This paper introduces an innovative approach to enhance the state estimator for high-speed autonomous race cars, addressing challenges related to unreliable measurements, localization failures, and computing resource management. The proposed robust localization system utilizes a Bayesian-based probabilistic approach to evaluate multimodal measurements, ensuring the use of credible data for accurate and reliable localization, even in harsh racing conditions. To tackle potential localization failures during intense racing, we present a resilient navigation system. This system enables the race car to continue track-following by leveraging direct perception information in planning and execution, ensuring continuous performance despite localization disruptions. Efficient computing resource management is critical to avoid overload and system failure. We optimize computing resources using an efficient LiDAR-based state estimation method. Leveraging CUDA programming and GPU acceleration, we perform nearest points search and covariance computation efficiently, overcoming CPU bottlenecks. Real-world and simulation tests validate the system's performance and resilience. The proposed approach successfully recovers from failures, effectively preventing accidents and ensuring race car safety.

翻译：本文提出了一种创新方法，以增强高速自主竞速赛车的状态估计器，解决不可靠测量、定位失效及计算资源管理等方面的挑战。所提出的鲁棒定位系统采用基于贝叶斯的概率方法评估多模态测量数据，确保在恶劣竞速条件下使用可信数据进行精确可靠的定位。针对激烈比赛中可能出现的定位失效问题，我们构建了一个弹性导航系统。该系统通过在执行与规划过程中利用直接感知信息，使赛车能够持续进行赛道跟踪，即使定位中断也能保持性能。高效的计算资源管理对于避免过载与系统故障至关重要。我们通过一种高效的基于激光雷达的激光雷达状态估计方法优化计算资源。借助CUDA编程与GPU加速，我们高效执行最近点搜索与协方差计算，突破了CPU瓶颈。实际道路与仿真测试验证了该系统的性能与弹性。所提出的方法成功从失效中恢复，有效防止事故并确保赛车安全。