RGB-D cameras serve as indispensable sensors for indoor simultaneous localization and mapping (SLAM) in lightweight robots. However, many RGB-D SLAM systems fail to capitalize on the multi-modal information provided by cameras due to computational constraints, leading to suboptimal performance in challenging environments such as structure-less scenes for LiDARs and texture-less scenes for cameras. To address this issue, we propose a novel, lightweight, and robust real-time depth-inertial odometry (R 2 DIO) designed for Time-of-Flight (ToF) RGB-D cameras. It effectively extracts pseudo 3D line and plane features from color and depth images through the utilization of agglomerative hierarchical clustering (AHC), which leverages the adjacency relationships between pixels and incorporates multi-modal constraints. To enhance real-time performance, directional consistency constraints are applied to filter mismatches during feature alignment. R 2 DIO estimates states and generates dense colored maps using line and plane matching constraints, IMU pre-integration constraints, and historical odometry constraints. Experimental results underscore the robustness, accuracy, and efficiency of R 2 DIO. It can accurately locate in structure-less or texture-less scenes and operate at 30 Hz on a low-power platform. We publicly provide R 2 DIO’s source code and experiment datasets to foster community development.
RGB-D cameras serve as indispensable sensors for indoor simultaneous localization and mapping (SLAM) in lightweight robots. However, many RGB-D SLAM systems fail to capitalize on the multi-modal information provided by cameras due to computational constraints, leading to suboptimal performance in challenging environments such as structure-less scenes for LiDARs and texture-less scenes for cameras. To address this issue, we propose a novel, lightweight, and robust real-time depth-inertial odometry (R 2 DIO) designed for Time-of-Flight (ToF) RGB-D cameras. It effectively extracts pseudo 3D line and plane features from color and depth images through the utilization of agglomerative hierarchical clustering (AHC), which leverages the adjacency relationships between pixels and incorporates multi-modal constraints. To enhance real-time performance, directional consistency constraints are applied to filter mismatches during feature alignment. R 2 DIO estimates states and generates dense colored maps using line and plane matching constraints, IMU pre-integration constraints, and historical odometry constraints. Experimental results underscore the robustness, accuracy, and efficiency of R 2 DIO. It can accurately locate in structure-less or texture-less scenes and operate at 30 Hz on a low-power platform. We publicly provide R 2 DIO’s source code and experiment datasets to foster community development.