A tightly coupled multi-sensor SLAM algorithm based on feature planes in indoor scenes is proposed for laser SLAM algorithms in indoor environments affected by glass and mirrors and with few feature points. Firstly, the odometry motion estimation is performed by fusing inertial guidance, and the key frames are judged by the positional transformation. Secondly, the key frames are extracted based on RANSAC, matched with the data in the feature plane manager, and then the data are merged and expanded. Finally, the LIDAR data information, inertial guidance information and feature plane information are put into the sliding window optimizer and solved by nonlinear optimization to obtain the optimal poses and maps. To verify the effectiveness of the algorithm, experiments are conducted in real indoor scenes and detailed comparisons are made on the optimization time and localization accuracy. The experimental results show that this method achieves better positional estimation accuracy and shows good robustness and real-time performance compared with current advanced laser SLAM methods.
Multi-sensor Tightly Coupled SLAM Algorithm Based on Feature Planes in Indoor Scenes
Lect.Notes Computer
International Conference on Intelligent Robotics and Applications ; 2023 ; Hangzhou, China July 05, 2023 - July 07, 2023
2023-10-21
12 pages
Article/Chapter (Book)
Electronic Resource
English
SLAM , Indoor Environment , Feature Plane , Sliding Window Computer Science , Artificial Intelligence , Software Engineering/Programming and Operating Systems , Computer Applications , Computer Communication Networks , Special Purpose and Application-Based Systems , User Interfaces and Human Computer Interaction
Efficient and Accurate Tightly-Coupled Visual-Lidar SLAM
IEEE | 2022
|A tightly coupled LIDAR-IMU SLAM in off-road environment
IEEE | 2019
|