期刊文献+

融合IMU的RGBD-SLAM算法改进研究 被引量:7

Research of improved RGBD-SLAM algorithm fusing IMU
下载PDF
导出
摘要 Kinect采集的图像数据特征点稀少或缺失时,会导致RGBD-SLAM算法的定位和3D构图发生定位失效和极大构图误差,为此提出一种结合惯性传感器IMU、体感传感器Kinect以及机器人本身运动状态的改进定位算法。通过对姿态先比较再融合,利用IMU的测量数据对位移构建预估模型,利用Kinect位姿估计的结果构建观测模型,将机器人的运动指令和运动限制作为约束条件进行扩展卡尔曼滤波(extended Kalman filter,EKF)融合,改善机器人的定位效果。实验结果表明,该方法能够有效提高机器人的定位精度,改善RGB-D SLAM算法的构图效果。 Localization based on the RGBD-SLAM may fail and generate great mapping error when collected Kineet feature points of image data are rare or absent. To solve the problem, an improved localization algorithm was proposed based on the inenial sen- sor (IMU), the somatosensory sensor (Kinect) and the motion state of the robot itself. The comparison and fusion were done for attitudes, at the same time, the prediction model and the observation model were constructed using IMU measurement data and results of Kinect pose estimation for position respectively, the robot's movement and motion commands restrictions were taken as constraints to do the extended Kalman filter (extended Kalman filter, EKF) integration for robot localization and mapping. Experimental results show that the method can improve the localization accuracy of the robot and the effect of mapping based on the RGBD-SLAM algorithm.
作者 闵华松 杨杰
出处 《计算机工程与设计》 北大核心 2015年第1期120-126,共7页 Computer Engineering and Design
基金 国家自然科学基金项目(61175094)
关键词 惯性测量单元 KINECT 姿态解算 扩展卡尔曼滤波算法 同时定位与构图 inertial measurement unit Kinect attitude solution extended Kalman filter simultaneous localization and mapping
  • 相关文献

参考文献11

  • 1Henry P,Krainin M,Herbst E,et al.RGB-D mapping:Using Kinect-style depth cameras for dense 3Dmodeling of indoor environments[C]//International Journal of Robotics Research,2012,31(5):647-663.
  • 2Felix Endres,Jürgen Hess,Daniel Cremers,et al.An evaluation of the RGB-D SLAM system[C]//In Proc of the IEEE Int Conf on Robotics and Automation,2012.
  • 3Kerl C,Sturm J,Cremers D.Robust odometry estimation for RGB-D cameras[C]//In Proc of the IEEE Int Conf on Robotics and Automation,2013.
  • 4Audras C,Comport AI,Meilland M,et al.Real-time dense appearance-based SLAM for RGB-D sensors[C]//In Proc Australian Conf Robotics and Automation,2011.
  • 5Stuckler J,Behnke S.Model learning and real-time tracking using multi-resolution surfel maps[C]//In AAAI Conf on Artificial Intelligence,2012.
  • 6Bouvrie BD.Improving RGBD indoor mapping with IMU data[D].Holland:Delft University of Technology,2011.
  • 7Fredrik Hjelmare,Jonas Rangjs.Simultaneous localization and mapping using a Kinect in a sparse feature indoor environment[D].Sweden:Linkping University,2012.
  • 8Thibault Hervier,Silvere Bonnabel,Francois Goulette.Accurate 3D maps from depth images and motion sensors via nonlinear Kalman filtering[C]//In Proc of the IEEE/RSJ Int Conf on Intelligent Robots and Systems,2012.
  • 9Sparkfun Electronics.9 degrees of freedom-razor imu[EB/OL].https://www.sparkfun.com/products/10736,2014.
  • 10Starlino Electronics.DCM tutorial-An introduction to orientation kinematics[EB/OL].http://www.starlino.com/dcm_tutorial.html,2011.

同被引文献55

引证文献7

二级引证文献29

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部