Posted on

Jessica’s Status Report for 3/6

This week, I focused on preparing our design presentation. For the slides, I mainly filled out the block diagram and  mechanical solution and implementation sides. With my group, I then met with our professor and the TA to discuss potential improvements to our presentation. After some advice from our TA to add more implementation details, Lauren and I met to finalize sensor placement and Jetson Nano GPIO allocation.

I also spent a lot of time finalizing the mechanism.  After deciding to reduce our target mechanism latency to <1s last week, I began researching different linear motor actuators. The main types of mechanisms I found were screwball, rack and pinion, and belt driven. It seems like all of these mechanisms are suitable for our use case given that we can adjust the mechanism speed based on gear sizes. I was also able to find CAD mechanisms for the rack and pinion and belt driven mechanisms so that we can hopefully laser cut most of our mechanism.

My progress is slightly behind. I focused most of my time on the hardware aspect of our project and on finalizing the slides, so I was not able to research different image classification models. Hopefully, we can use the resnet model that Lauren and I found a couple of weeks ago.

Next week, I hope to hook up our sensors to an Arduino and begin collecting data. Although we have a general idea of which stepper motors and motor drivers we want, we also need to submit the purchasing request.

Posted on

Jessica’s Status Report for 2/27

This week, I mainly researched different sensors so that we could submit our first purchase request by the end of this week. I tried to find sensors with a decent sensing range that fit within our budget, but most sensors have around an 8mm range. From the sensors that I researched, we ended up purchasing an inductive, capacitive, and load sensor. My group also met with our TA to further discuss our mechanism and our requirements. After our discussion, we decided to tighten the requirements to 90% classification accuracy and 1-2 second latency.

Our project is still on-schedule. Next week, I plan to finalize our mechanism, order the mechanism parts, and prepare for our design presentation.

Posted on

Team Status Report for 2/27

From last week, we changed several of our requirements to improve the use case of our product. For classification accuracy, we increased the requirement from 31% to 90% accuracy. For latency, we decreased the time from 2-3 seconds to 1-2 seconds. Both of these changes will make designing our classifier and mechanism more challenging, but they will significantly improve the user experience and overall system. With a reduced latency and increased classification accuracy, the user can place items into the trash can and sort them both reliably and quickly.

The most significant risks we are currently facing are meeting the range requirements of our sensors and reducing the overall latency. We plan to purchase multiple sensors to build a sensor array, but that method might become too expensive, depending on how much of our budget we can dedicate towards purchasing more sensors. We had also intended to embed most of the sensors underneath the platform, but after some research, that might not an option for some sensors. In terms of latency, we plan to finalize the dimensions of our project and pick out motors next week to ensure that our mechanism can meet the latency requirement. As a back-up plan, we are researching other potential mechanisms including a swiveling platform which might be able to move items faster to each bin.

Our project is still on track. This week, we presented our proposal and submitted an order request for our sensors as planned. Next week, we will finish finalizing the mechanism and continue ordering parts.

Posted on

Jessica’s Status Report for 2/20

This week, I helped to narrow down the scope of our project and further develop our project. Specifically, I researched  potential sensors that we could use in the case that our classifier was not accurate enough. We ended up choosing an IR and inductive sensor that were mentioned in a garbage segregation research paper that I had found. I also helped to finalize our mechanism and modify our proposal presentation slides due this weekend .

Our project is still on-schedule. During the week, we had to schedule extra meetings with our professor and TA to address some problems with our idea, but we have now resolved all of those issues.

Next week, I plan to start the design process including finalizing budget, making preliminary sketches of the mechanism, and beginning to prepare for our design presentation in two weeks.

 

Some resources for sensors:

https://lillych.in/files/Chin-2019-icra.pdf

https://iopscience.iop.org/article/10.1088/1742-6596/1007/1/012057/pdf