Category: Uncategorized

Work Accomplished:

This week, I was able to complete component and system testing for the device at Aldi’s. I confirmed that the device can be attached and sit securely onto the shopping cart handlebar and the barcode is accessible to the user. We tested the full integrated system by scanning items in the store and receiving real-time updates in the app.

Progress Status:

We are currently on track as per our schedule. Now, we are working on final documentation.

Next Week’s Goal:

• final poster, report, video demo

Progress:

• Made a trip to Aldi’s to test full pipeline and collect footage for demo video

• Successfully transitioned all component communication (profile processing, product scanning, meal recommendation, ingredient substitution) to MQTT broker

• Subsystems now fully decoupled and interact via MQTT publish/subscribe model.

• Ran extensive unit tests for each module

Next goals:

• Get ready for demo/demo video

 

Images:

Work Accomplished:

This week, I was able to make the hardware device completely portable and start up all scripts upon connection to the power bank. As soon as the rasberry pi starts up, it can run two scripts setting up the MQTT connection, and start sending scanned products to the mobile app. I also was able to configure the Rasberry Pi to automatically configure to hotspot, so it can start up immediately in store.

Progress Status:

I am currently on progress with our schedule. My main job now is testing the device at Aldi’s through the full pipeline of scanning a product and testing its product recognition accuracy. 

Next Week’s Goal:

• full integration testing

Progress:

• Built a semantic product matcher using sentence-transformers (all-MiniLM-L6-v2) to match ingredient names with Aldi product listings.

• Filtered grocery list recommendations based on cosine similarity thresholds to avoid irrelevant matches.

Goals:

• Add product ranking logic based on nutritional tags (e.g., high protein, low sugar).
• Expand allergen support to include nested ingredients (e.g. “mayo” contains eggs).

For this update, I built out the logic that takes a meal plan and turns it into a personalized grocery list with real Aldi product suggestions. If the user has any allergens, our system catches those and swaps the ingredients out with safe alternatives, pulling real options using Spoonacular and Aldi’s product data. I also connected everything through MQTT, so now the backend listens for meal plans, processes them with allergy-aware substitutions, and sends back a clean grocery draft for the user to review.

Progress:

• Implemented logic to analyze meal plan ingredient lists and cross-reference against user allergens.
• Integrated substitution logic with a mapping function to recommend safe alternatives when allergens are detected.
• Integrated API to fetch 1–3 real Aldi products for each ingredient.

Goals:

• Finalizing dynamic frontend integration to reflect real product recommendations.

• Begin auto-updating the bill as products are added (real-time tallying).

Work Accomplished:

This week, I finished attaching the portable power bank to the device, allowing for a constant power supply during a shopping experience. I also bought the shopping cart clip on, which I will pick up next week and attach to the device. I have been working on making the rasberry pi start up the barcode scanning script automatically and read in barcodes. However, I have ran into many obstacles with this task.

Progress Status:

Due to the obstacle with making the rasberry pi start reading barcode scans automatically, I am a bit behind on this particular aspect of the project. However, making the device portable is my last major task and I have contacted my TA to try new ways to achieve it. 

Next Week’s Goal:

• attach clip-on device
• fix rasberry pi barcode scanning issues
• test in-person

Interim Demo Presentation

Work Accomplished:

This week, I finished printing the 3D case that makes up the whole hardware system and attaches to the cart. In addition, I finished the connection between the USB barcode scanner, rasberry pi, and the front end mobile app updates. This finishes the basic functionality of scanning a product, retrieving its product details and displaying it on the mobile app.

Progress Status:

I am currently on track in our schedule. We adjusted our schedule based on design changes. My focus now is to make the device completely portable and able to attach to a shopping cart for our final user experience

Next Week’s Goal:

• Make UPC scanning work with remote ssh
• make device completely portable
• initial testing with aldi products

Risks & Management

• Risk: With multiple components (LangChain, Spoonacular, barcode scanning, MQTT) now functioning independently, the risk lies in delays or errors during integration of the full end-to-end workflow.
• Management: A system-level integration plan is being developed. Tasks have been divided to ensure frontend and backend components communicate seamlessly through MQTT, and fallback logs are in place to trace errors.

Design Changes & Justification:

• Reorganized backend into modular components for easier testing and debugging.

• Added a persistent product object structure for better real-time tracking and removal from cart UI.

Progress:

• 3D printed outer shell for device

• Completed LangChain + OpenAI integration for dietary-specific meal plan generation

• Developed object structure for in-store ingredient tracking and real-time tally

• Frontend tested receiving product data

Work Accomplished:

• Completed a modular backend design that outlines the full data flow, from user profile intake to product tracking and budgeting. The system now supports clear separation of concerns across user_profile, meal_planner, ingredient_substitutor, grocery_tracker, product_scanner, and mqtt_handler
  • Successfully integrated LangChain with the GPT-4 model to extract dietary preferences, allergens, and cultural requirements from user input and generate personalized meal plans
  • Wrote standalone test files for each backend component to ensure correctness and maintainability

Progress Status:

I am now on track with the backend development roadmap. The foundation is built and tested. Modules are independently working, with API integrations functional. Code is modular and testable.

Goals:

 

• Complete MQTT-to-frontend integration with real hardware input.

• Connect product substitution logic with real scanned products.