Abstract: The research on multi-sensor fusion simultaneous localization and mapping (SLAM) is crucial for improving the reliability of autonomous vehicles. Multi-sensor fusion technology can help unmanned vehicles better identify environmental information, plan routes, and navigate and position, achieving more reliable and precise autonomous driving functions. Based on an unmanned car platform, this paper starts from the perspective of fusing visual sensors and lidar for map building and positioning, and studies the test results and characteristics of multi-sensor fusion map building and navigation positioning to propose suggestions and methods for improving the reliability of autonomous vehicle operation. Through testing, using visual sensor and lidar data fusion for map building and localization can effectively enhance the accuracy and reliability of autonomous vehicles in stereoscopic collision avoidance scenarios.

Key words: sensor fusion; simultaneous localization and mapping; unmanned vehicles; reliability

摘要： 多传感器融合同步定位和地图绘制（SLAM）技术对于提高自动驾驶车辆的可靠性至 关重要。多传感器融合技术能帮助无人驾驶车辆更好地识别环境信息、做好路径规划和导航 定位，实现更可靠和精确的自动驾驶功能。文章以无人小车为平台，分别从视觉传感器和激 光雷达融合建图定位的角度出发，通过研究多传感器融合建图导航定位的对比测试结果与特 性，提出可以提升自动驾驶车辆建图定位可靠性的建议和方法。通过测试，使用视觉传感器 和激光雷达数据融合进行建图和定位，可以在立体防撞应用场景有效提升自动驾驶车辆的准 确性和可靠性。

关键词: 传感器融合；同步定位和地图绘制；无人小车；可靠性