Yongbin Zheng

To address the cooperative guidance problem for autonomous aerial vehicle (AAV) formation with false-data injection and only the leader equipped with a seeker, a hybrid algorithm is developed to estimate the line-of-sight (LOS) angles between AAVs and the target by integrating Tiny Long Short-Term Memory (TLSTM) and Kalman Filter (KF). A cooperative guidance method with the leader-first follower (LFF) configuration is proposed to achieve simultaneous attacks on a maneuvering target within a prescribed time by regulating the contraction rate of the formation. First, the Expectation-Maximization (EM) algorithm is employed to optimize the parameters of the KF, while the TLSTM model is integrated for updating the observation for the optimized KF. The KF extracts local features of the angular data to smooth the angle predictions from the TLSTM. Subsequently, a prescribed-time guidance law is developed for the leader in the LOS direction. To ensure rapid convergence of follower AAVs, a prescribed performance control method is adopted to adjust the contraction rate of the formation. Finally, rigorous theoretical demonstration and numerical simulations validate the effectiveness of the proposed approach.

Recent studies in remote sensing object detection have made excellent progress and shown promising performance. However, most current detectors only explore rotation-invariant feature extraction but disregard the valuable spatial and semantic prior knowledge in remote sensing images (RSIs), which limits the detection performance when encountering blurred or heavy occluded objects. To address this issue, we propose a mask-reconstruction relation learning (MRRL) framework to learn such prior knowledge among objects and a consistency-reasoning transformer over relation proposals (CTRP) to recognize objects with limited visual features via consistency reasoning. Specifically, MRRL framework applies random mask to some objects in the training dataset and performs masked objects reconstruction to guide the network to learn the distribution consistency of objects. CTRP is the core component of the MRRL framework, which models the interaction between spatial and semantic priors, and uses easy detected objects to reason hard detected objects. The trained CTRP can be integrated into the existing detector to improve the ability of object detection with limited visual features in RSIs. Extensive experiments on widely-used datasets for two distinct tasks, namely remote sensing object detection task and occluded object detection task, demonstrate the effectiveness of the proposed method. Source code is available at https://github.com/sunpeng96/CTRP_mmrotate.

Convergence rate is a key performance index for flight vehicles, and accelerating it remains a critical open issue. In this paper, a fast robust integrated guidance and control scheme for flight vehicles based on convergence rate estimation mechanism is proposed, which improves the control performance and interception accuracy of flight vehicles. In the fast robust control scheme, a convergence rate indicator for integrated guidance and control systems is developed to measure the impact on convergence rate imposed by model nonlinearities and couplings within flight vehicles. Based on the indicator, the influences on convergence rate are transformed and injected into controllers to accelerate the convergence of flight vehicles. The unmatched lumped uncertainties in flight vehicle dynamics are addressed by a backstepping control method and finite-time convergence disturbance observers, which improves the robustness of the vehicle’s control system. Furthermore, the stability analysis of the closed-loop system is performed via the Lyapunov stability theorem. Extensive numerical simulations are conducted to verify the effectiveness and interception performance of the proposed method, and the comparison results confirm that it outperforms three other recently developed robust control methods.

Low, small, and slow (LSS) unmanned aerial vehicles (UAVs) pose great challenges for conventional guidance methods. However, existing deep reinforcement learning (DRL)-based interception guidance law has mostly focused on simplified two-dimensional planes and requires strict initial launch scenarios (constructing collision triangles). Designing more robust guidance laws has therefore become a key research focus. In this paper, we propose a novel recurrent proximal policy optimization (RPPO)-based guidance law framework. Specifically, we first design initial launch conditions in three-dimensional space that are more applicable and realistic, without requiring to form a collision triangle at the initial launch. Then, considering the temporal continuity of the seeker’s observations, we introduce the long short-term memory (LSTM) networks into the proximal policy optimization (PPO) algorithm to extract hidden temporal information from the observation sequences, thus supporting the policy training. Finally, we propose a reward function based on velocity prediction and overload constraints. Simulation experiments show that the proposed RPPO framework achieves an interception rate of 95.3% and a miss distance of 1.2935 m under broader launch conditions. Moreover, the framework demonstrates strong generalization ability, effectively coping with unknown maneuvers of UAVs.

Oriented object detection has attained remarkable progress in addressing the challenges associated with rotating invariant feature extraction. However, most existing object detection most existing encounter serious performance degradation when processing objects with tiny size, blurring and occlusion. One of the reasons is that existing methods mainly focus on local features, while overlooking the correlation among objects and common sense knowledge, which is inconsistent with the human visual system. To address this issue, we propose a dual-stream global relationship learning (DGRL) method consisting of two modules: a dynamic correlation learning (DCL) method and a global knowledge mapping (GKM) module. The DCL method can construct a region-to-region dynamic relationship graph based on feature correlations and implicitly guides the detection network to learn more powerful class representation by updating nodes of the graph. The GKM module generates a class-to-class global semantic relationship graph via external knowledge and achieve more stable representation learning by dynamically global relational mapping. Extensive experiments are performed on oriented object detection datasets DOTA, HRSC2016, DIOR-R as well as horizontal object detection datasets NWPU VHR-10, RSOD. The results demonstrate that the proposed method achieves the state-of-the-art detection accuracy.