Implementation of Re-Simulation-Based Integrated Analysis System to Evaluate and Improve Autonomous Driving Algorithms

Autonomous driving technology requires rigorous testing and validation of perception, decision-making, and control algorithms to ensure safety and reliability. Although existing simulators and testing tools play critical roles in algorithm evaluation, they struggle to satisfy the demands of complex, real-time systems. This study proposes a re-simulation-based integrated analysis system designed to overcome these challenges by providing advanced visualization, algorithm-testing, re-simulation, and data-handling capabilities. The proposed system features a comprehensive visualization module for real-time analysis of diverse sensor data and ego vehicle information, offering intuitive insights to researchers. Additionally, it includes a flexible algorithm-testing framework that abstracts simulator-specific dependencies, enabling seamless integration and evaluation of algorithms in various scenarios. The system also introduces robust re-simulation capabilities, enhancing algorithm validation using iterative testing based on real-world or simulated sensor data. To address the computational demands of high-frequency sensor data, the system employs optimized data-handling mechanisms based on shared memory, thereby significantly reducing latency and improving scalability. The proposed system overcomes critical challenges faced by existing alternatives by providing a robust, efficient, and scalable solution for testing and validating autonomous-driving algorithms, ultimately accelerating the development of safe and reliable autonomous vehicles.