组合导航系统工程化及L3级自动驾驶汽车批量应用验证数据集
收藏资源简介：
本数据集数据来源于国家重点研发计划项目“汽车级高精度组合导航传感器系统开发及应用”（项目编号：2021YFB3202300）。针对组合导航系统低成本、高精度、高可靠的需求，定制自动化组装设备，建设组合导航传感器系统批量化柔性生产线，建立批量制造平台，实现惯性传感器和组合导航传感器系统系列化产品工程化。通过开发快速标定系统，对MEMS惯性传感器进行全温区标定，实现传感器零偏、标度的温度误差补偿及交叉耦合补偿等，形成宽温区多通道低成本快速标定测试平台。并且开展产品的加速环境应力测试、加速寿命模拟测试、封装组合完整性测试、设计提供芯片晶圆可靠性测试、电气特性确认测试、缺陷筛选测试和腔体封装完整性测试等车规认证试验。搭建一套比被测系统定位精度更高、稳定性更好、可靠性更高的真值系统作为评价基准，实现L3级自动驾驶汽车在不同道路状况下测试组合导航传感器系统定位数据。评价各种场景下组合导航系统的定位误差是否能够满足自动驾驶的要求，开展多场景实车道路测试，进行批量装车应用，数据集中主要记录了组合导航传感器系统实车测试的相关测试记录以及相应的批量制造工艺开发方法及步骤，数据量为57MB。
This dataset is sourced from the National Key R&D Program of China titled "Development and Application of Automotive-Grade High-Precision Integrated Navigation Sensor System" (Project No.: 2021YFB3202300). To address the requirements of low-cost, high-precision and high-reliability integrated navigation systems, customized automated assembly equipment was developed, a batch-oriented flexible production line for integrated navigation sensor systems was built, and a mass manufacturing platform was established to realize the engineering of serialized products for inertial sensors and integrated navigation sensor systems. By developing a rapid calibration system, full-temperature-range calibration was conducted for MEMS inertial sensors, achieving temperature error compensation and cross-coupling compensation for sensor bias and scale factor, and a wide-temperature-range, multi-channel low-cost rapid calibration and testing platform was constructed. Moreover, vehicle-specification certification tests were carried out for products, including accelerated environmental stress testing, accelerated life simulation testing, package assembly integrity testing, chip wafer reliability testing, electrical characteristic confirmation testing, defect screening testing and cavity package integrity testing. A truth reference system with higher positioning accuracy, better stability and higher reliability than the tested system was built as the evaluation benchmark, and positioning data of integrated navigation sensor systems tested on L3-level autonomous vehicles under different road conditions were collected. We evaluated whether the positioning error of the integrated navigation system could meet the requirements of autonomous driving in various scenarios, conducted real-vehicle road tests in multiple scenarios, and carried out batch vehicle-mounted applications. The dataset mainly records the relevant test records of real-vehicle tests for integrated navigation sensor systems, as well as the corresponding development methods and procedures for batch manufacturing processes, with a total data volume of 57 MB.
