Xuanke Zhong

The evolving low-altitude economy enables Unmanned Aerial Vehicles (UAVs) to gather diverse sensor data, including RGB images, 3D point clouds, and inertial measurements, offering untapped potential for environmental mapping. Traditional urban 3D modeling methods often face delays in updates and scalability issues. This paper introduces a novel UAV-based collaborative mapping framework that integrates heterogeneous data from multiple UAVs to efficiently reconstruct dynamic urban environments. The framework employs advanced visual recognition and optical character recognition (OCR) for semantic feature extraction, complemented by LiDAR inertial odometry for precise map construction. To address challenges posed by sparse LiDAR data in indoor settings, a temporal alignment mechanism is employed to generate synchronized keyframes, enhancing data coherence. Additionally, camera-LiDAR calibration combined with cross-modal registration and semantic-guided point cloud stitching boosts system robustness. Experimental results demonstrate that feature-guided point cloud registration, bolstered by semantic alignment, surpasses traditional methods, achieving efficient mapping and offering a scalable solution for urban 3D modeling, applicable in real-time urban planning and smart city development.

Indoor positioning is a critical component for numerous applications and services. However, GNSS systems face challenges in delivering accurate positioning information in indoor environments. Current indoor positioning research primarily concentrates on enhancing the positioning performance of individual terminals through various techniques. As we transition into the Internet of Things (IoT) era, former indoor positioning methods need refinement. In this paper, we propose a novel indoor positioning method that leverages robots as mobile base stations to mitigate the problem of inadequate fixed base stations and aims to enhance positioning accuracy by incorporating pedestrian inertial navigation data. The process involves several steps. First, the mobile robots accurately determine their positions and performing coordinate transformations to ensure consistency with pedestrian coordinate systems. Then, pedestrians use the ranging information from these robots along with their smartphones’ sensors for multi-source fusion positioning. Finally, an Extended Kalman Filter (EKF) is applied to fuse the multiple sources of data, considering various sources of errors, to provide enhanced positioning performance. Experimental results demonstrate the effectiveness of this approach in addressing indoor positioning challenges. This method could benefit numerous scenarios involving robots, enhancing pedestrian positioning accuracy and overall system robustness. The paper provides a comprehensive exploration of this proposed method, its implications, and potential directions for future advancements.