Efficient Autonomous UAV Exploration Framework With Limited FOV Sensors for IoT Applications

—Due to the outstanding maneuverability, unmanned aerial vehicles (UAVs) garner increasing applications in the Internet of Things (IoT), such as data collection, environmental monitoring, emergency communication, search and rescue, and autonomous exploration is the foundation of these missions which can obtain a prebuilt map automatically. However, current methods suffer from low efficiency. To address this, we propose a hierarchical exploration framework for UAVs with limited field-of-view (FOV) sensor, encompassing frontier and viewpoint generation, global coverage path planning, and active perception trajectory generation. First, we employ the random seeds frontier generation and anisotropic Gaussian sampling for environment information update, which can efficiently utilize sensor’s sensing range. Then, we design an appropriate heuristic function to represent the connection cost between different viewpoints and solve the global coverage path as a traveling salesman problem (TSP) to balance the long-term and short-term information gain. Moreover, active perception trajectory planning is proposed to enhance flight safety, smoothness, and exploration efficiency. Simulation and real-world scenario results indicate that the proposed method achieves higher efficiency in frontier generation and viewpoint sampling, and the difficulty of solving global coverage path does not significantly increase with the environment scale. Our proposed method improves exploration efficiency by 17%–27% compared to the state-of-the-art (SOTA) method.