Deep Reinforcement Learning for Adverse Garage Scenario Generation
This addresses the problem of inefficient scene creation for experimenters in autonomous driving simulation, though it is incremental as it automates an existing manual process.
The paper tackles the time-consuming manual construction of 3D static scenes in autonomous driving simulators by proposing an automated program generation framework using deep reinforcement learning, which generates 2D ground script codes to build 3D models and map files displayed in the Carla simulator for navigation algorithm testing.
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.