Search

This paper focuses on the three-dimensional guidance strategy for a reusable launching vehicle (RLV) during terminal area energy management (TAEM) phase. Based on sliding mode and shrinking horizon techniques, the proposed scheme consists of trajectory generation and correction mechanisms, which can enhance the guidance precision and robustness against disturbances. The RLV guidance model, in the form of a set of highly non-linear differential equations in time-domain, is recast as an altitude-domain model. By this means, the main characteristics of TAEM gliding motion are extracted. The altitude-domain model is thereby used for trajectory generation. A sliding surface and guidance law are proposed. Hybrid TAEM constraints can be fully satisfied when the proposed guidance law drives the altitude-domain vehicle model to the designated altitude. Using the proposed guidance law as the input of altitude-domain model, a constrained TAEM trajectory is generated, leading to TAEM guidance commands simultaneously. The commands are utilized to drive the time-domain model to the terminal target. In an attempt to compensate for model uncertainties and initial deviations, the guidance commands are modified periodically by shrinking-horizon correction mechanism according to current states. Simulations on different scenarios are provided to demonstrate the performance of the proposed guidance strategy.

This paper presents a disturbance observer-based adaptive sliding mode control (SMC) strategy for a quadrotor helicopter subject to multiple actuator faults, parametric uncertainties, and external disturbances. Unlike most of the existing control strategies for quadrotor helicopters, actuator faults, parametric uncertainties, and external disturbances can be simultaneously compensated within the proposed control scheme. Firstly, by employing the adaptive control parameters in both continuous and discontinuous control parts, the proposed control strategy can generate appropriate control signals to accommodate actuator faults and parametric uncertainties without merely relying on the robust discontinuous control strategy of SMC. Then, a nonlinear disturbance observer is designed and integrated to attenuate external disturbances while keeping the small value of the discontinuous control gain of SMC. In addition, the stability analysis of the proposed control strategy is given, showing that the presented controller can ensure system tracking performance and make the tracking errors arbitrarily small under the concerned situation. The effectiveness of the proposed control strategy is demonstrated through comparative numerical simulations and experimental tests of a quadrotor helicopter under different faulty and uncertain scenarios.

Sensor faults could occur in unmanned aerial vehicles (UAVs) during a mission of flight, which might deteriorate UAV’s performance or even cause catastrophe. Considering different types of sensor faults of a quadrotor UAV, a new fault detection and classification method based on time-frequency analysis (TFA) and deep learning (DL) technologies is proposed in this paper. Firstly, the data sets including different types of sensor fault in time-domain are generated randomly. The date sets are then transformed into time-frequency domain by short-time Fourier transform (STFT), resulting in time-frequency graph (TFG). Secondly, the time-frequency graph sets are used to train the deep network, by which the fault type can be rapidly classified with high accuracy. Finally, the simulations are carried out to verify the performance of the proposed algorithm and the accuracy reaches to 99.6%.

The soft landing of the Mars lander is one of the key problems of Mars exploration. The lander’s dynamic equation is nonlinear and is restricted by various constraints. Analytical solution is hard to be obtained. This paper focuses on planning the Mars landing trajectory by the Gauss pseudo-spectral method. The motion equations during the landing stage is firstly established. The trajectory optimization problem is then established with consideration to dynamic constraints, terminal state constraints, and landing site constraints. The control variables and state variables are discretized using Gauss pseudo-spectral method. Thereby a large-scale sparse nonlinear programming problem is formulated. The problem is then solved by SNOPT solver based on sequential quadratic programming algorithm. Simulation results show the efficiency of the proposed method.

Aiming at the problems that carrying out forest fire monitoring and fighting missions by using the Rapidly-exploring Randomized Tree (RRT) algorithm to plan paths cannot adapt to the autonomous movement of an Unmanned Aerial Vehicle (UAV) and that high-order dynamic characteristics may mutate during the mission, this paper investigates a trajectory generation algorithm based on the integration of the RRT algorithm and the minimum snap algorithm. First, the RRT algorithm is used to generate the initial path, then the minimum snap algorithm is used to smooth the initial path and obtain a trajectory suitable for the actual flight of the UAV. However, because the UAV is considered as a particle in the simulation, during the actual flight, this trajectory may not guarantee the safe flight of the UAV and may cause the UAV to collide with an obstacle or other nearby UAVs in the cases of formation flight. To solve this problem, flight corridor concept is used to limit the UAV’s flight trajectory for ensuring the safe flight of the UAV. Simulation results show that the algorithm can effectively ensure the safety, smoothness, feasibility, and trajectory of unmanned aerial vehicles.

This paper proposes a new type of forest firefighting method. When one or more suspected fire spots are found in the forest, the firefighting Unmanned Aerial Vehicles (UAVs) can safely and quickly reach the desired location, conduct a thorough investigation of the suspected fire spots. If a fire occurs, it is necessary to drop firefighting materials to put out the fire. At the same time, considering the characteristics of limited endurance and low load capability have always limited the applications of UAVs, Unmanned Ground Vehicles (UGVs) are considered in this paper as an additional and comprehensive problem solution to provide energy and supplement materials for UAVs. In order to enable firefighting UAV to plan a safe and effective path in real time in the complex forest environment, a new improved D*Lite algorithm is proposed for UAVs in the mission team. Even when the 3D workspace is partially known or completely unknown, the algorithm can plan an effective path so that the firefighting UAV can move to the fire spots and UGV in real time.

Forest resources safety is of paramount importance for natural and public security. Forest fire detection methods have been attracted much attention recently, but the performance in terms of comprehensiveness, rapidity, and accuracy is still not satisfactory. A deep learning fire detection algorithm is proposed in this paper, aiming at improving the detection accuracy and efficiency by using the unmanned aerial vehicle (UAV). A large-scale YOLOv3 network is firstly developed which can ensure the detection accuracy. The algorithm is then applied to UAV forest fire detection (UAV-FFD) platform, where the fire images can be captured by the UAV and transmitted to the ground-station in real time. The testing results indicate that the recognition rate of the detection algorithm is about 91%, and the frame rate can reach up to 30 FPS (Frames Per Second). It shows strong potential in real-time application for precision forest fire detection.

A terminal area energy management (TAEM) guidance system for an unpowered reusable launch vehicle (RLV) is proposed in this paper. The mathematical model representing the RLV gliding motion is provided, followed by a transformation of extracting the required dynamics for reference profile generation. Reference longitudinal profiles are conceived based on the capability of maximum dive and maximum glide that a RLV can perform. The trajectory is obtained by iterating the motion equations at each node of altitude, where the angle of attack and the flight-path angle are regarded as regulating variables. An onboard ground-track predictor is constructed to generate the current range-to-go and lateral commands online. Although the longitudinal profile generation requires pre-processing using the RLV aerodynamics, the ground-track prediction can be executed online. This makes the guidance scheme adaptable to abnormal conditions. Finally, the guidance law is designed to track the reference commands. Numerical simulations demonstrate that the proposed guidance scheme is capable of guiding the RLV to the desired touchdown conditions.

Reusable launch vehicle (RLV) is designed as one kind of the second generation launch vehicles, which can launch payloads to outer space frequently and return back to the earth like an aircraft. A reliable guidance and control system for terminal area energy management (TAEM) phase is of paramount importance to ensure a safe return. This paper presents a TAEM guidance and control (TAEM G&C) approach. Within the proposed scheme, off-line trajectory, task management, guidance law, control law, and 6-DOF RLV model are included. The developed TAEM G&C system is able to ensure the RLV safely return to the terminal end point from an arbitrary entry point in a specific range. Numerical simulation is conducted to evaluate the efficiency of the performance of the TAEM G&C system.

Unmanned aerial vehicles (UAVs) are increasingly being used in forest fire monitoring and detection thanks to their high mobility and ability to cover areas at different altitudes and locations with relatively lower cost. Traditional fire detection algorithms are mostly based on the RGB color model, but their speed and accuracy need further improvements. This paper proposes a forest fire detection algorithm by exploiting YOLOv3 to UAV-based aerial images. Firstly, a UAV platform for the purpose of forest fire detection is developed. Then according to the available computation power of the onboard hardware, a small-scale of convolution neural network (CNN) is implemented with the help of YOLOv3. The testing results show that the recognition rate of this algorithm is about 83%, and the frame rate of detection can reach more than 3.2 fps. This method has great advantages for real-time forest fire detection application using UAVs.

Forest fires are very dangerous. Once they become disasters, it is very difficult to extinguish. In this paper, an unmanned aerial vehicle (UAV) image-based forest fire detection approach is proposed. Firstly, the local binary pattern (LBP) feature extraction and support vector machine (SVM) classifier are used for smoke detection, so as to make a preliminary discrimination of forest fire. In order to accurately identify it in the early stage of the fire, according to the convolutional neural network (CNN), it has the characteristics of reducing the number of parameters and improving the training performance through local receptive domain, weight sharing and pooling. This paper proposes another method for detecting forest fires in convolutional neural networks. Image preprocessing operations such as histogram equalization and smooth low-pass filtering are performed prior to inserting the image into the CNN network. The effectiveness of the proposed method is verified by detecting real forest fire images.

The samples representing abnormal situation is usually very few in the dataset, which makes it difficult to learn the features of abnormal samples by machine-learning-based methods. To improve the accuracy of anomaly detection, the number of abnormal samples should be expanded to ensure the balance of the dataset. In this paper, a discrete synthetic minority oversampling technique (D-SMOTE) is proposed to generate new samples. A closed area is constructed using the three nearest abnormal samples in the dataset. The new samples are then uniformly interpolated in a closed area. By this means, the problem of the imbalance for the original dataset is handled, thus improving the data quality. Based on the expanded datasets, a two-dimensional convolutional neural network (2D CNN) is constructed to detect abnormal samples. In experiments, three cases and different machine learning methods are considered for comparison. Several indexes including accuracy, precision, confusion matrix, F1-score, and Recall have been used to evaluate the detection effectiveness. The results show that the abnormal samples can be detected accurately using oversampling data obtained from the proposed D-SMOTE method.

This paper presents a dual adaptive fault-tolerant control strategy for a quadrotor helicopter based on adaptive sliding mode control and adaptive boundary layer. Within the proposed adaptive control strategy, both model uncertainties and actuator faults can be compensated without the knowledge of the uncertainty bounds and fault information. By virtue of the proposed adaptive control scheme, the minimum discontinuous control gain is adopted, which significantly reduces the control chattering effect. As compared to the existing adaptive sliding mode control schemes in the literature, larger actuator faults can be tolerated by employing the proposed control scheme while suppressing control chattering. Moreover, boundary layer is used to smoothen control discontinuity and further eliminate control chattering. Nevertheless, the choice of boundary layer thickness is a trade-off between system stability and tracking accuracy. By explicitly considering this fact, an adaptive boundary layer is developed and synthesized with the proposed adaptive control framework to ensure stability and tracking accuracy of the considered system. When the control parameter tends to be overestimated, the thickness of boundary layer can be appropriately adjusted to avoid control parameter overestimation. Simulation and experimental tests of a quadrotor helicopter are both conducted to validate the effectiveness of the proposed control scheme. Its advantages are demonstrated in comparison with a conventional adaptive sliding mode control scheme.

A sliding mode terminal guidance strategy is developed for an unpowered reusable launch vehicle (RLV) during the terminal area energy management (TAEM) phase. The main idea is to use the finite-time reaching phase of the sliding mode method to solve the three-dimensional (3D) guidance problem with multiple flight constraints. Firstly, the mathematical model of a RLV in the altitude domain is provided, based on which a new sliding surface is constructed to account for multiple constraints on terminal conditions and dynamic pressure profile. Subsequently, a second-order sliding mode guidance law is constructed to ensure the reaching of the sliding surface at a specific altitude. Finally, the effectiveness of the proposed guidance strategy in both nominal case and the case of bank limitations is illustrated by the numerical simulations.

As a exible, efficient, and powerful platform for a variety of practical applications, the unmanned aerial vehicle (UAV) has attracted increasing attention in the field of forest re monitoring, detection, and tracking in recent years. Generally, more complicated and heavier tasks can be achieved by using a team of UAVs other than a single UAV. However, a possible problem is that faults may occur on a UAV in the formation or the power may gradually run out during the task, so that the disabled UAV must be replaced by a newly assigned UAV from the base. Hence, the problem becomes how to guide the new UAV to join the team in an optimal manner, and then to maintain the formation during the remaining task. Meanwhile, collision avoidance should be involved to avoid hazardous impacts from other formation members during the whole mission. To solve these challenges, an automated maneuvering decision strategy consisting of a tailored scoring function and a game tree decision algorithm is developed in this study. The newly assigned UAV can be guided to join the patrol team from arbitrary initial locations, and the formation can be maintained during the patrol task in the presence of disturbances. Numerical simulations are conducted to validate the proposed decision strategy.

A sliding mode guidance strategy is developed for an unpowered reusable launch vehicle (RLV) during the terminal area energy management (TAEM) phase. The 3-DOF guidance model of a RLV in the domain of altitude is firstly provided, based on which a new sliding surface is constructed to account for multiple constraints on terminal conditions and dynamic pressure profile during flight. A second-order sliding mode guidance law is then developed to ensure the reaching of the sliding surface at a specific altitude. The simulation results confirm the effectiveness of the proposed method.

A three-dimensional trajectory planning algorithm is proposed for the terminal area energy management (TAEM) phase of an unpowered reusable launch vehicle (RLV). Firstly, a reference dynamic pressure profile which characterizes the longitudinal motion is conceived on the basis of the maximum dive and maximum glide capabilities. Secondly, a reference ground-track path is developed, which is composed of four flight segments determined by the location, the size, and the turning mode of a heading alignment cone. Then, the RLV motion equations modeled by kernel extraction protocol (KEP) are numerically solved via secant iteration method, according to the knowledge of the pre-designed dynamical pressure profile and the ground-track path. Finally, a down-track correction scheme is designed to correct the down-track position along the runway centerline. Numerical simulations are conducted to illustrate the effectiveness of the proposed trajectory planning algorithm.

Sliding mode control is known as a robust control approach to maintain system performance and keep it insensitive to disturbances. This paper proposes an integral sliding mode based adaptive robust control for a quadrotor helicopter with parametric uncertainties and disturbances. With the help of the synthesized on-line adaptive scheme, the uncertain parameters can be accurately estimated without the knowledge of the uncertainty bounds. In this case, there is no need to increase the discontinuous control gain, which may stimulate control chattering effect, to maintain the robustness of the controller. The effectiveness of the proposed control strategy is validated through a simulation of the payload transportation application. Compared to the commonly used linear quadratic regulator (LQR) approach, the proposed adaptive robust control strategy can maintain the tracking performance during the whole flight phase.