Multi-Sensor 6-DoF Localization For Aerial Robots In Complex GNSS-Denied Environments

Abstract

The need for robots autonomously navigating in more and more complex environments has motivated intense R&D efforts in making robot pose estimation more accurate and reliable. This paper presents a multi-sensor multi-hypothesis method for robust 6-DoF localization in complex environments. Robustness and accuracy requirements are addressed as follows. First, camera and LIDAR features are seamlessly integrated in the same statistical framework, benefiting from their synergies and providing robustness in scenarios with low or varying densities of LIDAR and visual features. Second, a multi-hypothesis approach is adopted to cope with scenario symmetries. The method has been carefully designed to operate in real time using feature and hypothesis filtering and efficient hypothesis refinement, and has been coded in a multi-core implementation. The proposed method has been extensively validated for closedloop aerial robot navigation in different urban and industrial scenarios and has shown advantages over well-known singlesensor techniques.

Online Detection and Tracking of Pipes During UAV Flight in Industrial Environments

“…It refines the parameters of the pipe (location and orientation) following a recursive Prediction-Update approach. In the Prediction stage, the robot odometry -computed from 3D LiDaR scans as in [12]-is used to predict the pipe position and orientation in the point cloud. In the Update stage the Random Sample Consensus (RANSAC) algorithm is used for computing the pipe parameters that best fit within the point cloud.…”

Past, Present, and Future of Aerial Robotic Manipulators

“…Finally, at small distances, stereo cameras can be applied and fuse the point clouds resulting from the camera with those provided by the 3-D LIDAR. In [38], a multisensor six-DoFs localization method is applied. An iterative closest point (ICP) algorithm extended to consider 3-D-3-D matchings between LIDAR (3-D distances) or cameras (distances in the SURF space) is used in the prediction stage.…”

“…The current third generation of aerial manipulators includes several advanced features: operations in both outdoor/indoor environments [28], fully actuated platforms [29]- [32], multiple arms [33]- [36], GNSS free navigation capabilities, on-board SLAM [37], [38], on-board perception without markers [39], [40], off-board real-time planning with control awareness [41], [42], and on-board reactivity and planning. Applications include structure assembly, contact-based inspection in refineries (pipes and tanks), and bridges [43], [44].…”

Towards UAS Surveillance using Event Cameras

“…LIDAR sensors are also very widely used mainly as navigation sensor [24] [25]. They use the reflections of pulsed laser light on object surfaces to provide distance measurements.…”