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.

To address the demand of digital twin (DT) model construction, we introduce the autonomous exploration framework for Internet of Drones (IoD) network, to autonomously construct models in the preset areas. However, current multi-UAV autonomous exploration frameworks suffer from low efficiency. To address this, we propose an innovative multi-UAV autonomous exploration framework. Using the LiDAR point cloud, our proposed framework firstly generates mesh frontiers based on the unit sphere point cloud flip, without building an occupancy grid map. Secondly, we design a multi-UAV exploration information interaction method, which can efficiently integrates the information obtained from various UAVs. Based on the information, a sparse topological graph is constructed to store the previous local feasible regions. A heuristic function is used to allocate the exploration targets for UAVs. The simulation results indicate that the proposed method achieves higher efficiency in frontier generation and improves exploration efficiency by 13.3-64.6% compared to the state-of-the-art methods.

Autonomous exploration is a fundamental challenge for numerous applications of mobile robots. Traditional methods often lead to impractical and discontinuous trajectories, which may substantially deteriorate the exploration time. In this work, we propose a rapid autonomous exploration framework with a field-of-view (FOV) expansion mechanism. We present a 1-degree-of-freedom (DOF) FOV expansion mechanism, coupled with a frontier-gravitation FOV direction planning method to decouple the direction of the sensor's FOV from the robot velocity direction. Our approach includes a rapid frontier viewpoint generation method utilizing principal component analysis (PCA). Moreover, we introduce a sliding window travelling salesman problem (TSP) for global coverage path planning, incorporating an attenuation coefficient to increase the exploration priority of independent small frontiers and reduce revisit probability. Finally, compared to state-of-the-art (SOTA) approaches, our proposed mechanism and framework beneficially reduce exploration time by 30%-44% and enhance the continuity of the robot movement in both simulation and real-world scenarios.

With the rapid development of wireless communication networks, UAVs serving as base stations are increasingly being applied in various scenarios which not only include edge computation and task offloading, but also involve emergency communication, vehicular network enhancement, etc. In order to enhance the utility of UAV base stations’ allocation and deployment, a series of algorithms have been proposed, utilizing heuristic methods, learning-based algorithms or optimization approaches. However, it is intractable for current algorithms to handle the exponential computation increment with UAV base stations increasing, and complicated application scenarios with high dynamic demands. To solve the above issues, we formulate a decision problem with a long sequence to optimize the deployment of multi-UAV base stations for maximizing vehicular networks’ communication coverage ratio, which needs to be subject to co-constraints consisting of moving velocity, energy consumption and communication coverage radius. To solve this optimization problem, we creatively propose an algorithm named dense multi-agent reinforcement learning (DMARL), which is under the dual-layer nested decision-making framework, centralized training with decentralized deployment, and accelerates training by only collecting critical states into the dense sampling buffer. To prove our proposed algorithm’s effectiveness and generalization ability, we conduct experimental simulations in scenarios with different scales. Corresponding results have been provided to verify our algorithm’s superiority in training efficiency and performance metrics, including coverage ratio and energy consumption, compared with other algorithms.

Exploring the widespread applications of unmanned aerial vehicles (UAVs) in Internet of Things has become a current research hotspot. In some tasks related to UAV-based environmental monitoring and transportation, the simultaneous consideration of UAV task allocation and path planning constitutes a category of joint optimization problems. This paper focuses on a warehouse cargo inspection scenario with multiple heterogeneous UAVs. In such scenarios, existing heuristic path finding algorithms that consider task allocation cannot make a good balance between solution time and solution quality. Therefore, in this paper, we propose a reinforcement learning assisted task allocation and conflict-free path framework to achieve better task allocation and path finding results. The framework uses a multiple traveling salesman transformation algorithm for task allocation and a multi-agent reinforcement learning (MARL) algorithm for conflict-free path finding. The path finding policy can be extended to larger-scale environments with more UAVs. We conduct the training of the path planning module and the verification of the overall framework in random environments. Simulation results show that our reinforcement learning assisted framework has a significant advantage over the existing algorithms in terms of solution time, solution quality and scalability.