Real-Time Self-Driving Car Navigation using DNN - Test model in lane keeping task after optimizing
In this project, a monocular vision-based self-driving car prototype using Deep Neural Network on Raspberry Pi is proposed.
The technical contributions of this work are three-fold. First, the CNN model parameters were trained by using data collected from a vehicle platform built with a 1/10 scale RC car, Raspberry Pi 3 Model B computer, and front-facing camera.
The training data were road images paired with the time-synchronized steering angle generated by manually driving.
Second, the stored data is then transferred to a desktop computer and used for training the model to autonomously navigate the car.
Finally, road tests the model on Raspberry to drive itself in the outdoor environment around oval-shaped and 8-shaped with traffic sign lined track.
Link to the Real-Time Self-Driving Car Navigation using Deep Neural Network Project:
https://sites.google.com/view/truongd...