The well-known generalization problem hinders the application of artificial neural networks in continuous-time prediction tasks with varying latent dynamics. In sharp contrast, biological systems can neatly adapt to evolving environments benefiting from real-time feedback mechanisms. Inspired by the feedback philosophy, we present feedback neural networks, showing that a feedback loop can flexibly correct the learned latent dynamics of neural ordinary differential equations (neural ODEs), leading to a prominent generalization improvement. The feedback neural network is a novel two-DOF neural network, which possesses robust performance in unseen scenarios with no loss of accuracy performance on previous tasks. A linear feedback form is presented to correct the learned latent dynamics firstly, with a convergence guarantee. Then, domain randomization is utilized to learn a nonlinear neural feedback form. Finally, extensive tests including trajectory prediction of a real irregular object and model predictive control of a quadrotor with various uncertainties, are implemented, indicating significant improvements over state-of-the-art model-based and learning-based methods.

Due to its small size and light weight, the tiny unmanned aerial vehicle (UAV) is especially suitable for tasks that involve confined indoor space exploration. However, autonomous localization of the tiny UAV has become a great challenge in the global navigation satellite system (GNSS)-denied, unstructured, and resource-constrained environments. In this paper, an onboard ultra-wideband (UWB)-based relative localization scheme of the tiny UAV is presented, where an anchor-UAV equipped with the UWB anchors is employed to provide position reference for the tiny UAV. As the key in the proposed scheme, the state estimation algorithm should be able to overcome the joint effect of the inertial sensor bias, the UWB measurement noises, and the limited computational resources. To this end, a composite disturbance filtering (CDF) method is proposed which consists of the disturbance observer for real-time bias compensation, an improved particle filter to deal with the non-Gaussian noises, and a particle size adaptation procedure to release the computation burden. The proposed CDF method represents a refined treatment of the multi-source heterogeneous uncertainties in the relative localization system and strikes a balance between localization accuracy and computational efficiency. The effectiveness of the proposed localization method is validated via both simulation tests and flight experiments.Note to Practitioners—The tiny UAVs are capable of dexterous flight in confined indoor spaces, which makes them especially suitable for the indoor operation tasks such as environment exploration, disaster relief, gas seeking, and meteorological measurement. In these tasks, accurate localization of the tiny UAV is of vital importance. To achieve autonomous localization of the tiny UAV in the GNSS-denied, infrastructure-free, and unstructured indoor environment, an onboard inertial measurement unit (IMU)/UWB fusion-based relative localization scheme is presented. In the presented scheme, a large UAV equipped with UWB anchors is employed to provide position reference for the tiny UAV. To address the multi-source heterogeneous disturbances (the dynamic IMU biases and the non-Gaussian UWB noises) in the localization model and the limited computational resource onboard the tiny UAV, a CDF method with an adaptive sample size is proposed. As demonstrated by the simulation and experiments, the positioning accuracy and computation efficiency of the tiny UAV have been effectively enhanced with the proposed scheme.

One of inescapable challenges in facilitating the application of aerial manipulators is to achieve the high precision control performance of the end-effector. The manipulator motions beneath the UAV platform constantly contend with composite disturbances, such as floating base, strong inner coupling effects, and model uncertainties. These factors collectively contribute to an inadequate control performance. In this paper, a composite control scheme is presented to tackle this issue. Specifically, a joint velocity planner is proposed to handle the base-floating disturbance in kinematic loop. By virtue of the generated joint reference signal, the base-floating disturbance can be effectively alleviated. The tracking error of the end-effector can be ensured within a small set. Moreover, in a complementary manner, neural network (NN) approximation and nonlinear disturbance observer (NDO) compensation are combined to track the joint references. The NN is adopted to estimate composite dynamic model including inner coupling effects and model uncertainties, while the NDO is designed to handle the remaining uncompensated part. The stability of the closed-loop system including the manipulator kinematics and dynamics is guaranteed using the Lyapunov-like method. Experimental results are reported to manifest the effectiveness of the proposed composite control scheme.Note to Practitioners—This work is driven by the precise end-effector control problem of an aerial manipulator subject to base-floating, strong dynamic coupling, and model uncertainties. Most of existing approaches implicitly address this issue by improving the flight performance of the aerial platform. However, the composite disturbances acted on the manipulator, which would deteriorate the operation accuracy of the end-effector, are not systematically addressed. In this work, a composite control scheme is constructed, which consists of the manipulator joint velocity planner and the dynamic controller. The idea is intuitive. The joint velocity is generated to counteract the fluctuation of the aerial platform. Furthermore, the dynamic controller is developed to accurately track the planned joint velocity in the presence of strong coupling and model uncertainties. The proposed scheme guarantees the stability of the close loop system, making our approach especially promising solution for aerial manipulation under composite disturbances.

This article develops a safety-driven distributed cooperative framework (SDDCF) for multiple unmanned aerial vehicles (UAVs) subject to actuator faults in the application of emergency search-and-rescue mission. A capability-triggered decision mechanism is proposed to conquer the challenging situation that the system redundancy cannot satisfy the requirement of fault-tolerant control. By quantitatively analyzing the capability of UAV, a safety threshold is provided, which can be updated adaptively in the light of performance requirement and real-time system capability estimated by a fixed-time fault observer. When the safety threshold is violated, the active performance degradation of the faulty UAVs and communication topology reconfiguration of the multiple UAVs are performed. By virtue of the SDDCF with capability-triggered mechanism, the safety of multiple UAVs system suffering from severe actuator faults is ensured for mission completion. The efficacy of the presented framework is demonstrated by a proof-of-concept emergency search-and-rescue mission in real-world flight experiments. Note to Practitioners—The proposed SDDCF is devoted to reduce the safety risk of multiple UAVs with severe actuator faults in emergency missions, where the mobility and reliability must be balanced carefully. Compared with the existing fault-tolerant control schemes, the SDDCF can ensure the safety even if the actuator faults exceed the system redundancy in a specific mission. Moreover, the practicability of the SDDCF, which can be extended to diverse task scenarios, has been verified in real-world flight experiments. In the future, the abilities of cooperative perception and risk avoidance should be improved to further enhance the safety of multiple UAVs in uncertain environments.

This article addresses issues of covert attacks detection and resilient control of quadcopters. In the presence of generalized covert attacks characterized by strong stealth, passive detection techniques prove to be insufficient. Active detection methods are common solutions to this problem, but the balance between the detection capability and the stability of quadcopters still remains as a challenge. Different from the existing active attack detection methods, a coding and channel switching approach and its matched resilient controller for quadcopters are proposed. First, the design and detectability analysis of the coding-based attack detection method are given. Once covert attacks revealed, a secure channel is activated to replace the attacked channel. Second, to enhance quadcopter resilience against covert attacks, a resilient control framework is proposed. It incorporates attack effect estimation and compensation via a fixed-time observer. This framework maintains the stability of the quadcopter's control system under covert attacks. Finally, the numerical simulation and real-world experiments are conducted to evaluate the effectiveness and feasibility of the proposed scheme.

The avoidance of dynamic obstacles is a challenging issue for uncrewed aerial vehicle (UAV) due to its limited perception range.This article presents a framework including cooperative warning and risk-averse safety control for multiple UAVs. When external obstacles are discovered, the evaluation of conditional value-at-risk for the obstacles is performed by the discoverers. Whenever the risk value violates the designed safety threshold, the warning information will be transmitted to the threatened neighbors immediately. Moreover, by incorporating the event-triggered mechanism, the risk-averse safety control scheme is constructed. Consequently, multiple UAVs are able to evade dynamic obstacles from various directions with enhanced safety and reduced conservatism. The effectiveness and superiority of the proposed scheme are substantiated by comparative simulations and real-world flight experiments.

This article presents a bio-inspired safety control scheme for unmanned aerial vehicles (UAVs) in confined environments with disturbance. Although there has been some existing research on the effect of disturbance for a single UAV, multi-UAV formation under external wind disturbances remains challenging, especially in a tight and confined environment. Inspired by nature, this study concentrates on an anti-disturbance mechanism for safe multi-UAV formation in a tight environment. The presented safety control system combines disturbance observer-based control (DOBC), bionic formation switching (BFS) strategy, and safety evaluation. Two safety issues are considered in this article. For a single UAV, the estimated disturbance is compensated in the inner-loop controller. While for multi-UAV formation, the BFS strategy attenuates the effect of external wind disturbance leveraging the formation configuration. The so-called group perturbation immune factor (GPIF) is designed to analyze and evaluate the safety of the overall formation. The experimental results validate the comprehensiveness and anti-disturbance capability of the system.

In nature, when encountering unexpected uncertainty, animals tend to react quickly to ensure safety as the top priority, and gradually adapt to it based on recent valuable experience. We present a framework, namely EVOLutionarymodel-baseduncertainty obserVER (EVOLVER), to mimic the bio-behavior for robotics to achieve rapid transient reaction ability and high-precision steady-state performance simultaneously. In particular, the Koopman operator is leveraged to explore the latent structure of internal and external disturbances, which is subsequently utilized in anevolutionarymodel-based disturbance observer to estimate the eventual disturbance. The resulting observer can guarantee a provable convergence in optimal conditions. Several practical considerations, including construction of a training dataset, data noise handling, and lifting functions selection, are elaborated in pursuit of the theoretical optimality in real applications. The lightweight feature of our framework enables online computation, even on a microprocessor (STM32F7 with 100 Hz control frequency). The framework is thoroughly evaluated by one simulation and three experiments. The experimental scenarios include: 1) Trajectory prediction of an irregular free-flying object subject to aerodynamic drag, 2) indoor and outdoor agile flights of a quadrotor subject to wind gust, and 3) high-precision end-effector control of a manipulator subject to base moving disturbance. Comparison results show that the performance of our proposed EVOLVER is superior to several state-of-the-art model-based and learning-based schemes.

Achieving accurate control performance of the end-effector is critical for practical applications of aerial manipulator. However, due to the presence of floating-base disturbance from the unmanned aerial vehicle (UAV) platform and the kinematic error amplification effect from multilink structure of the manipulator, it is extremely challenging to ensure the high-precision performance of aerial manipulator. Building upon the philosophy of disturbance rejection, we propose a predictive optimization scheme that allows aerial manipulator to successfully execute millimeter-level flying pick and peg-in-hole task. First, the error amplification effect of the floating base is quantitatively analyzed by virtue of the aerial manipulator kinematics. Intuitively, it is found that if the further motion of the UAV platform is well predicted, the manipulator can directly counteract the floating disturbance by following a modified reference trajectory. Hence, a learning-based prediction approach is leveraged to rapidly forecast the UAV platform motion online. Subsequently, an optimization controller is formulated to follow the reference trajectory by incorporating multiple practical constraints of aerial manipulator. Flight tests demonstrate that this study goes a step further to achieve higher accuracy of the end-effector than the existing results (centimeter-level).

This article considers the safety control problem of a quadrotor unmanned aerial vehicle (UAV) subject to actuator faults and external disturbances, based on the quantization of system capability and safety margin. First, a trajectory function is constructed online with backpropagation of system dynamics. Therefore, a degraded trajectory is gracefully regenerated, via the tradeoff between the remaining system capability and the expected derivatives (velocity, jerk, and snap) of the trajectory. Second, a control-oriented model is established into a form of strict feedback, integrating actuator malfunctions and disturbances. Therefore, a retrofit dynamic surface control (DSC) scheme based on the control-oriented model is developed to improve the tracking performance. When comparing to the existing control methods, the compensation ability is analyzed to determine whether the faults and disturbances can be handled or not. Finally, simulation and experimental studies are conducted to highlight the efficiency of the proposed safety control scheme.

Malware, exposed on the ground control station, can tamper with the unmanned aerial vehicles (UAVs) interaction information. It makes UAVs vulnerable to the desired trajectory attacks, which deteriorates the flight safety if no timely action is taken. Therefore, this article focus on fast reactive mechanism for desired trajectory attacks on UAVs. A fixed-time detection scheme is proposed based on fixed-time unknown inputs observer and trajectory tracking errors. Subsequently, a fixed-time sliding mode attack observer is developed to compensate the effect caused by attacks. Meanwhile, the estimation errors of attacks can be stabilized within fixed time. Finally, experiment tests are presented to demonstrate the effectiveness of the proposed methods.

This article investigates the moving-target circular formation control problem for multiple nonholonomic vehicles under a directed graph. First, a novel moving-target enclosing control scheme is proposed by using the feedback linearization approach, in which the design procedure of the cooperative controller is more straightforward. Compared with the existing literature, the designed controller relaxes some existing constraints and the corresponding stability analysis is more concise. Second, based on the distance measurements, the observers, including sliding-mode observer and relative position observer, are designed to estimate the relative position so that the global position measurements are not required. Therefore, the observer-based controller becomes more suitable for practical application. Numerical simulations are conducted to illustrate the effectiveness of the proposed controllers.

This puts forth an infrastructure-free cooperative relative localization (RL) for unmanned aerial vehicles (UAVs) in global positioning system (GPS)-denied environments. Instead of estimating relative coordinates with vision-based methods, an onboard ultra-wideband (UWB) ranging and communication (RCM) network is adopted to both sense the inter-UAV distance and exchange information for RL estimation in 2-D spaces. Without any external infrastructures prepositioned, each agent cooperatively performs a consensus-based fusion, which fuses the obtained direct and indirect RL estimates, to generate the relative positions to its neighbors in real time despite the fact that some UAVs may not have direct range measurements to their neighbors. The proposed RL estimation is then applied to formation control. Extensive simulations and real-world flight tests corroborate the merits of the developed RL algorithm.

In this paper we propose a method to achieve relative positioning and tracking of a target by a quadcopter using Ultra-wideband (UWB) ranging sensors, which are strategically installed to help retrieve both relative position and bearing between the quadcopter and target. To achieve robust localization for autonomous flight even with uncertainty in the speed of the target, two main features are developed. First, an estimator based on Extended Kalman Filter (EKF) is developed to fuse UWB ranging measurements with data from onboard sensors including inertial measurement unit (IMU), altimeters and optical flow. Second, to properly handle the coupling of the target's orientation with the range measurements, UWB based communication capability is utilized to transfer the target's orientation to the quadcopter. Experiments results demonstrate the ability of the quadcopter to control its position relative to the target autonomously in both cases when the target is static and moving.