation models, since this will be an important part of our product. I found a few models that look promising, but want to do some benchmarking.

 

We got the RPI this week, so I will be running benchmarks over the weekend on these models, to verify the numbers as well. I want to generate intuition for the accuracy and limitations of these models.

 

I also worked on the design presentation, primarily focusing on my sections, and updating the theme and visuals, since I will be presenting

Posted on

Cole’s Status Report for Feb 15th

This week, I focused on researching suitable lithium polymer (LiPo) batteries to power an amplifier and reviewed the code for a chassis kit sourced from Amazon. The aim was to ensure compatibility, efficiency, and safety in integrating these components into our project.

 

After looking at LiPo battery models and specifications suitable for powering the amplifier and analyzing battery capacity, discharge rates, and form factors to meet project requirements, I settled on 2200mah 3S 30C LiPo’s to power the microcontrollers and chassis motors. For the speaker and amplifier I chose 1500mah 4S 120C LiPos to power the speaker magnet. After reviewing the code that came with the chassis kit it looks like the vast majority of the work has been done for us. We likely will only have to change the pin connections in the code, wire it to the GPIO pins on the Raspberry Pi, and call the prewritten functions.

The next steps will be continue work on the design presentation and help assemble the equipment we ordered for the first test.

 

Posted on

Team Status Report for 2/8

Currently, the biggest risks for our project lie in robotics and the results of our testing. As a group, we don’t have tons of robotics experience, and this will be an important part of our project. We feel we have enough similar technical skills to figure this out, however. During the presentations, someone raised the concern of the impact of smoke. We want to test our behavior under smoky conditions, but also have a contingency involving thermal camera sensor fusion. 

 

Our progress is on schedule so far. Currently, we don’t have any plans to change our design, but we are planning to do more due diligence next week. There may be changes during this step as we solidify the design.

Posted on

Steph’s Status Report for February 8th

In the past week, we put together the proposal presentation and I practiced for the presentation on Monday. On the day of the presentation, we received questions that we should take into consideration such as storing the signal into ESP32 for example. Along with that, I have put together a bill of materials spreadsheet that the team can keep track with on what needs to be bought, what has been delivered, and what we already have. While doing this, I have been researching and picking out the best subwoofer magnets to utilize and ones that would be most affordable but also hit our range of frequencies.

I hope to test fires with a standard speaker in the next week to get an approximate idea of the distance the speaker needs to be in relation to the fire. Furthermore, it would help to gauge how big of a fire we expect to put out.

Posted on

Kushaan’s Status Report For 2/8

This week we were primarily focused on creating the presentation. We took a look at parts and determined which would be suitable for our use-case requirements. Particularly, I looked at the computer vision section and what hardware would be necessary. I looked at benchmarks on various compute platforms (RPI vs Jetson) of object detection algorithms. I found that an RPI can infer in ~500ms if we tweak the parameters correctly, which we found suitable for this use case. We also looked at camera options, and I believe that a regular pi camera will provide suitable resolution at a reasonable price. 

 

In our presentation, someone brought up concerns about the effect of smoke on image detection. I considered this problem, and while I don’t have a definitive answer, one workaround I thought about was sensor-fusing with a thermal camera. We could use the combination of inputs to more accurately detect fires. 

 

I am currently on track with the schedule. Next week, I will be looking into creating some notebooks and doing proof-of-concept testing to make sure my intuition is correct about my sensing components.

Posted on

Cole’s Status Report for Feb 8th

Over the course of this week I spent time researching different mecanum wheel chassis to determine which ones might fit our project best. My main source has been Amazon as it appears they have the most accessible kits with documentation.

While at the end of this week I feel confident in the final options I’ve narrowed down the chassis to there are still variables to consider that have not been fully defined.