Data generation using simulation technology to improve perception mechanism of autonomous vehicles

TL;DR

This paper explores how advanced simulation technology can generate synthetic data to enhance perception systems in autonomous vehicles, especially for dangerous or rare scenarios, by combining real and simulated data in a multi-level learning framework.

Contribution

It introduces a novel multi-level deep learning perception framework that learns from simple to complex scenarios using both real and simulated data.

Findings

Synthetic data improves object detection accuracy.

Simulated dangerous scenarios enhance system robustness.

Combined training outperforms real-only datasets.

Abstract

Recent advancements in computer graphics technology allow more realistic ren-dering 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 environment, 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 the simulated world to train perception systems 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 a series of tasks from the simple to more difficult ones are learned in a certain domain. The autonomous car perceptron can learn from easy-to-drive scenarios to more challenging ones customized by simulation software.