Simultaneous localization and mapping (SLAM) is widely used in industrial automation, enabling autonomous robots and drones to navigate and operate in complex environments.In this study, we investigated the application of advanced sensor technologies, including light detection and ranging (LiDAR), cameras, inertial measurement units (IMUs), ultrasonic sensors, GPS, and thermal sensors, in a multisensor SLAM system.Aerial drone experiments conducted in a challenging urban roundabout environment demonstrated the system's ability to maintain reliable localization and mapping despite environmental variability, dynamic obstacles, and inconsistent lighting.The integration of LiDAR odometry with IMU data reduced positional errors by 52%, while thermal and proximity sensors enhanced resilience against visual data loss.Although the trajectory accuracy achieved (88.31%) was lower than the benchmark results reported in controlled laboratory studies, the system exhibited strong real-time responsiveness, adaptability, and safety-focused navigation.The feasibility of multisensor SLAM in unpredictable industrial settings is validated using the advanced sensor fusion strategies for automation.The results of this study underscore the importance of adaptive calibration, robust error correction, and benchmarking to improve accuracy, while demonstrating that multisensor integration already provides significant operational benefits for warehouse robotics, autonomous delivery vehicles, and drone inspections.
Li et al. (Mon,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: