Human-unmanned aerial vehicle (UAV) collaboration requires control frameworks that are both efficient and safe. This article introduces a stochastic fixed-time inverse optimal control (FxT-IOC) approach designed for such systems. The proposed framework constructs IOC, enabling the extraction of human operator intent. It features a FxT adaptive learning mechanism that guarantees parameter convergence within a predetermined time, irrespective of initial conditions. Crucially, the design explicitly incorporates prescribed performance control (PPC) to enforce state constraints while handling input saturation, ensuring operational safety and reliability. Rigorous theoretical analysis establishes the FxT stability of the learning process and the closed-loop system under these constraints. The effectiveness of the FxT-IOC framework is validated through comprehensive numerical simulations and physical hardware experiments, demonstrating superior trajectory tracking precision, accelerated learning convergence, and robust constraint satisfaction compared to human demonstrations. This work offers a principled and practical solution for developing high-performance, reliable human-UAV collaborative systems.

The object detection of the substation is the key to ensuring the safety and reliable operation of the substation. The traditional image detection algorithms use the corresponding texture features of single-class objects and would not handle other different class objects easily. The object detection algorithm based on deep networks has generalization, and its sizeable complex backbone limits the application in the substation monitoring terminals with weak computing power. This article proposes a multitargets joint training lightweight model. The proposed model uses the feature maps of the complex model and the labels of objects in images as training multitargets. The feature maps have deeper feature information, and the feature maps of complex networks have higher information entropy than lightweight networks have. This article proposes the heat pixels method to improve the adequate object information because of the imbalance of the proportion between the foreground and the background. The heat pixels method is designed as a kind of reverse network calculation and reflects the object’s position to the pixels of the feature maps. The temperature of the pixels indicates the probability of the existence of the objects in the locations. Three different lightweight networks use the complex model feature maps and the traditional tags as the training multitargets. The public dataset VOC and the substation equipment dataset are adopted in the experiments. The experimental results demonstrate that the proposed model can effectively improve object detection accuracy and reduce the time-consuming and calculation amount.