Unmanned farms employ a variety of sensors, automated systems, and data analysis techniques to enable fully automated and intelligent management. This not only heightens agricultural production efficiency but also reduces the costs associated with human resources. As integral components of unmanned farms’ automation systems, agricultural UAVs have been widely adopted across various operational stages due to their precision, high efficiency, environmental sustainability, and simplicity of operation. However, present-day technological advancement levels and relevant policy regulations pose significant restrictions on UAVs in terms of payload and endurance, leading to diminished task efficiency when a single UAV is deployed over large areas. Accordingly, this paper aggregates and analyzes research pertaining to UAV swarms from databases such as Google Scholar, ScienceDirect, Scopus, IEEE Xplorer, and Wiley over the past decade. An initial overview presents the current control methods for UAV swarms, incorporating a summary and analysis of the features, merits, and drawbacks of diverse control techniques. Subsequently, drawing from the four main stages of agricultural production (cultivation, planting, management, and harvesting), we evaluate the application of UAV swarms in each stage and provide an overview of the most advanced UAV swarm technologies utilized therein. Finally, we scrutinize and analyze the challenges and concerns associated with UAV swarm applications on unmanned farms and provide forward-looking insights into the future developmental trajectory of UAV swarm technology in unmanned farming, with the objective of bolstering swarm performance, scalability, and adoption rates in such settings.

The feasibility of aerial fertilization by UAV-based granular fertilizer spreaders (GFSs) has been widely accepted. Although commercial UAV-based spreaders have emerged, their performance in granular fertilizer spreading application has rarely been studied. This paper tested the performances of four existing UAV-based GFSs in the automatic controllability, range of the discharge rate and the swath width and uniformity of the distribution. An analytic hierarchy process (AHP)-based method was proposed to evaluate their comprehensive performance in spreading application. The main results are as follows: (a) GFS-A showed the maximum controllable discharge rate of 27 kg/min, and GFS-B showed the minimum (proximately 3 kg/min). The discharge rate could be changed in a stepless way by GFS-B, C and D. The relationship between the discharge rate and the rotational speed of the fluted roller of GFS-D showed a significant linear relationship ( $\text {R}^{2} = 0.9991$ ) for the operational range. (b) The distribution patterns of GFS-A and D were trapezoidal, which was the better deposition pattern for generating uniform spreading; those of the other two UAV-based GFSs were a wide triangle with obviously asymmetrical sides (GFS-B) and a typical M-shape with two peaks (GFS-C). (c) the simulation of CV-swath width illustrated that the available effective swath width (CV ≤ 20%) for these UAV-GFSs were 5.1m (CV = 14.73%), 4.8m(CV = 17.55%), 3.9m(CV = 13.02%) and 5.7m(CV = 18.36%) respectively under the given conditions. Furthermore, according to the AHP-based evaluation model, it was proved that GFS-D was able to provide superior performance in precise fertilization for a large application range, which is important for its practical application. This comparative study makes useful contribution for farmers and researchers in this field in understanding the application performance of various UAV-based GFSs.

This paper proposes an optical tracking system to realize the clustering of multiple unmanned aerial vehicles (UAVs). The system uses a laser spot as a visual recognition target to realize cluster flight operations in a complex environment. To reduce the interference of sunlight in the optical visual navigation and obtain the optimal combination of laser receiving devices, we selected lasers in a variety of spectrum bands and filter films with different light transmittances to conduct a comprehensive test. By performing a fluid simulation of the UAVs with the related modules mounted in different positions, the optimal installation position was selected to enhance the effect of the UAV wind field. An online learning tracking framework based on the multi-feature extraction of convolutional networks was developed to realize robust long-term visual tracking. In the tracking process, the tracking algorithm could train the detector online according to the status of the target and adaptively initialize the target. Finally, to verify the practical application performance of the clustering system, a group of UAVs was tested in flight. We verified that the proposed method and device exhibit a high feasibility and reliability.

This paper introduces a lightweight Semantic-guided Mutually Reinforcing network (SMR-Net) for the tasks of cross-modal image fusion and salient object detection (SOD). The core concept of SMR-Net is to leverage semantics for directing the mutual reinforcing between image fusion and SOD. Specifically, a Progressive Cross-modal Interaction (PCI) image fusion subnetwork is designed to exploit local interactions via convolution operations and extend to global interactions utilizing spatial and channel attention mechanisms. Subsequently, a cross-modal Bit-Plane Slicing-based SOD subnetwork (BPS) is developed by incorporating the fused image as a third modality. This component employs bit-plane slicing and the deformable convolution technique to effectively extract irregular semantic information embedded in fusion features. The refined semantic information then guides the feature extraction process of the source modalities in a reweighted fashion. By cascading these two subnetworks, BPS leverages final semantic results to direct PCI towards focusing more on semantic information. Ultimately, through this semantic-guided mutual enhancement process, SMR-Net excels in both producing high-quality fused images and achieving effective salient object detection. Our extensive experiments on image fusion and SOD tasks convincingly demonstrate the superiority of our network over existing state-of-the-art alternatives without introducing noticeable computational costs. Compared to nearest competitors, our method demonstrates a stronger generalization ability with 26% fewer parameters.