Deep Reinforcement Learning for Adverse Garage Scenario Generation

TL;DR

This paper introduces a deep reinforcement learning framework that automates the generation of 2D ground scripts for 3D scene construction in autonomous vehicle simulation testing, reducing manual effort.

Contribution

It presents a novel deep reinforcement learning-based method to automatically generate scene scripts, streamlining the creation of complex 3D simulation environments for autonomous driving.

Findings

Successfully generates diverse 2D ground scripts

Enables automated construction of 3D scenes in Carla simulator

Reduces manual effort in scene setup

Abstract

Autonomous vehicles need to travel over 11 billion miles to ensure their safety. Therefore, the importance of simulation testing before real-world testing is self-evident. In recent years, the release of 3D simulators for autonomous driving, represented by Carla and CarSim, marks the transition of autonomous driving simulation testing environments from simple 2D overhead views to complex 3D models. During simulation testing, experimenters need to build static scenes and dynamic traffic flows, pedestrian flows, and other experimental elements to construct experimental scenarios. When building static scenes in 3D simulators, experimenters often need to manually construct 3D models, set parameters and attributes, which is time-consuming and labor-intensive. This thesis proposes an automated program generation framework. Based on deep reinforcement learning, this framework can generate different 2D ground script codes, on which 3D model files and map model files are built. The generated 3D ground scenes are displayed in the Carla simulator, where experimenters can use this scene for navigation algorithm simulation testing.