Posted on

Team’s Status Report 4/26

Risks:
Lower accuracy than anticipated, but no large risks!

Changes:

Changed our algorithm for how we are doing downward stairs detection.

 

Unit Tests and Overall System: 

I will list the test followed by the findings we had from each test:

Object Detection –> Pretty solid all around. We tightened up the range that we accept objects so that it will only detect objects in a shorter range.

Steps –> With data augmentation, our model is very accurate in dim/weird angle areas.

Wall Test –> Mainly very accurate, only inaccurate on slanted walls where the closer wall is in a distance hole (distance of 0).

FSR -> mainly accurate, only inaccurate on carpets

Haptics –> completely accurate

Integration –> mainly accurate, only inaccurate on moments where there is a person on the stairs.

Posted on

Team Status Report 4/19

Risks:
Lower accuracy than anticipated, but no large risks!

Changes:
Moved to a fine-tuned model with an augmented portion of the dataset and different training parameters.

Posted on

Team Status Report 4/12

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 risks that could jeopardize the success of the project is the battery not working for the Jetson Orin Nano and it possibly frying our Jetson. We performed extensive research on this to make sure it won’t fry it but for the small chance that it will, we backed up all of our code on github and have all of the individual components. working seperately

• 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?
• Provide an updated schedule if changes have occurred.
• This is also the place to put some photos of your progress or to brag about a
component you got working.

There have been no chances to the existing design. There have been no changes to the schedule.

We have finished composing our cane!

 

Now that you have some portions of your project built, and entering into the verification and validation phase of your project, provide a comprehensive update on what tests you have run or are planning to run. In particular, how will you analyze the anticipated measured results to verify your contribution to the project meets the engineering design requirements or the use case requirements?

Validation

We plan on testing all of the various main features individually and then together. This means testing the object detection on 50 various objects, testing the wall detection on 50 various walls, testing the FSR on 25 different surfaces. For the various object and wall tests, the haptic feedback should detect on 48 out of the 50 tests respectively (~95%). For the 25 different surfaces, we want the FSR’s to detect the floor on 24 out of 25 of them (~95%).

Additionally, we want the system to only have false positives <= 5% of the time.

Posted on

Team Status Report 3/29

Risks:
The only risk is that sometimes the depth stream from the LiDAR camera gives us the wrong data/doesn’t work in random holes of the frame, so it tells us objects are 0 meters away which will likely lower our accuracy but hopefully won’t end up interfering with too much.

Changes:
We changed our plan back to the original plan of using pyrealsense2.

Posted on

Team Status Report 03/22

Risks:

The only risk we have is that the only way we can access the distance data is through a terminal command. We need to come up with a way to run that in parallel with the CV algorithm.

 

Changes:

We are no longer using pylibrealsense2 for our ML model and instead using open cv with a yolo model.

Posted on

Team Status Report 3/8

Risks:

We have yet to attempt connecting the Jetson and L515, so that is a potential risk we may face, but we will be trying to do that this week so that we have ample time to problem solve if it does not work initially.

Changes:

The only change we have made is a new power supply due to our new power calculations. We did not realize that our computer vision would require our Jetson to be in Super Mode, which requires an additional 10W from what we had originally planned for. But we have found a new power source that supplies our required 5V, 6A.

A was written by Maya, B was written by Kaya and C was written by Cynthia.

Part A: Our cane addresses a global need for increased accessibility and independence for individuals with visual impairments. Around the world, millions of visually impaired people face mobility challenges that hinder their ability to safely navigate unfamiliar environments. The need for better mobility tools spans urban areas, rural villages, and developing areas, meaning it is not limited to any one country or region. Our design considers adaptability to different terrains and cultures, ensuring the cane can be valuable in settings from crowded malls to personal homes. By enhancing mobility and safety for people with visual impairments on a global scale, the product contributes to broader goals of accessibility, inclusivity, and equal opportunity.

Part B: Our cane addresses different cultures having varying perceptions of disability, independence, and accessibility. In communities with strong traditions of communal living, the single technology-advanced cane encourages seamless integration into these communities by drawing less attention and allowing users to maintain their independence.  Additionally, the haptic feedback system will allow for users to integrate seamlessly by drawing less attention by producing no noise from the device. By considering these cultural factors, our solution will allow for greater acceptance and integration into various societies.

Part C: We designed CurbAlert to take into consideration environmental factors, such as disturbing the environment around the user and interacting with the environment. Specifically, the feedback mechanism (haptic feedback) was chosen to notify only the user without creating extra noise or light or disturbing the surrounding environment or people. Additionally, our object detection algorithm is designed to detect hazards without physically interacting with the user’s environment and without having to be in contact with anything besides the ground and the user’s hand. Additionally, our prototype will be robust and rechargeable, making the product have no additional waste and making it so that a user will only need one of our prototype. By being considerate of the surrounding environment, CurbAlert is eco-friendly.

Posted on

Team Status Report 2/22

Risks:

Our most prominent risks right now are setting up the RealSense SDK, and troubleshooting any connection or compatibility issues that we may have with the Jetson.

Changes:

We initially had Maya and Kaya working together for most of the hardware components, but we are going to have Kaya and Cynthia work on more of the Computer Vision together as we changed our implementation to use a more challenging algorithm, and Maya will continue working on the hardware components. We are in a better spot with the Jetson than the RealSense and we are realizing that object detection is likely going to take longer than we planned, so we are giving that aspect more attention because many other aspects are reliant on the object detection being completed.

 

Posted on

Team Status Report 2/15

Risks:

Only risk would be if the software libraries we choose are not compatible with all of our devices.

Changes:

No changes in the plan yet. We plan on starting the initialization of our technical devices this week.

 

A was written by Cynthia, B was written by Maya, and C was written by Kaya.

A: With regards to public health, CurbAlert can improve the mental well-being of our users by increasing their confidence and independence with navigation, along with reducing the stress related to mobility challenges when both support and a white cane is needed.  The safety of our disabled users will also be improved with CurbAlert, since its main purpose is to prevent falls and collisions by detection obstacles and providing feedback with enough time to take action.  So, the product will both provide support to help keep injured or elderly individuals from falling and warning and feedback to prevent collisions and other injuries with objects, walls, or stairs.  By being a practical, everyday tool that provides independence and accessibility, our project improves overall welfare, ensuring that individuals with mobility impairments can navigate more freely and safely.

B: Our inspiration for this project was a family friend of mine that was recently injured, and has to walk with a walking cane, but also has to walk with a blind cane. She was expressing to me how difficult it was for her to live a normal life because she can’t get around very well at all. After talking to my group about this project, I decided to call and get her opinion on possible design choices and what the most important features were for her. She said she wants the ability to navigate safely in unfamiliar environments without feeling overwhelmed or dependent on others for guidance. We believe our cane will be a form of advocacy for individuals who feel that they have lost their independence or ability to have any form of social life because of the limitations that 2 canes provide. We also believe that our cane can provide blind people with more workplace accessibility, and more opportunities for employment.

C.  Economically, most of the devices we are using are recycled devices from last semester. These recycled deices include the F515 Camera and the Jetson Nano. After these devices, we chose our cane based off of affordability and usability as we choose the cheapest cane that matches our needs. This will allow us to sell the cane at an affordable price. For production/distribution, we would plan on making these canes in bulk such that we could lower the price of these canes. Our main goal is to have our cane be accessible to people of any income.

Posted on

Team Status Report for 2/8

This week, our team presented our first proposal, conducted additional research, and wrote a few requests for the equipment. Currently, the only risks that could jeopardize our project success are if we picked a type of Jetson that can’t configure properly later with our camera or if our power requirements are too high for the planned battery setup. We are managing the risks by ensuring we have backup equipment planned, including alternative options for the camera, sensors, power supply, and microcontroller. An updated schedule will be we will have to add an additional week just for finding and configuring any new equipment.