🍔 🚗 🛎️ 📶 After months of hard work, I published my new proof-of-concept research project on developing an AI-assisted drive-through restaurant establishment from the ground up, which offers a full-fledged drive-through kiosk, an automatic H-Bot-inspired food delivery system, and a restaurant web application utilizing LLMs to generate user-specific menus/deals.
According to the features I envisioned, I worked on these tasks while developing my project.
🤖 Preliminary Tasks
✅ Establishing Ollama on LattePanda Mu and installing distinct open-source LLMs (large language models).
✅ Optimizing, fine-tuning, and testing the available LLMs to pinpoint the most suitable ones for user-specific menu/deal generation.
✅ Establishing the LoRaWAN data transfer procedure between the kiosk customer endpoint and The Things Network via the dedicated LoRaWAN gateway.
✅ Installing the PHP-MQTT client on LattePanda Mu to enable the restaurant web application to obtain LoRa-transmitted data packets from The Things Network.
✅ Enabling the web application to present the latest LoRa transmission logs and the current order status automatically.
✅ Prototyping and designing the kiosk customer endpoint PCB.
✅ Designing assembly parts for the kiosk customer endpoint and the vehicle platform.
✅ Designing assembly parts and AprilTag signs for the food prep stations.
✅ Prototyping and designing the food delivery system Flex PCB with stiffeners.
✅ Designing assembly and mechanical parts for the automatic food delivery system inspired by the H-Bot kinematic structure.
✅ Building a FOMO object detection model with Edge Impulse for recognizing the registered customer vehicles.
✅ Building a FOMO object detection model with Edge Impulse for identifying individual food prep stations by their assigned AprilTag signs.
After completing the mentioned tasks and rigorously examining various LLMs for user-specific menu/deal generation, I decided to enable these models on the restaurant web application to provide a wide range of options:
➡️ deepseek-r1:8b
➡️ deepseek-r1:7b
➡️ deepseek-r1:1.5b
➡️ gemma3:4b
➡️ gemma3:1b
➡️ llama3.2:3b
➡️ qwen3:4b
➡️ phi4-mini
By referring to the following
@Hacksterio tutorial, you can inspect the in-depth feature, design, and code explanations with the challenges I faced during the overall development process.
🤖 ➡️
hackster.io/kutluhan-aktar/a…
@EdgeImpulse @dfrobotcn @Elecrow1 @Raspberry_Pi @arduino @ollama @LattePandaCN @thethingsntwrk
#LLM #3DPrinting #AI #IoT #PCB #LoRa #MQTT #TTN #LoRaWAN #LattePanda #Foodservice #restaurant #Kiosk #Ollama #largelanguagemodel #thethingsstack #research #programming
Note: I printed all of the parts and components I designed with my Bambu Lab A1 Combo.
@BambulabGlobal #BambuLetsMakeIt