Real-time lidar-visual feature co-optimization for complex indoor environments: an adaptive fusion framework with illumination-robust enhancement

In complex indoor environments—such as chaotic warehouses or post-disaster sites—achieving accurate simultaneous localization and mapping (SLAM) is hindered by inherent limitations of the sensors involved: Light Detection and Ranging (LiDAR) loses effectiveness in glass corridors, and Red–Green–Blue-Depth (RGB-D) cameras suffer from performance degradation when exposed to poor lighting conditions. To address this, we proposes a real-time multi-sensor fusion SLAM framework that integrates 2D LiDAR and RGB-D cameras. An improved particle filter–based IP-Mapping algorithm is introduced, redesigning the proposal distribution and incorporating KLD adaptive resampling, which accelerates particle convergence by 1.5 × compared with Gmapping while maintaining mapping accuracy. Additionally, a novel I-SURF feature matching method combines ORB with edge-enhanced descriptors, achieving 96.8% matching accuracy under varying illumination and scale conditions. A region-based fusion algorithm is further developed to align RGB-D point clouds with 2D LiDAR scans using octree and KD-tree structures. Experiments in office-like environments demonstrate that the proposed framework reduces localization error by 75.4%–83.5% relative to single-sensor baselines, achieving a grid map resolution of 0.05 m/cell in real time. These results validate the effectiveness of the method for robust robotic mapping and navigation in cluttered indoor settings.