Real‐time moving object detection and removal from 3D pointcloud data for humanoid navigation in dense GPS‐denied environments
Real‐time moving object detection and removal from 3D pointcloud data for humanoid navigation in dense GPS‐denied environments
复制标题
实时移动物体检测并从 3D 点云数据中移除，以便在密集 GPS 拒绝的环境中实现人形导航
DOI：
10.1002/eng2.12275
复制
发表时间：
2020
影响因子：
2
通讯作者：
Dilip Kumar Pratihar
中科院分区：
文献类型：
--
作者：
Prabin Kumar Rath;A. Ramirez;Dilip Kumar Pratihar
机器人在动态受限的非结构化环境中的感知是一项具有挑战性的任务，因为周围环境发生了意想不到的变化。虽然3D感知传感器能够高精度地捕捉地形拓扑，但由于运动实体相对于机器人的运动导致采集的传感器数据之间的临时变化，导致环境的噪声映射。本文提出了一种能够从室内环境中采集的输入点云数据中检测并消除运动点群的实时三维感知过滤器。使用激光雷达和IMU传感器，该机制可以在动态和非结构化GPS拒绝的环境中帮助精确地生成3D点云地图。本文基于数据聚类、相对运动、点云变化检测和置信度跟踪等概念，提出了一种新的方法。这种方法的新颖性在于它能够检测集群内的运动，并提出了一种通用的跟踪方法来处理通常在室内环境中发现的对象的不一致运动。对于运动目标的检测，所提出的机制不需要关于目标实体的任何先验知识。针对点云数据的预处理问题，提出了一种基于体素网格协方差的地面去除方法。该方法在室内办公环境中的类人机器人上进行了实验，使用的是Velodyne VLP-16LiDAR和Intel T265 IMU。实验结果表明，该方法能有效地实现室内运动目标的实时检测。
Robot perception in dynamic confined unstructured environments is a challenging task due to unanticipated changes that take place in the surroundings. Although 3D perception sensors are able to capture terrain topology with high precision, the interim variations between collected sensor data that are caused due to the motion of moving entities with respect to the robot lead to noisy mappings of the environment. In this article, a real‐time 3D perception filter is presented that is capable of detecting and eliminating moving point clusters from the input pointcloud data collected in an indoor environment. Using LiDAR and IMU sensors the proposed mechanism can help in precise 3D pointcloud map generation in dynamic and unstructured GPS‐denied environments. In this article, a novel approach has been proposed based on the concepts of data clustering, relative motion, pointcloud change detection and confidence tracking. The novelty of this approach lies in its ability to detect within cluster movements and the proposal of a generic tracking method for handling inconsistent motion of objects typically found in indoor environments. For the detection of moving objects, the proposed mechanism does not require any prior knowledge about the target entity. For pointcloud preprocessing, a ground plane removal approach has been proposed based on voxel grid covariance along the axis normal to the ground. The approach was experimented on a humanoid robot in indoor office environments using Velodyne VLP‐16 LiDAR and Intel T265 IMU. The results show that the proposed approach is efficient in detecting indoor moving objects in real time.
影响因子：
7.8
作者：
Endres, Felix;Hess, Juergen;Burgard, Wolfram
通讯作者：
Burgard, Wolfram
影响因子：
9.2
作者：
Geiger, A.;Lenz, P.;Urtasun, R.
通讯作者：
Urtasun, R.