Toward a Full-Stack Co-Simulation Platform for Testing of Automated Driving Systems

2025-07-09

AI Summary

Existing simulation toolchains struggle to simultaneously achieve automated scenario generation and end-to-end closed-loop validation of advanced autonomous driving functions. To address this, this paper proposes a full-stack co-simulation platform that automatically constructs diverse, realistic test scenarios driven by real-world traffic data. The platform integrates CarMaker (for high-fidelity vehicle dynamics), ROS (for middleware communication), and Baidu Apollo (for autonomous driving perception, planning, and control algorithms) into a unified, closed-loop simulation environment. Its key innovation lies in the seamless, end-to-end integration—from data-driven scenario generation to multi-framework co-simulation—overcoming the traditional trade-off between scenario diversity and system-level closed-loop verification. Experimental evaluation demonstrates that the platform significantly enhances automation and engineering practicality in virtual testing, enabling rapid iteration and robust validation of L4-level autonomous driving systems under complex, realistic traffic scenarios.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Virtual testing has emerged as an effective approach to accelerate the deployment of automated driving systems. Nevertheless, existing simulation toolchains encounter difficulties in integrating rapid, automated scenario generation with simulation environments supporting advanced automated driving capabilities. To address this limitation, a full-stack toolchain is presented, enabling automatic scenario generation from real-world datasets and efficient validation through a co-simulation platform based on CarMaker, ROS, and Apollo. The simulation results demonstrate the effectiveness of the proposed toolchain. A demonstration video showcasing the toolchain is available at the provided link: https://youtu.be/taJw_-CmSiY.

Problem

• Integrating automated scenario generation with simulation environments
• Validating automated driving systems efficiently
• Developing a full-stack co-simulation platform

Innovation

• Full-stack toolchain for automated scenario generation
• Co-simulation platform integrating CarMaker, ROS, Apollo
• Real-world dataset-driven validation approach