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...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。展开更多
In this work,we propose an efficient multi-mesh adaptive finite element method for simulating the dendritic growth in two-and three-dimensions.The governing equations used are the phase field model,where the regularit...In this work,we propose an efficient multi-mesh adaptive finite element method for simulating the dendritic growth in two-and three-dimensions.The governing equations used are the phase field model,where the regularity behaviors of the relevant dependent variables,namely the thermal field function and the phase field function,can be very different.To enhance the computational efficiency,we approximate these variables on different h-adaptive meshes.The coupled terms in the system are calculated based on the implementation of the multi-mesh h-adaptive algorithm proposed by Li(J.Sci.Comput.,pp.321-341,24(2005)).It is illustrated numerically that the multi-mesh technique is useful in solving phase field models and can save storage and the CPU time significantly.展开更多
基金The project supported by the Science Foundation of Laboratory of Computational Physics,Science Foundation of China Academy of Engineering Physics,and National Natural Science Foundation of China under Grant Nos.10702010,10775018,10472052,and 10604010
文摘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。
基金Part of Hu’s research was carried out while visiting Hong Kong Baptist UniversityHis research was also supported by an National Basic Research Program of China under the grant 2005CB32170+2 种基金Li’s research was partially supported by the National Basic Research Programof China under the grant 2005CB321701Foundation forNational ExcellentDoc-toral Dissertation Award of China and the Joint Applied Mathematics Research Institute between Peking University and Hong Kong Baptist UniversityTang’s research was sup-ported by CERG Grants of Hong Kong Research Grant Council and FRG grants of Hong Kong Baptist University.
文摘In this work,we propose an efficient multi-mesh adaptive finite element method for simulating the dendritic growth in two-and three-dimensions.The governing equations used are the phase field model,where the regularity behaviors of the relevant dependent variables,namely the thermal field function and the phase field function,can be very different.To enhance the computational efficiency,we approximate these variables on different h-adaptive meshes.The coupled terms in the system are calculated based on the implementation of the multi-mesh h-adaptive algorithm proposed by Li(J.Sci.Comput.,pp.321-341,24(2005)).It is illustrated numerically that the multi-mesh technique is useful in solving phase field models and can save storage and the CPU time significantly.
