Wood Nathan A, Liu Tian Yu Tommy, Waugh Kevin, Zenati Marco A, Riviere Cameron N
The Robotics Institute, Carnegie Mellon University, Pittsburgh, Pennsylvania 15213, USA. fnwood@
Annu Int Conf IEEE Eng Med Biol Soc. 2012;2012:1413-6. doi: 10.1109/EMBC.2012.6346204.
This paper presents preliminary work toward localizing on a surface which undergoes periodic deformation, as an aspect of research on HeartLander, a miniature epicardial crawling robot. Using only position measurements from the robot, the aim of this work is to use the nonuniform movements of the heart as features to aid in localization. Using a particle filter, with motion and observation models which accurately model the robotic system, registration and localization parameters can be quickly and accurately identified. The presented framework is demonstrated in simulation on dynamic 2-D models which approximate the deformation of the surface of the heart.
本文介绍了在周期性变形表面上进行定位的初步工作，这是对微型心外膜爬行机器人HeartLander研究的一个方面。这项工作的目标是仅利用机器人的位置测量，将心脏的非均匀运动作为特征来辅助定位。使用粒子滤波器，通过能精确模拟机器人系统的运动和观测模型，可以快速准确地识别配准和定位参数。所提出的框架在动态二维模型的仿真中得到了验证，这些模型近似于心外膜表面的变形。
