Abstract
This article concerns the problem of a dense mapping system for a robot exploring a new environment. In this scenario, a robot equipped with an RGB-D camera uses RGB and range data to build a consistent model of the environment. Firstly, dense mapping requires the selection of the data representation. Secondly, the dense mapping system has to deal with localization drift which can be corrected when loop closure is detected. In this article, we deal with both of these problems, and we make several technical contributions. We define local maps which use the Normal Distribution Transform (NDT) stored in the 2D structures to represent the local scene with varying 3D resolution. This method directly utilizes the uncertainty model of the range sensor and provides information about the accuracy of the data in the map. We also propose an architecture that utilizes pose and covisibility graphs to correct a global model of the environment after loop closure detection. We show how to integrate the dense local mapping with the pose graph and keyframes management system in the ORB-SLAM2 localization. Finally, we show the advantages of the view-dependent model over the methods that uniformly divide the space to represent objects in the environment.
Highlights
Mobile robots are becoming increasingly popular in factories, warehouses, houses, and even hospitals
We propose the use of view-dependent Normal Distribution Transform (NDT)-OM maps coupled with ORB-SLAM2 which uses keyframes (RGB images) organized in a graph to represent the transformation between camera poses [30]
We propose a new representation which is based on Normal Distribution Transform Occupancy Maps (NDT-OM) [36]
Summary
Mobile robots are becoming increasingly popular in factories, warehouses, houses, and even hospitals. They support activities, such as autonomous transport, floor cleaning, or facility surveillance. When the robot is equipped with a robotic arm, the number of possible applications significantly increases. The robot can support the production process, object pick-and-place, load and unload machines with parts or materials, palletize, or assemble objects. Mobile manipulating robots are used to bring objects on demand. In all those applications robots should localize themselves and build a dense model of the environment to avoid collisions with obstacles and navigate safely in the previously unknown environment
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
