| | --- |
| | license: mit |
| | library_name: keras |
| | tags: |
| | - autonomous-driving |
| | - end-to-end |
| | - imitation-learning |
| | - self-driving |
| | - udacity |
| | - vision |
| | - cnn |
| | - dave2 |
| | - nvidia |
| | datasets: |
| | - maxim-igenbergs/thesis-data |
| | --- |
| | # DAVE-2 End-to-End Driving Model |
| | Implementation of NVIDIA's DAVE-2 architecture trained on the Udacity self-driving car simulator for the bachelor's thesis: Dual-Axis Testing of Visual Robustness and Topological Generalization in Vision-based End-to-End Driving Models. |
| | ## Model Description |
| | DAVE-2 is the original end-to-end driving architecture proposed by NVIDIA in 2016. It learns to map raw camera images directly to steering and throttle commands through imitation learning. |
| | ### Architecture |
| | ``` |
| | Input: RGB Image (66 × 200 × 3) |
| | ↓ |
| | Conv2D(24, 5×5, stride=2) + ELU |
| | Conv2D(36, 5×5, stride=2) + ELU |
| | Conv2D(48, 5×5, stride=2) + ELU |
| | Conv2D(64, 3×3) + ELU |
| | Conv2D(64, 3×3) + ELU |
| | ↓ |
| | Flatten |
| | ↓ |
| | Dense(1164) + ELU |
| | Dense(100) + ELU |
| | Dense(50) + ELU |
| | Dense(10) + ELU |
| | ↓ |
| | Output: [steering, throttle] |
| | ``` |
| | ## Checkpoints |
| | | Map | Checkpoint | |
| | |-----|------------| |
| | | GenRoads | `genroads_20251028-145557/` | |
| | | Jungle | `jungle_20251209-175046/` | |
| | ### Files per Checkpoint |
| | - `best_model.h5`: Keras model weights |
| | - `meta.json`: Training configuration and hyperparameters |
| | - `history.csv`: Training/validation metrics per epoch |
| | - `loss_curve.png`: Visualization of training progress |
| | ## Citation |
| | ```bibtex |
| | @thesis{igenbergs2026dualaxis, |
| | title={Dual-Axis Testing of Visual Robustness and Topological Generalization in Vision-based End-to-End Driving Models}, |
| | author={Igenbergs, Maxim}, |
| | school={Technical University of Munich}, |
| | year={2026}, |
| | type={Bachelor's Thesis} |
| | } |
| | ``` |
| | ## Related |
| | - [DAVE-2-GRU Driving Model](https://huggingface.co/maxim-igenbergs/dave2-gru) |
| | - [ViT Driving Model](https://huggingface.co/maxim-igenbergs/vit) |
| | - [TCP Driving Model](https://huggingface.co/maxim-igenbergs/tcp-carla-repro) |
| | - [Training Data](https://huggingface.co/datasets/maxim-igenbergs/thesis-data) |
| | - [Evaluation Runs](https://huggingface.co/datasets/maxim-igenbergs/thesis-runs) |
