v2.0.0: Official Python Implementation and Multi-Platform Support

📦 Release v2.0.0: Python Implementation & Cross-Platform Support
Tag version: v2.0.0 Release title: Python Implementation & Cross-Platform Support (D2OC)

Description
Following the initial MATLAB release, this version introduces the official Python implementation of the Density-Driven Optimal Control (D2OC) framework. This update enables researchers and engineers to integrate D2OC into modern AI and robotics pipelines more easily.

What's New in Python Implementation:
Core Logic: Full port of the Optimal Transport-based decentralized control.

Ease of Use: Single-file execution (D2OC_main.py) for simplified research integration.

Environment: Compatible with standard scientific Python stacks (NumPy, Matplotlib).

Cross-Platform: Ready for Linux, macOS, and Windows without proprietary software requirements.

Key Features (D2OC Framework):
Optimal Transport Control using Wasserstein distance.

Decentralized Weight Update logic for multi-agent coordination.

Quadrotor-inspired LTI Dynamics (8-state formulation).

Non-uniform Density Coverage for complex environment mapping.

Official Links:
📄 Paper (IEEE TSMC): https://doi.org/10.1109/TSMC.2025.3622075

📚 arXiv: https://arxiv.org/abs/2511.12756

🛸 Live Demo (Hugging Face): D2OC Space

Initial Release – MATLAB D2OC (Optimal Transport Control)

This is the first official release of the MATLAB implementation of
Density-Driven Optimal Control (D2OC), an Optimal Transport–based decentralized
multi-agent coverage control framework using Wasserstein distance.

Included:

• Main_D2OC.m
• Hamiltonian OT-based target computation
• Decentralized weight update logic
• Quadrotor-inspired LTI dynamics
• DF density maps
• Simulation configurations (Sim_rev60.mat)
• Parameter files

Paper:
IEEE Transactions on Systems, Man, and Cybernetics: Systems
DOI: https://doi.org/10.1109/TSMC.2025.3622075

GitHub Repository:
https://github.com/kooktaelee/D2OC