Deep Learning and Control Algorithms of Direct Perception for Autonomous Driving
This is an incremental improvement for autonomous driving simulation, focusing on highway scenarios in TORCS.
The authors tackled autonomous driving by modifying AlexNet and GoogLeNet CNNs to map images to perception indicators (e.g., heading angle, distances) and designing a controller for collision avoidance in the TORCS simulator, resulting in better training efficiency and driving stability compared to earlier methods.
Based on the direct perception paradigm of autonomous driving, we investigate and modify the CNNs (convolutional neural networks) AlexNet and GoogLeNet that map an input image to few perception indicators (heading angle, distances to preceding cars, and distance to road centerline) for estimating driving affordances in highway traffic. We also design a controller with these indicators and the short-range sensor information of TORCS (the open racing car simulator) for driving simulated cars to avoid collisions. We collect a set of images from a TORCS camera in various driving scenarios, train these CNNs using the dataset, test them in unseen traffics, and find that they perform better than earlier algorithms and controllers in terms of training efficiency and driving stability. Source code and data are available on our website.