Back to All
Project

AutoChef

A Cutting-Edge Smart Device Powered by Qualcomm® RB3 Gen 2 and AI to Track Food Inventory, Minimize Waste, and Optimize Meal Planning

AutoChef is a revolutionary smart device designed to seamlessly manage your food inventory. It sends timely notifications about expiration dates and suggests personalized recipes to help you minimize waste, optimize meal planning, and maximize savings. Utilizing the Qualcomm® RB3 Gen 2 development kit, an advanced edge device, AutoChef employs AI software trained to recognize and log food items. This ensures you are alerted when and how to prepare the foods you have stored. Additionally, the device integrates with your VR headset to provide real-time information, including camera streams and sensor data, enhancing your culinary experience.

UX/XR Demo of AutoChef_1.
UX/XR Demo of AutoChef_1.
UX/XR Demo of AutoChef_2
UX/XR Demo of AutoChef_2.
Camera stream from Device with Qualcomm® technology
Camera stream from Device with Qualcomm® technology
Computer vision example of our model
Computer vision example of our model

Objective

Food waste is a significant but frequently underestimated issue, with one-third of all food going uneaten in the United States . This not only has a tremendous environmental impact but also causes enormous financial loss—the average American household loses nearly $1,500 in food waste each year. Given the scope of this problem, we were inspired to create a solution that not only saves people money but also contributes to a more sustainable food supply.

 

Our goal is to drastically reduce food waste at the household level by providing a smart, user-friendly solution. We envision a device that monitors food in refrigerators and pantries, tracks expiration dates, and sends timely notifications to users. To make food management even easier, the device will offer guided recipes based on available ingredients, helping users make the most of what they already have. By implementing this system, we aim to empower individuals to make informed food choices, reduce waste, save money, and contribute to a more sustainable planet.

 

Tools

Part Name Description / Link to purchase
Qualcomm RB3 Gen 2 Dev Kit-Vision Kit, QCS6490 Qualcomm® development kit with Qualcomm® QIRP SDK for on board processing and camera Streaming
Meta Quest 3 Device FVR Headset from Meta

 

Source Code

Description Link
Model Dataset with an optimization to use specific YOLO versions https://universe.roboflow.com/freshness-detection-vwn1a/freshness-detection-rhrze/model/3
Qualcomm model used as a base layer for model distillation in creation of our model https://aihub.qualcomm.com/models/yolov8_det_quantized?chipsets=QCS6490+%28Proxy%29
Qualcomm QIRP Camera Demo Example https://docs.qualcomm.com/bundle/publicresource/topics/80-65220-2/qrb-ros-camera_5_2_5.html?product=1601111740013886
Unity ROS Plugin https://github.com/Unity-Technologies/ROS-TCP-Endpoint
Qualcomm QIRP SDK https://www.qualcomm.com/developer/software/qualcomm-intelligent-robotics-product-sdk
ShapesXR Space https://shapes.app/space/view/1bebc65a-956d-4545-9019-38146edb958b/23s2d51a

 

Additional Resources

Resource Title Link
Presentation https://docs.google.com/presentation/d/1i7o-s_hT7I1B-ugdGHgYZIf2y6VPSsXrpXbTsnat9IQ/edit?usp=sharing
Devpost https://devpost.com/software/autochef-3r1ezc
Attribute sources https://www.usda.gov/about-food/food-safety/food-loss-and-waste
http://usda.gov/foodlossandwaste/consumers

 

Build / Assembly Instructions

1. Block Diagram

Qualcomm-image

2. Connect to the Qualcomm RB3 Gen2 dev kit using adb from the host system using usb

adb devices
adb shell

3. Use nmcli to connect to the wifi

nmcli dev wifi connect <WiFi-SSID> password <WiFi-password>

4. Source the qirp-setup.sh

source /usr/share/qirp-setup.sh

5. Launch the camera node

ros2 launch qrb_ros_camera qrb_ros_camera_launch.py

6. Set the same domain name for the host and the dev kit

export ros_domain_id = 0

Note: On the host system you should have access to the topics from the Qualcomm RB3 Gen2 dev kit if not check the firewall settings of the host system.
 

7. Setup the ROS TCP Connector on the host system and Unity
 

8. Provide the address and necessary settings and enter the ip address of the host system

Qualcomm-image

9. Create custom ROS publishers and subscribers to communicate with the Qualcomm RB3 Gen2 dev kit

10. Create the build for android and deploy on the VR headset
 

Usage Instructions

1. Autochef service technicians can provide seamless installation.

2. This project is designed to run autonomously so no work will be done for the end user

3. UX App displaying food data in the fridge

Qualcomm-image

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries ("Qualcomm"). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.

Project Authors
Isaiah WilliamsUndergraduate Cybersecurity Student
Mayank ChadhaResearch Assistant
Akhil AtluriUX Designer
Ash ShahAR Prototype Engineer
Qualcomm relentlessly innovates to deliver intelligent computing everywhere, helping the world tackle some of its most important challenges. Our leading-edge AI, high performance, low-power computing, and unrivaled connectivity deliver proven solutions that transform major industries. At Qualcomm, we are engineering human progress.

Stay connected

Get the latest Qualcomm and industry information delivered to your inbox.

Subscribe
Manage your subscription

© Qualcomm Technologies, Inc. and/or its affiliated companies.

Snapdragon and Qualcomm branded products are products of Qualcomm Technologies, Inc. and/or its subsidiaries. Qualcomm patented technologies are licensed by Qualcomm Incorporated.

Note: Certain services and materials may require you to accept additional terms and conditions before accessing or using those items.

References to "Qualcomm" may mean Qualcomm Incorporated, or subsidiaries or business units within the Qualcomm corporate structure, as applicable.

Qualcomm Incorporated includes our licensing business, QTL, and the vast majority of our patent portfolio. Qualcomm Technologies, Inc., a subsidiary of Qualcomm Incorporated, operates, along with its subsidiaries, substantially all of our engineering, research and development functions, and substantially all of our products and services businesses, including our QCT semiconductor business.

Materials that are as of a specific date, including but not limited to press releases, presentations, blog posts and webcasts, may have been superseded by subsequent events or disclosures.

Nothing in these materials is an offer to sell or license any of the services or materials referenced herein.