| --- |
| license: agpl-3.0 |
| tags: |
| - reservoir-computing |
| - echo-state-networks |
| - connectomics |
| - drone-control |
| - robotics |
| - pybullet |
| - neuroscience |
| metrics: |
| - rmse |
| --- |
| |
| # Fly Connectome Echo State Network for Drone Control |
|
|
| This repository contains research and simulation code that utilizes biological neural connectivity data (the connectome of the *Drosophila melanogaster* fruit fly) as the reservoir inside an **Echo State Network (ESN)** to perform autonomous drone flight control. |
|
|
| ## Project Overview |
|
|
| * **Biological Reservoir**: The network reservoir is built from the synaptic connectivity graph of the fly brain. We scale the spectral radius of the graph below `1.0` to guarantee the Echo State Property and stabilize dynamics. |
| * **Drone Control Task**: The ESN outputs 4D control signals (target velocities: $v_x$, $v_y$, $v_z$, and yaw rate) from a 12D drone state vector. |
| * **Simulation Environment**: Real-time evaluation is conducted using `gym-pybullet-drones`, a physics engine simulating ground effect, aerodynamic drag, and rotor downwash. |
| |
| ## Directory Structure |
| |
| ```text |
| flydrone-esn/ |
| │ |
| ├── LICENSE # AGPL 3.0 license file |
| ├── README.md # English documentation (with HF YAML front matter) |
| ├── README.txt # Detailed Turkish documentation |
| │ |
| └── src/ # Code files |
| ├── utils.py # Core mathematics and ESN reservoir helpers |
| ├── database_interaction.ipynb # CAVE API client for retrieving connectome synapses |
| ├── drone_realtime_simulation.py # Script to run the trained model in PyBullet and log video |
| ├── classes_by_cell_type.csv # Neuron cell classifications |
| ├── W_drone_components.pkl # Pre-trained ESN drone controller weights |
| └── networks_graphs/ # Connectome .graphml data files |
| ``` |
| |
| ## Setup and Quick Start |
|
|
| ### 1. Install Dependencies |
| Make sure you have python 3.10 installed, then run: |
| ```bash |
| pip install -r requirements.txt |
| ``` |
|
|
| ### 2. Run the Real-time Simulation |
| To run the pre-trained ESN-controlled drone in the PyBullet simulator with a graphical interface, run: |
| ```bash |
| python src/drone_realtime_simulation.py |
| ``` |
| This runs the simulation and logs third-person and first-person camera flight recordings to `drone_third_person.mp4` and `drone_first_person.mp4` in your directory. |
|
|
