Data Generation Using Simulation Technology to Improve Perception Mechanism of Autonomous Vehicles

Abstract

Recent advancements in computer graphics technology allow more realistic rendering of car driving environments. They have enabled self-driving car simulators such as DeepGTA-V and CARLA (Car Learning to Act) to generate large amounts of synthetic data that can complement the existing real-world dataset in training autonomous car perception. Furthermore, since self-driving car simulators allow full control of the environments, they can generate dangerous driving scenarios that the real-world dataset lacks such as bad weather and accident scenarios. In this paper, we will demonstrate the effectiveness of combining data gathered from the real-world with data generated in simulated world to train perception system on object detection and localization task. We will also propose a multi-level deep learning perception framework that aims to emulate a human learning experience in which series of tasks from simple to more difficult ones are learnt in a certain domain. The autonomous car perceptron can learn from easy-to-drive scenarios to more challenging ones customized by simulation software.