Ore’s Status Report for 3/21/26

This week, I focused on continuing to debug the user detection deployment to the Raspberry Pi 5. I worked on identifying setup and runtime issues on the device. I also installed the fan case for the Raspberry Pi because it was overheating even when idle, which will help ensure stable operation during longer testing sessions. Progress this week was somewhat limited because I was at a conference starting midweek and had to leave the Raspberry Pi on campus, but I still spent time diagnosing issues and planning next steps for debugging and setup.

My progress is behind schedule due to the remaining setup and debugging work required on the Raspberry Pi. There are still a few external components we need, such as a USB keyboard and mouse, and an Ethernet cable, to fully configure and streamline code development on the Pi 5. Once those are available, I expect the setup issues to be resolved quickly. Importantly, this delay does not block my teammates’ progress, as they are continuing work on the mechanical assembly and other subsystems in parallel.

Next week, I plan to complete the Raspberry Pi setup and get it running reliably on the hardware. I also aim to begin integrating the user detection system with the motor control subsystem, allowing the position error output to drive the pan and tilt adjustments. As the physical assembly progresses, I will support early integration testing of the full system to ensure the tracking pipeline works smoothly with the mechanical components.

Ore’s Status Report for 3/14/26

This week I focused on getting the user detection system running on the Raspberry Pi 5 with the Raspberry Pi Camera Module. I ported the vision pipeline to the Raspberry Pi and began testing live camera input while running the pose estimation model. The system uses MoveNet to detect body keypoints and estimate the user’s torso center, which is then used to compute the position error relative to the center of the camera frame. I spent most of my time testing the pipeline on the Raspberry Pi, debugging runtime issues, and verifying that the camera feed and model inference run correctly on the target hardware.

My progress is slightly behind schedule because I am still debugging a few issues related to running the system on the Raspberry Pi.

Next week, I plan to finish debugging the user detection system on the Raspberry Pi and continue testing the tracking pipeline with the camera. As I also help get the physical assembly completed, this will allow me to begin early integration testing of the full system. I will begin connecting the vision output to the motor control system so the umbrella can adjust its position based on the detected user location.

Team Status Report for 3/14/26

One of the most significant risks to the success of the project is delays in the physical assembly of the system, particularly the integration of the motors, gears, and structural components. Although much of the initial software development has been completed, meaningful system testing depends on the mechanical components being installed and functioning properly. Without the motors and gearing mechanisms in place, we cannot fully validate the motion control, actuation, and overall system responsiveness of the shade system. Mechanical integration also presents challenges such as alignment issues, mounting stability, and ensuring that the motors provide sufficient torque to move the canopy reliably.

To manage this risk, we’re prioritizing the completion of the remaining mechanical tasks so that the hardware and software subsystems can be integrated as soon as possible. The focus for the current phase of the project is completing the mounting brackets, canopy fabrication, and the full physical assembly of the arm, joints, canopy, and motors. These tasks are distributed across the team to ensure steady progress and reduce the likelihood of delays caused by a single point of failure. By accelerating the physical assembly process by having more people helping, we will be able to begin integrated system testing earlier and identify potential issues before the final stages of the project timeline.

Ore’s Status Report for 3/7/26

This week, I helped narrow down which parts to buy and started submitting actual purchase orders. I also worked on the user detection implementation, but mainly this week, for me, was drafting, refining, and submitting the design report. I’m currently on track with my scheduled work. Next week and a half, I hope to finish locally testing the user detection and have the full physical assembly of our shade system completed.

Team Status Report for 3/7/26

At the moment, the most significant risks that could jeopardize the success of the project are falling behind on our individual work, which may cause other team members to not be able to progress within their areas of work in the project. We’re planning to be more strict with following our schedule and staying on top of things to have a working demo in time, and shifting priorities within the project as needed, keeping our TA and designated professor in the loop. We’re currently working on the perception, app development, and the physical assembly of our project

 

A was written by Bonnie, B was written by Ore, and C was written by Nicholas.

Part A: Global Factors

Our smart beach umbrella considers several global factors beyond a local setting. Rising global temperatures and increased UV exposure make sun protection more important worldwide. An automatically adjusting umbrella can help reduce health risks such as heat stroke and sunburn in many regions.

Accessibility is also a global factor. Not all users are physically able or technologically experienced enough to adjust a traditional umbrella frequently. Automating the process makes the product more inclusive.

Cost and scalability were considered by using affordable components such as a Raspberry Pi and standard motors, making the system more practical across different economic environments. Privacy is also important, since the umbrella uses a camera and mobile app, so data processing should remain local to protect users.

 

Part B: Cultural Factors

The design of Shade.ai also considers cultural factors associated with beach recreation and outdoor leisure. In many coastal communities, beach outings are social and family-centered activities where convenience, relaxation, and shared spaces are valued. A system that autonomously maintains shade allows users to focus on spending time with friends and family rather than repeatedly adjusting equipment.

 

Part C: Environmental Factors

Shade.ai prioritizes the protection of living organisms and the responsible use of natural resources through its core functionality and material selection. By utilizing autonomous solar modeling and CV-based tracking, the system provides a reliable barrier against harmful UV radiation, addressing a health risk for beach-goers that is often underestimated due to unreliable cooling sensations.

Ore’s Status Report for 2/21/26

I worked this week on deciding on the best motors we planned to use based on the requirements of our project.  I have worked on initial designs of how the motors will interact with the umbrella; I also looked into different umbrellas/canopies we’re going to purchase, along with the best material/fabrication to use so the arms and joints don’t put too much pressure on the motor.s

My work is currently on schedule with the reworked schedule that we put into place after our project changes from Professor and TA feedback. Next week, I hope that once we acquire a camera, our motors, and the umbrella/canopy, I can start making progress towards the implementation of the lighting calibration and user detection.

Team Status Report for 2/21/26

The biggest risk right now is making sure the motors can provide enough torque to move and hold the umbrella. Since umbrella size and weight greatly affect the required torque, we are estimating these values early and researching appropriate stepper motors and gear ratios. If the torque requirements end up being too high, we can reduce the canopy size or use additional gearing or mechanical support to reduce the load on the motors.

 

We’ve started working on the arms and joints design, and perception & estimation components.

Team Status Report for 2/14/26

This week, we had several meetings about our intended product and its feasibility within the scope of the semester.  The major risk now is that we decided to pivot away from working with drones, so we then spent the next few days doing some research on our other ideas for the upcoming design review presentation, ultimately helping to pinpoint and flesh out a new idea we can go with for our capstone project. To mitigate the risk of the success of our project, we are actively keeping our designated professor and TA in the loop throughout the whole process. The main change we made to our existing design is removing drone usage for the shade provider and moving to a more stationary design. This change was necessary beacuse not only is drone autonomous flight challenging to get done within one semester, but there were also outside factors that weren’t initially considered: getting permission from CMU to fly a drone,  and/or having to locate an area to fly a drone, and to continue to use drones, we would need to review the CMU code for rules and requirements. No more cost was incurred from this change; costs were redistributed across new components of our design.

A was written by Bonnie,  B was written by Ore, and C was written by Nicholas.

 

B: From a social perspective, beaches are shared public spaces that bring together diverse groups across age, ability, and economic backgrounds. Not everyone has the same physical strength or mobility to repeatedly adjust a heavy umbrella in sand, particularly older adults, individuals with disabilities, or caregivers managing children. By reducing the physical effort required to maintain shade, our solution promotes greater accessibility and inclusivity in recreational spaces. Additionally, in hot coastal regions where extreme sun exposure can pose health risks, improving access to reliable shade supports public health and encourages longer, safer social interaction in outdoor environments.

Ore’s Status Report for 2/14/26

This week, we had several meetings about our intended product and its feasibility within the scope of the semester.  We decided to pivot away from working with drones, so I then spent the next few days doing some research on our other ideas for the upcoming design review presentation, ultimately helping to pinpoint and flesh out a new idea we can go with for our capstone project, actively keeping our designated professor and TA in the loop. Our collective progress is a bit behind due to us having to pivot from our initial capstone project, which also means I’m individually behind in what I had initially planned for the week. I am working towards getting the design review presentation done on time first, and then start gathering components and resources we’ll need to start building out our product in the coming week.

Ore’s Status Report for 2/7/26

This week, I focused on doing research for our proposed sensing, computation, and communication approach for our system. I also researched hardware requirements needed to run efficient, lightweight CV models: camera modules, CSI connectors, and mounting considerations. I looked into the hardware options for our drone, comparing different levels of assembly, and seeing which one is the most feasible and optimal for us.  I also looked at obstacle avoidance requirements, weighing the pros and cons of 2D vs 3D implementations. Finally, I began looking into what canopy design and material would be best suited to our use cases, and would have minimal impact on our overall drone flight stability and accuracy. Next week,  we’re looking into actually acquiring a drone, and then I’ll begin component-flight controller communication setup with the team. I’ll also try to start building the Git repository with all the pipelines and models we’ll be using. My progress is on schedule.