Readme and refactor

Author: fed12345

.gitignore

@@ -1,10 +1,5 @@
 myenv/
 __pycache__/
 output.mp4
-models/
-logs/ 
-videos/
-results/c_code/
-results/onnx/
-results/quantized/
+
 

README

@@ -1,25 +1,75 @@
 # G&C Network
 
-This project consists in training a feedfoward network using reinforcement learning to fly a drone through a set of gates. More information of this project can be found on the following scientific paper.
+This project consists in training a feedfoward network using reinforcement learning to fly a drone through a set of gates. For more information, consult the [Nano Drone Racing](https://github.com/fed12345/nano-drone-racing) repository.
 
 
 ## Description
+This is a repository to that create, trains and accelerates a nerual network, which handles the drone’s guidance and control functions. This network runs at an impressive rate of 167Hz on an STM32F405 processor, outputting attitude rates and thrust values for an attitude rate PID controller.
+
+The steps that need to be carried out are:
+1. Carry out system identification of the drone
+2. Train the decided architerue and train NN
+3. Evaluate NN
+4. Convert it to C code via [ONNX](https://github.com/onnx/onnx)
+5. Deploy it on any drone autopilot for example [bitcraze](https://github.com/bitcraze/crazyflie-firmware)(this is not included in this repo)
 
-An in-depth paragraph about your project and overview of use.
 
 ## Getting Started
 
 ### Dependencies
 
-- Describe any prerequisites, libraries, OS version, etc., needed before installing the program.
-- ex. Windows 10
+- [Docker](https://docs.docker.com/engine/install/) 
+- [Conda](https://www.anaconda.com/download) or Pip
 
 ### Installing
 
-- How/where to download your program
-- Any modifications needed to be made to files/folders
+1. **Clone the repository:**
+
+   ```bash
+   git clone https://github.com/fed12345/controlnet
+   cd controlnet
+   ```
+   
+
+2. **Set Up a Virtual Environment (recommended)**
+
+It’s a best practice to use a virtual environment to manage dependencies. To create a virtual environment, run the following command with conda installed:
+
+```bash
+conda create --name controlnet
+conda activate controlnet
+```
+
+3. **Intall Dependencies**
+
+With the environment active, install all necessary packages by running:
+
+```bash
+pip install -r requirements.txt
+```
+##  Executing Progam
+
+1. **Model Quadcopter**
+It is necessary to aquire some data on the dynamics on the drone, as we will model the droens response as a first over system in terms of roll, pitch, yaw and thrust. We desired states and measured stated. 
+
+We can then use the python modelling script to model the drone, the output will be a series of marticies which have to be inputted in the simulator:
+
+```bash
+model_quadcopter.py
+```
+
+2. **Training the Model**
+The training stage will save model in the 
+```bash
+train_godzilla.py
+```
+
+3. **Evaluate the model**
+
+```bash
+run_sim.py
+```
+
+
 
-### Executing program
 
-- How to run the program
-- Step-by-step bullets

crazyflie_dataset/example_8.csv crazyflie_dataset/crazyflie_flight.csv

@@ -1,5 +1,4 @@
 absl-py==1.4.0
-ale-py==0.7.4
 anyio==4.0.0
 appnope==0.1.3
 argon2-cffi==23.1.0
@@ -144,3 +143,4 @@ websocket-client==1.6.3
 Werkzeug==2.3.7
 widgetsnbextension==4.0.8
 zipp==3.16.2
+ale-py==0.7.4

evaluation/plot_log.py

@@ -151,9 +151,9 @@ def run():
 import importlib
 from quadcopter_animation import animation
 
-models_dir = 'models/PPO_INDI'
-log_dir = 'logs/PPO_INDI'
-video_log_dir = 'videos/PPO_INDI'
+models_dir = 'results/models/PPO_INDI'
+log_dir = 'resultslogs/PPO_INDI'
+video_log_dir = 'results/videos/PPO_INDI'
 
 if not os.path.exists(models_dir):
     os.makedirs(models_dir)
@@ -220,4 +220,4 @@ def train(model, test_env, log_name, n=1000):
         all_items = os.listdir(models_dir + '/' + log_name)
 
 
-#train(model, test_env, 'INDI_TEST2_with_rate_penalty')
+train(model, test_env, 'INDI_TEST2_with_rate_penalty')