EdgeNet: An End-to-End Deep Neural Network Pretrained with Synthetic Data for a Real-World Autonomous Driving Application

This paper presents a novel end-to-end architecture based on edge detection for autonomous driving. The architecture has been designed to bridge the domain gap between synthetic and real-world images for end-to-end autonomous driving applications and includes custom edge detection layers before the Efficient Net convolutional module. To train the architecture, RGB and depth images were used together with inertial data as inputs to predict the driving speed and steering wheel angle. To pretrain the architecture, a synthetic multimodal dataset for autonomous driving applications was created. The dataset includes driving data from 100 diverse weather and traffic scenarios, gathered from multiple sensors including cameras and an IMU as well as from vehicle control variables. The results show that including edge detection layers in the architecture improves performance for transfer learning when using synthetic and real-world data. In addition, pretraining with synthetic data reduces training time and enhances model performance when using real-world data.