Week #6

Week #6 #

  • Deployment: (Add deployment link if available)
  • API Docs: (Add API documentation link if available)
  • Design: (Add design documentation link if available)
  • Demo: (Add demo link if available)

Final deliverables #

Project overview #

Our project aims to create an autonomous drone system capable of semantic 3D reconstruction and high-fidelity mapping. This week, we enhanced our technical stack by integrating pg-vector, refining the webcam simulation for improved realism, and implemented the foundational version of an agentic AI system.

Features Implemented this Week: #

  • Integrated pg-vector to support vector storage and search functionalities.
  • Improved webcam simulation to enhance realism in Unity simulation.
  • Developed initial basic version of an Agentic AI Module for drone control and scene understanding.

Tech stack #

  • Unity 3D
  • Python (FastAPI, PyTorch)
  • PostgreSQL (pg-vector)
  • Docker and Docker Compose
  • WebSocket and RESTful APIs for communication

Setup instructions #

Clone the repository and follow the steps below:

git clone <repository-link>
cd <project-directory>
docker-compose up --build

Ensure Docker and Docker Compose are installed.

Presentation draft #

  • (Add a link to the presentation draft if available)

Weekly Commitments #

Individual Contributions #

  • Alexander & Ilvina

    • Improved Unity simulation realism by enhancing webcam simulation.
    • Started groundwork for Unity backend integration.

  • Nikita

    • Integrated initial version of the Agentic AI Module (basic agent functionality).

  • Mahmoud

    • Path Planning and Frontier-Based Exploration: In working condition.

Confirmation of the code’s operability #

We confirm that the code in the main branch:

  • Is in working condition.
  • Runs via docker-compose (as described in the README.md).