| Rao-Blackwellized滤波器实现机器人同时定位和地图创建 |
| |
| 引用本文： | 魏振华,厉茂海,胡黎明,罗荣华. Rao-Blackwellized滤波器实现机器人同时定位和地图创建[J]. 哈尔滨工业大学学报, 2008, 40(3): 401-406 |
| |
| 作者姓名： | 魏振华 厉茂海 胡黎明 罗荣华 |
| |
| 作者单位： | 哈尔滨工业大学计算机科学与技术学院,哈尔滨,150001;华北电力大学计算机科学与技术学院,北京,102206;哈尔滨工业大学计算机科学与技术学院,哈尔滨,150001;海军驻北京8359所军事代表室,北京,10039 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划) , 黑龙江省哈尔滨市科研项目 |
| |
| 摘 要： | 为了实现移动机器人仅依靠单目视觉和里程计创建可靠地图,本文提出了基于Rao-Blackwellized粒子滤波器的同时定位和地图创建方法.文中建立了鲁棒的运动模型和感知模型;通过有效的尺度不变特征变换方法提取环境特征,并采用基于KD-Tree的高维特征点最近邻快速搜索算法实现特征匹配;通过对匹配对的三维重建创建了密集的空间三维自然路标.实际实验表明本文方法能创建较高精度的地图.
|
| 关 键 词： | 移动机器人 同时定位和地图创建 Rao-Blaekwellized粒子滤波器 尺度不变特征变换 KD-Tree 最近邻搜索 |
| 文章编号： | 0367-6234(2008)03-0401-06 |
| 修稿时间： | 2006-03-07 |
Rao-blackwellized particle filters for robot simultaneous localization and mapping |
| |
| WEI Zhen-hua,LI Mao-hai,HU Li-ming,LUO Rong-hua. Rao-blackwellized particle filters for robot simultaneous localization and mapping[J]. Journal of Harbin Institute of Technology, 2008, 40(3): 401-406 |
| |
| Authors: | WEI Zhen-hua LI Mao-hai HU Li-ming LUO Rong-hua |
| |
| Affiliation: | 1(1.College of Computer Science and Technology,Harbin Institute of Technology,Harbin 150001,China;2.School of Computer Science and Technology,North China Electric Power University,Beijing 102206,China;3.Navy Delegate Room in the 8359 Institute of Beijing,Beijing 10039,China) |
| |
| Abstract: | For building the robust map of mobile robot only with monocular vision and odometer,simultaneous localization and mapping(SLAM) is implemented efficiently with the Rao-Blackwellized particle filters(RBPF).The robust motion model and observation model was constructed.Scale Invariant Feature Transform(SIFT) was used to extract image features served as the nature landmarks,and a fast nearest neighbor search algorithm for matching multi-dimensional features in a KD-Tree was presented to implement feature matching.The map representation was executed with dense 3D natural landmarks reconstructed with the matching pairs.Experiments on the real robot show that the proposed method is of high precision. |
| |
| Keywords: | mobile robot simultaneous localization and mapping Rao-Blackwellized particle filter scale invariant feature transform KD-Tree based nearest neighbor search |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
