Autonomous Car

Creating an automatic driving system entirely controlled by a Neural Neural network using a single RGB camera.

Project Summary

Research, Hypothesis, and Results

• Research Question: Can adversarial defense training methods improve the neural network’s generalization skills to unseen lighting conditions?
• Hypothesis: The CNN models trained with adversarial machine learning defense methods will perform better in unseen lighting conditions than CNN models trained with standard procedures.
• Results: The CNN models trained with adversarial machine learning defense methods did perform better in never-seen-before lighting conditions than CNN models trained with standard procedures. The models M-TS and M-TL, trained with standard methods, failed to generalize to the unseen higher lighting (H), having several collisions against the wall. On the other hand, the models trained with adversarial methods performed well in the unseen higher lighting (H), completing two laps without collisions.
• This project received the highest distinction and was elected the second best project of the year by Tartu University.
• The model won the second place in the Delta X autonomous driving competition.

Cloning and Forking

git clone https://github.com/mikecamara/adversarial-machine-learning-attacks.git