Abstract
In large-scale and sparse scenes, such as farmland, orchards, mines, and substations, 3D simultaneous localization and mapping are challenging matters that need to address issues such as maintaining reliable data association for scarce environmental information and reducing the computational complexity of global optimization for large-scale scenes. To solve these problems, a real-time incremental simultaneous localization and mapping algorithm called MIM_SLAM is proposed in this paper. This algorithm is applied in mobile robots to build a map on a non-flat road with a 3D LiDAR sensor. MIM_SLAM’s main contribution is that multi-level ICP (Iterative Closest Point) matching is used to solve the data association problem, a Fisher information matrix is used to describe the uncertainty of the estimated pose, and these poses are optimized by the incremental optimization method, which can greatly reduce the computational cost. Then, a map with a high consistency will be established. The proposed algorithm has been evaluated in the real indoor and outdoor scenes as well as two substations and benchmarking dataset from KITTI with the characteristics of sparse and large-scale. Results show that the proposed algorithm has a high mapping accuracy and meets the real-time requirements.
Highlights
In recent years, the simultaneous localization and mapping (SLAM) based on a 3D LIDAR sensor have become an important topic in robotics due to the rise of autonomous driving technology.the building of a map has become the basis for an autonomous mobile robot to complete tasks such as inspection and autonomous navigation [1] in some harsh environments.The research on SLAM can be traced back to Smith et al [2] of Stanford University in the1980s
For large-scale and sparse environments, we propose a novel MIM_SLAM algorithm in this
We propose a novel algorithm in thisinpaper, Forlarge-scale large-scale and sparse environments, propose a novel this paper, which simplifies the SLAM
Summary
The simultaneous localization and mapping (SLAM) based on a 3D LIDAR sensor have become an important topic in robotics due to the rise of autonomous driving technology. The SLAM problem has been thoroughly researched, there are still many problems to be solved, including the fact that computational complexity will increase from two-dimensions to three-dimensions, and how to ensure a consistent map with the increase of the size of mapping and reliable data association with less information in sparse environments Combining these issues, Zlot [7] utilizes a rotating 2D LIDAR sensor to achieve high-precision map construction in a wide mine, but it cannot be applied online. How to reduce the computational complexity of graph optimization is a problem that needs to be improved To solve these problems, we propose a real-time incremental SLAM algorithm called the MIM_SLAM based on a multi-level ICP matching method.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
