- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
[IEEE 2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) - Irkutsk, Russia (2019.8.4-2019.8.9)] 2019 IEEE International Conference on Real-time Computing and Robotics (RCAR) - A Hierarchical Searching Approach for Laser SLAM Re-localization on Mobile Robot Platform
摘要： Simultaneous localization and mapping (SLAM) is an important issue for mobile robot system. Re-localization, as a part of close loop checking of SLAM, focuses on localize the position of a robot agent when it is restarted. Traditional localization methods couldn’t reach both a high accuracy and a little time cost. In this paper, we proposed a newly hierarchical searching approach for laser SLAM re-localization. We do hierarchically searching to match an input laser frame with the whole 2-D map, instead of comparing it with each frame in the map. By using such approach, we could accelerate re-localization speed, so the performance of SLAM is improved. Our SLAM system is well organized on a mobile robot platform. After ?eld test, our approach reaches a average precision (AP) of 90.6% on a 20m× 20m map area, and the time cost is averagely 30ms. The result shows our hierarchical searching approach is effective for re-localization problems on laser SLAM.
关键词： SLAM,laser SLAM,hierarchical searching,mobile robot,re-localization
更新于2025-09-23 15:19:57
-
An Offline Coarse-To-Fine Precision Optimization Algorithm for 3D Laser SLAM Point Cloud
摘要： 3D laser simultaneous localization and mapping (SLAM) technology is one of the most efficient methods to capture spatial information. However, the low-precision of 3D laser SLAM point cloud limits its application in many fields. In order to improve the precision of 3D laser SLAM point cloud, we presented an offline coarse-to-fine precision optimization algorithm. The point clouds are first segmented and registered at the local level. Then, a pose graph of point cloud segments is constructed using feature similarity and global registration. At last, all segments are aligned and merged into the final optimized result. In addition, a cycle based error edge elimination method is utilized to guarantee the consistency of the pose graph. The experimental results demonstrated that our algorithm achieved good performance both in our test datasets and the Cartographer public dataset. Compared with the reference data obtained by terrestrial laser scanning (TLS), the average point-to-point distance root mean square errors (RMSE) of point clouds generated by Google’s Cartographer and LOAM laser SLAM algorithms are reduced by 47.3% and 53.4% respectively after optimization in our datasets. And the average plane-to-plane distances of them are reduced by 50.9% and 52.1% respectively.
关键词： laser SLAM,point clouds,LiDAR,precision optimization,mobile mapping
更新于2025-09-19 17:13:59
-
[IEEE 2019 Chinese Control And Decision Conference (CCDC) - Nanchang, China (2019.6.3-2019.6.5)] 2019 Chinese Control And Decision Conference (CCDC) - Experimental Research on Feature Extraction of Laser SLAM Based on Artificial Landmarks
摘要： Simultaneous Localization and Mapping (SLAM) is the core issue in the field of mobile robots. Laser SLAM is one of the widely used solutions for the application of SLAM in engineering. Laser SLAM estimates the change of the robot pose using the features of the environment. However, it is difficult to extract natural features in a highly similar environment. Therefore, artificial landmarks are needed to be placed in the environment when necessary. In this paper, the reflective characteristics of the artificial landmark are analyzed experimentally, and two feature parameters for the extraction of the artificial landmark are proposed based on their reflective characteristics. One of them is the intensity of the reflected light received by the laser ranger, and the other is the number of the laser points that the artificial landmark can continuously reflect back in each scan. Through the statistical analysis of the laser data collected in the experiment, the specific values of these two parameters are determined, and the detection range of the laser ranger to effectively extract the landmark under the selected parameters is measured experimentally. These results provide experimental support for the deployment of the landmarks in the environment.
关键词： Artificial Landmarks,Feature Extraction,Laser SLAM
更新于2025-09-12 10:27:22