GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow

TL;DR

GarchingSim tackles the high cost and limited coverage of real-world autonomous driving testing by providing a Unity-based, photorealistic simulator with a physics-grounded vehicle model and a configurable sensor suite. It offers dual communication backends (ROS2 and Socket.IO) for easy integration with existing stacks and supports distributed, multi-agent simulations. The framework enables synthetic data labeling, imitation learning validation, reinforcement learning data generation, and V2V/V2X scenarios, all within an open-source, plug-and-play environment. This platform lowers barriers for startups and academia to evaluate ML-based driving algorithms in diverse, realistic settings and facilitates sim-to-real research pipelines.

Abstract

Conducting real road testing for autonomous driving algorithms can be expensive and sometimes impractical, particularly for small startups and research institutes. Thus, simulation becomes an important method for evaluating these algorithms. However, the availability of free and open-source simulators is limited, and the installation and configuration process can be daunting for beginners and interdisciplinary researchers. We introduce an autonomous driving simulator with photorealistic scenes, meanwhile keeping a user-friendly workflow. The simulator is able to communicate with external algorithms through ROS2 or Socket.IO, making it compatible with existing software stacks. Furthermore, we implement a highly accurate vehicle dynamics model within the simulator to enhance the realism of the vehicle's physical effects. The simulator is able to serve various functions, including generating synthetic data and driving with machine learning-based algorithms. Moreover, we prioritize simplicity in the deployment process, ensuring that beginners find it approachable and user-friendly.

Figures (6)

• Figure 1: The framework of our autonomous driving simulator.
• Figure 2: Simulation environment under different weathers and real-world scene
• Figure 3: Waypoint-based traffic system
• Figure 4: RGB camera, semantic camera, and radar
• Figure 5: Automatic labeling