室内复杂环境中LIO-SLAM算法的改进与优化OA

This paper proposes an improved method that integrates visual odometry to address the defect of traditional LIO-SLAM being affected by sparse laser features and dynamic occlusion in complex indoor environments,resulting in decreased positioning accuracy.Specifically,while maintaining the LIO-SLAM laser inertial tight coupling framework,ORB-SLAM is introduced as an independent visual odometry module to provide high-frequency and rich texture visual constraint information for the system.By using an adaptive weight fusion strategy,multi-source optimization of laser,inertial,and visual observations is achieved,enhancing robustness in environments with weak geometric constraints and rich textures but complex structures.The experiment was conducted in various typical indoor scenarios(corridors,open halls,and dynamic crowd environments),and the results showed that the overall trajectory error was reduced to 70%of the original system,compared to the original LIO-SLAM.This study validates the feasibility and effectiveness of visual laser inertial multimodal fusion in complex indoor environments,providing new ideas for high-precision indoor autonomous positioning and map construction.