Unmanned Systems

Unmanned surface vehicles (USVs) are gaining increasing attention for maritime missions such as environmental monitoring, target surveillance, and autonomous transport. However, the security and reliability of their control systems frequently face challenges from cyber-physical threats, particularly deception attacks that manipulate sensor data or communication signals. To address this issue, thi…

Multi-waypoint path planning for autonomous robots remains a challenging optimization problem, as traditional methods often struggle with scalability. Inspired by the network formation of Physarum polycephalum, the Slime Mould-based MultiWaypoint Planner (SMMWP), a novel nature-inspired algorithm, is introduced. The navigation task is formulated as a Travelling Salesman Problem. To address this, …

This study develops an integrated optimization model for vehicle-drone collaborative delivery in low-altitude logistics, incorporating heterogeneous social vehicles via a dynamic quotation and negotiation process. A hybrid heuristic framework combining mixed-integer programming and event-driven simulation is proposed to handle dynamic vehicle availability and pricing uncertainty. The approach coo…

To address the coupled problem of cooperative search and attitude control faced by multi-UAV systems in complex uncertain environments, a unified control strategy based on hierarchical POMDP is proposed. This strategy effectively decomposes multi-scale decision-making problems by constructing a hierarchical architecture of upper-level task planning and lower-level attitude control. The upper leve…

Coverage control in multimodal Gaussian environments remains challenging for distributed multi-agent systems with limited sensing and communication capabilities, as existing methods often lead to incomplete coverage, imbalanced agent allocation, and connectivity interruptions. To overcome these challenges, this paper proposes a novel coverage control strategy based on a leader-following framework…

This paper presents a generalizable decentralized Context-aware Deep Assignment Network (CDAN) tailored for addressing Perimeter Defense Problems (PDP). In PDP scenarios, a group of defenders operates along a segmented convex closed perimeter, aiming to intercept intruders attempting to breach it. The PDP is framed as an assignment learning problem for the defenders to sequentially capture intrud…

The core task of unmanned aerial vehicle (UAV) inspection for wind turbines lies in path planning, with the primary objectives being comprehensive coverage of the turbines and improved energy efficiency. Existing methods are mostly applicable to facilities with simple structures, overlooking the complex characteristics of wind turbines and failing to adequately consider energy consumption issues.…

The Unmanned Swarm Operations Experiment (USOE) simulation technology serves as a critical supporting technology for validating unmanned swarm combat concepts and assessing operational capabilities. It is essential to conduct a systematic investigation into the current research status of USOE simulation technology to deliver high-quality research outcomes to combat commanders and relevant researc…

Hybrid aerial–ground robots have recently attracted increasing attention for their versatile mobility and adaptability across complex environments. This paper presents a bias-aware estimation and control framework for a miniaturized dual-tilt aerial–ground robot. A complete nonlinear dynamic model is first established, and a bias-linearized allocation structure is derived to reveal the effect of …

Traditional neural networks are widely used for surrogate modeling of complex dynamics. However, they often suffer from poor interpretability, high computational costs, and an inability to provide the Jacobian matrices essential for model-based control. Physics-informed neural networks (PINNs), which embed physical laws into the training process, offer a promising alternative, yet their applicati…

Reliable and efficient obstacle-avoidance motion planning for redundant manipulators remains challenging, especially in environments with irregular obstacles and high-dimensional constraints. Although deep reinforcement learning (DRL) offers promising solutions, existing methods still suffer from slow convergence and suboptimal trajectory quality. This paper accounts for practical path-length and…

With the rapid advancements in artificial intelligence and control technologies in recent years, uncrewed systems have become increasingly prevalent across various fields. Path planning, a critical technology enabling autonomy in these systems, remains a challenging and active area of research. This review provides a comprehensive overview of the fundamentals of path planning and deep reinforceme…

Vehicle Tyre inspection has been a crucial activity for identifying tyre manufacturing defects. Currently, the inspection process is manual and time-consuming. To make the inspection process quicker, simpler, and more accurate, with lower cost, it is essential to make the Tyre inspection process automatic. This automation is possible using advanced computer vision techniques. However, this techni…

This article addresses the moving target enclosing control problem for nonholonomic multi-agent systems with guaranteed network connectivity and collision avoidance. We propose a novel control scheme to handle distance constraints imposed by the agents’ limited interaction ranges and collision-free thresholds. By leveraging a Henneberg construction method, we innovatively formulate the target enc…

In recent years, unmanned ground vehicles (UGVs) have advanced rapidly, attracting significant attention for their applications in modern military operations, particularly as target vehicles. Their ability to perform realistic combat maneuvers relies heavily on formation control, a key technology in this domain. This paper presents a novel formation control framework aimed at improving the accura…

Recent advancements in 3D reconstruction and neural rendering have enhanced the creation of high-quality digital assets, yet existing methods struggle to generalize across varying object shapes, textures, and occlusions. While Next Best View (NBV) planning and Learning-based approaches offer solutions, they are often limited by predefined criteria and fail to manage occlusions with human-like com…

Multi-agent pursuit-evasion has significant applications in military, transportation, and industrial sectors. This task faces dual challenges of uncertain swarm scale and environmental uncertainty within unstructured dynamic environments. To address these, we propose a hierarchical reinforcement learning framework based on permutation invariance to balance pursuit efficiency and collision avoidan…

As intelligent manufacturing continues to emerge as a dominant industrial paradigm, unmanned aerial vehicles (UAVs) have proven instrumental in enhancing workshop transhipment efficiency through their inherent operational flexibility. In this paper, we develop a comprehensive UAV swarm collaborative transhipment scheduling model with respect to three-dimensional continuous environments, and intro…

This paper presents a fast nonsingular terminal integral sliding mode (FNTISM) controller for attitude tracking of a tilt trirotor unmanned aerial vehicle (UAV) in vertical takeoff and landing (VTOL) flight mode. The rotation of UAV is described by the matrix group SO(3) to eliminate gimbal lock. Besides, the proposed controller offers fast response, high tracking accuracy, and strong disturbance…

To address the long formation time and total travel distance of large-scale UAV collaborative formations, as well as formation control errors caused by delays and interference, we first used the Kuhn-Munkres algorithm combined with the distributed Starfish optimization algorithm to find the optimal position allocation solution. We then used a second-order consistency method that incorporated pred…