Abstract
Place recognition is an indispensable part of the realization of intelligent and autonomous mobile robots. Since GPS is not available in all places, mobile robots can only use other sensors for place recognition when GPS is not available. We propose a method to construct a novel descriptor using the features obtained after point cloud projection. The descriptor has the characteristics of invariant rotation and invariant translation within a certain distance range, so it can be applied to the place recognition of mobile robots. There are advantages and disadvantages when using 3D Lidar or camera for place recognition. We propose a method that fuses 3D Lidar and camera to improve the robustness of the place recognition of mobile robot in different scenarios. We conducted experiments on our own dataset and the KITTI dataset. Our method can perform place recognition within 1 second, and the success rate is as high as 99%. The experimental results show the excellent ability of our method in various environments.
Sign-in/Register to access full text options 
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.
