AutoETS2/README.md

# AutoETS2

A ADAS(Advanced Driver Assistance System) for Euro Truck Simulator 2 (or American Truck Simulator) with Deep Learning and Automation Algorithms

## Plan

- [ ] LCC(Lane Centering Control) + LDW(Lane Departure Warning) + ALC(Auto Lane Change)
- [ ] TSR(Traffic Signs Recognition) + TJA(Traffic Jam Assistant)
- [ ] LCW(Lane Changing Warning) + FCW(Forward Collison Warning)
- [ ] NOA(Navigate on Autopilot)

## Modules 

1. Drivable Space Detection + Lane Detection + Object Detection (Perception)
3. Automatic control system + Decision system (Behaviour)

## Datasets 

1. [BDD100K](https://doc.bdd100k.com/) - A diverse driving dataset for heterogeneous multitask learning 
    - Multi-object Detection 
    - Lane Detection
    - Drivable Area Segmentation
2. [ETS2SCDataset](https://www.kaggle.com/datasets/vjekoslavdiklic/ets2sc) - Euro Truck Simulator 2 Captured Screen and Input
    - This dataset contains recorded screen of Euro Truck Simulator 2 and paired input from Steering wheel controller (Thrustmaster Ff430).
    - Dataset contains 323894 frames captured at 25fps.
    - Each frame is paired with steering wheel controller input values at that moment
    - Using [Europilot](https://github.com/marsauto/europilot)

Data Directory Structure: 

```
 (BDD100k dataset)
├── image
│   └── 100k
│       ├── test
│       ├── train
│       └── val
└── label
    ├── det_20
    ├── drivable
    │   ├── colormaps
    │   │   ├── train
    │   │   └── val
    │   ├── masks
    │   │   ├── train
    │   │   └── val
    │   ├── polygons
    │   └── rles
    └── lane
        ├── colormaps
        │   ├── train
        │   └── val
        ├── masks
        │   ├── train
        │   └── val
        └── polygons

```

![example.png](src/perception/sample.png)