Object detection is important in unmanned aerial vehicle (UAV) reconnaissance missions. However, since a UAV flies at a high altitude to gain a large reconnaissance view, the captured objects often have small pixel sizes and their categories have high uncertainty. Given the limited computing capability on UAVs, large detectors based on convolutional neural networks (CNNs) have difficulty obtaining real-time detection performance. To address these problems, we designed a small-object detector for UAV-based images in this paper. We modified the backbone of YOLOv4 according to the characteristics of small-object detection. We improved the performance of small-object positioning by modifying the positioning loss function. Using the distance metric method, the proposed detector can classify trained and untrained objects through object features. Furthermore, we designed two data augmentation strategies to enhance the diversity of the training set. We evaluated our method on a collected small-object dataset; the proposed method obtained 61.00% $mA{P}_{50}$ on trained objects and 41.00% $mA{P}_{50}$ on untrained objects with 77 frames per second (FPS). Flight experiments confirmed the utility of our approach on small UAVs, with satisfying detection performance and real-time inference speed.

For robot swarm applications, accurate positioning is one of the most important requirements for avoiding collisions and keeping formations and cooperation between individuals. However, in some worst cases, the GNSS (Global Navigation Satellite System) signals are weak due to the crowd being in a swarm or blocked by a forest, mountains, and high buildings in the environment. Thus, relative localization is an indispensable way to provide position information for the swarm. In this paper, we review the status and development of relative localization. It is first assessed that relative localization to obtain spatio-temporal relationships between individuals is necessary to achieve the stable operation of the group. After analyzing typical relative localization systems and algorithms from the perspective of functionality and practicality, this paper concludes that the UWB-based (ultra wideband) system is suitable for the relative localization of robots in large-scale applications. Finally, after analyzing the current challenges in the field of fully distributed localization for robotic swarms, a complete mechanism encompassing the relative localization process and the relationship between local and global localization that can be a possible direction for future research is proposed.

This paper presents a distributed cooperative search algorithm for multiple unmanned aerial vehicles (UAVs) with limited sensing and communication capabilities in a nonconvex environment. The objective is to control multiple UAVs to find several unknown targets deployed in a given region, while minimizing the expected search time and avoiding obstacles. First, an asynchronous distributed cooperative search framework is proposed by integrating the information update into the coverage control scheme. And an adaptive density function is designed based on the real-time updated probability map and uncertainty map, which can balance target detection and environment exploration. Second, in order to handle nonconvex environment with arbitrary obstacles, a new transformation method is proposed to transform the cooperative search problem in the nonconvex region into an equivalent one in the convex region. Furthermore, a control strategy for cooperative search is proposed to plan feasible trajectories for UAVs under the kinematic constraints, and the convergence is proved by LaSalle’s invariance principle. Finally, by simulation results, it can be seen that our proposed algorithm is effective to handle the search problem in the nonconvex environment and efficient to find targets in shorter time compared with other algorithms.

Infrared and visible image fusion is an important precondition of realizing target perception for unmanned aerial vehicles (UAVs), then UAV can perform various given missions. Information of texture and color in visible images are abundant, while target information in infrared images is more outstanding. The conventional fusion methods are mostly based on region segmentation; as a result, the fused image for target recognition could not be actually acquired. In this paper, a novel fusion method of airborne infrared and visible image based on target region segmentation and discrete wavelet transform (DWT) is proposed, which can gain more target information and preserve more background information. The fusion experiments are done on condition that the target is unmoving and observable both in visible and infrared images, targets are moving and observable both in visible and infrared images, and the target is observable only in an infrared image. Experimental results show that the proposed method can generate better fused image for airborne target perception.

Cooperative standoff tracking of moving targets is an important application of fixed-wing unmanned aerial vehicles (UAVs). To cope with the problem of long convergence time and unstable tracking in cooperative target tracking, traditional Lyapunov vector field guidance (LVFG) is modified. The guidance parameter $c$ is discussed, and the gradient descent method is utilized to develop the optimal guidance parameter search algorithm. As for tracking moving targets, an interacting multiple model-based unscented Kalman filter (IMM-UKF) estimator is built for predicting the target state, and the result is used for correcting the guidance law. Meanwhile, a speed-based controller is developed for faster convergence to the desired intervehicle phase, and the stability of the controller is proved using the Lyapunov stability theory. Numerical simulation results indicate the proposed guidance converges faster to the standoff circle without intersecting the orbit. The state estimator reduces the estimate error and the intervehicle phase converges faster to the desired phase than the traditional control method. Furthermore, extensive hardware-in-the-loop simulations are carried out to verify the feasibility of the algorithm.