Co-Robotic Cane: A New Robotic Navigation Aid for the Visually Impaired.
Co-Robotic Cane: A New Robotic Navigation Aid for the Visually Impaired.
复制标题
协作机器人拐杖：一种针对视障人士的新型机器人导航辅助设备。
DOI：
10.1109/msmc.2015.2501167
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
Wu,Wei
中科院分区：
文献类型：
--
作者：
Ye,Cang;Hong,Soonhac;Qian,Xiangfei;Wu,Wei
本文提出了一种新型的机器人导航辅助装置——协同机器人手杖（CRC）。CRC使用一个三维（3-D）相机在未知的室内环境中进行姿态估计和物体识别。六自由度位姿估计方法通过自运动估计法和迭代最近点算法确定CRC的位姿变化，并通过位姿图优化算法减小位姿积分误差。姿态估计方法不需要对环境有任何先验知识。物体识别方法通过基于高斯混合模型（GMM）的模式识别方法检测楼梯、门道等室内结构和桌子、电脑显示器等物体。一些结构/物体（例如楼梯）可以用作导航路径点，而另一些则可以用作避障。CRC可以在机器人手杖（主动）模式或白手杖（被动）模式下使用。在主动模式下，它通过控制自己进入所需的行进方向来引导用户，而在被动模式下，它就像一个计算机视觉增强的白手杖。CRC是一个协作机器人。它可以检测人的意图，并根据意图自动选择合适的模式。
This article presents a new robotic navigation aid (RNA) called a co-robotic cane (CRC). The CRC uses a three-dimensional (3-D) camera for both pose estimation and object recognition in an unknown indoor environment. The six-degrees-of-freedom (6-DOF) pose estimation method determines the CRC's pose change by an egomotion estimation method and the iterative closest point algorithm and reduces the pose integration error by a pose graph optimization algorithm. The pose estimation method does not require any prior knowledge of the environment. The object recognition method detects indoor structures, such as stairways and doorways, and objects, such as tables and computer monitors, by a Gaussian mixture model (GMM)-based pattern-recognition method. Some structures/objects (e.g., stairways) can be used as navigational waypoints and others for obstacle avoidance. The CRC can be used in either robot cane (active) mode or white cane (passive) mode. In the active mode, it guides the user by steering itself into the desired direction of travel, while in the passive mode it functions as a computer-visionenhanced white cane. The CRC is a co-robot. It can detect human intent and use the intent to select a suitable mode automatically.