基于多传感器融合的系统自我定位与地图重建

System Self-localization and Map Reconstruction Based on Multi-sensor Fusion

在图优化框架的基础上,设计多传感器融合方案和有效的优化方法,提出一套具有鲁棒性的定位与建图(Simultaneous Localization and Mapping,SLAM)方案,能够有效应对室内外复杂环境。进一步发展激光-视觉后端建图融合方法,构建具备全新地图表达形式的点云网格化地图。同时使用低成本传感器,设计实现基于多传感器融合的高性能低成本背包扫描系统,整体完成在未知环境中的自我定位和稠密建图,且在低性能CPU设备上将长时间运动带来的每100 m的轨迹误差平均降低至厘米级。提出的基于多传感器融合方案,在精度、算力消耗上能够匹配现有主流方案,对获取各种环境条件下的系统准确定位结果和丰富的空间信息具有重要意义。

Based on the graph optimization framework,a multi-sensor fusion approach and an effective optimization method are designed,and a multi-sensor fusion Simultaneous Localization and Mapping(SLAM)scheme with robust localization effect is proposed,which can effectively deal with complex indoor and outdoor environments.The laser-vision back-end mapping fusion method is further developed to construct a point cloud grid map with a new form of map expression.At the same time,low-cost sensors are used to design and implement a high-performance low-cost backpack scanning system based on multi-sensor fusion,which can complete the self-localization and dense mapping in unknown environment as a whole,and reduce the track error per 100 meters caused by long-time movement to centimeter level on the low-performance CPU device.The multi-sensor fusion scheme proposed can match the existing mainstream schemes in terms of accuracy and computing power consumption,and is of great significance for obtaining accurate positioning results and rich spatial information of the system under various environmental conditions.