Chi Yuan

Unmanned surface vehicles: An overview of developments and challenges

Abstract With growing worldwide interest in commercial, scientific, and military issues associated with both oceans and shallow waters, there has been a corresponding growth in demand for the development of unmanned surface vehicles (USVs) with advanced guidance, navigation and control (GNC) capabilities. This paper presents a comprehensive literature review of recent progress in USVs development. The paper first provides an overview of both historical and recent USVs development, along with some fundamental definitions. Next, existing USVs GNC approaches are outlined and classified according to various criteria, such as their applications, methodologies, and challenges. Finally, more general challenges and future directions of USVs towards more practical GNC capabilities are highlighted.

A Learning-Based Fault Tolerant Tracking Control of an Unmanned Quadrotor Helicopter

This paper presents a novel learning-based fault tolerant tracking control approach by using an extended Kalman filter (EKF) to optimize a Mamdani fuzzy state-feedback tracking controller. First, a robust state-feedback tracking controller is designed as the baseline controller to guarantee the expected system performance in the fault-free condition. Then, the EKF is employed to regulate the shape of membership functions and rules of fuzzy controller to adapt with the working conditions automatically after the occurrence of actuator faults. Next, based on the modified fuzzy membership functions and rules, the baseline controller is readjusted to properly compensate the adverse effects of actuator faults and asymptotically stabilize the closed-loop system. Finally, in order to verify the effectiveness of the proposed method, several groups of numerical simulations are carried out by comparing the performance of a tracking control scheme and the presented technique. Simulation results demonstrate that the proposed method is effective for optimizing the fuzzy tracking controller on-line and counteracting the side effects of actuator faults, and the control performance is significantly improved as well.

UAV-based forest fire detection and tracking using image processing techniques

In this paper, an unmanned aerial vehicle (UAV) based forest fire detection and tracking method is proposed. Firstly, a brief illustration of UAV-based forest fire detection and tracking system is presented. Then, a set of forest fire detection and tracking algorithms are developed including median filtering, color space conversion, Otsu threshold segmentation, morphological operations, and blob counter. The basic idea of the proposed method is to adopt the channel “a” in Lab color model to extract fire-pixels by making use of chromatic features of fire. Numerous experimental validations are carried out, and the experimental results show that the proposed methodology can effectively extract the fire pixels and track the fire zone.

Fault-Tolerant Formation Control of Unmanned Aerial Vehicles in the Presence of Actuator Faults and Obstacles

This paper presents a leader-follower type of fault-tolerant formation control (FTFC) methodology with application to multiple unmanned aerial vehicles (UAVs) in the presence of actuator failures and potential collisions. The proposed FTFC scheme consists of both outer-loop and inner-loop controllers. First, a leader-follower control scheme with integration of a collision avoidance mechanism is designed as the outer-loop controller for guaranteeing UAVs to keep the desired formation while avoiding the approaching obstacles. Then, an active fault-tolerant control (FTC) strategy for counteracting the actuator failures and also for preventing the healthy actuators from saturation is synthesized as the inner-loop controller. Finally, a group of numerical simulations are carried out to verify the effectiveness of the proposed approach.

Aerial Images-Based Forest Fire Detection for Firefighting Using Optical Remote Sensing Techniques and Unmanned Aerial Vehicles.

Due to their fast response capability, low cost and without danger to personnel safety since there is no human pilot on-board, unmanned aerial vehicles (UAVs) with vision-based systems have great potential for monitoring and detecting forest fires. This paper proposes a novel forest fire detection method using both color and motion features for processing images captured from the camera mounted on a UAV which is moving during the whole mission period. First, a color-based fire detection algorithm with light computational demand is designed to extract fire-colored pixels as fire candidate regions by making use of chromatic feature of fire and obtaining fire candidate regions for further analysis. As the pose variations and low-frequency vibrations of UAV cause all objects and background in the images are moving, it is challenging to identify fires defending on a single motion based method. Two types of optical flow algorithms, a classical optical flow algorithm and an optimal mass transport optical flow algorithm, are then combined to compute motion vectors of the fire candidate regions. Fires are thereby expected to be distinguished from other fire analogues based on their motion features. Several groups of experiments are conducted to validate that the proposed method can effectively extract and track fire pixels in aerial video sequences. The good performance is anticipated to significantly improve the accuracy of forest fire detection and reduce false alarm rates without increasing much computation efforts.

Leader-follower formation control of unmanned aerial vehicles with fault tolerant and collision avoidance capabilities

In this paper, a leader-follower formation control of multiple unmanned aerial vehicles (UAVs) design methodology is proposed to keep the desired formation, while simultaneously deal with the potential collision and actuator faults. The proposed formation control is divided into outer-loop and inner-loop controllers. First, a leader-follower control structure is constructed as the outer-loop controller. Then, an adaptive fault tolerant control (FTC) scheme along with a collision avoidance strategy are combined as the inner-loop controller. Simulation validations are conducted to demonstrate the effectiveness of this presented design method.

Active Fault-Tolerant Control of Unmanned Quadrotor Helicopter Using Linear Parameter Varying Technique

By adopting the linear parameter varying (LPV) control technique, this paper presents an active fault-tolerant control (FTC) strategy with application to unmanned quadrotor helicopter (UQH). Adverse effects from payload grasping and dropping caused variations of system dynamics as well as battery drainage induced loss of actuator effectiveness are expected to be counteracted in this study. First, the UQH is manipulated by a well designed baseline controller. In the presence of either payload grasping/dropping or battery drainage, their magnitudes are then obtained from a LPV-based fault detection and diagnosis (FDD) scheme. Next, based on the estimated values, a fault-tolerant tracking controller, which is linear parameter dependent, is devised in a convex polytopic LPV representation schedules to a new status in corresponding to the system variations, so that the negative impacts can be compensated. The parameters that change with system variations are specified as scheduling scalars for the LPV controller, while the ultimate control rule is obtainable by employing a set of well-established linear matrix inequality (LMI) conditions. Finally, both numerical simulations on a nonlinear model of UQH and experiments on a real UQH are conducted so as to testify the effectiveness of proposed methodology.

Adaptive fault-tolerant control of unmanned quadrotor helicopter using linear parameter varying control technique

This paper presents an active fault-tolerant control (FTC) design approach by virtue of an adaptive linear parameter varying (LPV) methodology. In this study, the magnitude of fault is obtained from the results of a fault detection and diagnosis (FDD) scheme. Based on the estimated fault magnitude, a fault-tolerant linear parameter dependent statefeedback controller in a convex polytopic LPV representation format is designed so as to counteract the adverse effects of actuator faults. The parameters that vary with actuator fault magnitudes are specified as design parameters for LPV controller, while the ultimate control law can be obtained using the well-established linear matrix inequality (LMI) conditions. Numerical simulations on an unmanned quadrotor helicopter nonlinear model are carried out to demonstrate the effectiveness of the proposed method.

Vision-based forest fire detection in aerial images for firefighting using UAVs

Due to their rapid maneuverability and improved personnel safety, unmanned aerial vehicles (UAVs) with vision-based systems have great potential for monitoring and detecting forest fires. In this paper, a novel forest fire detection method utilizing both color and motion features is described for UAV-based forest firefighting applications. First, a color decision rule is designed to extract fire-colored pixels as fire candidate regions by making use of chromatic feature of fire. Then, the Horn and Schunck optical flow algorithm is employed to compute motion vectors of the candidate regions. The motion feature is also estimated from the optical flow results to distinguish fire from other fire analogues. Through thresholding and performing morphological operations on the motion vectors, binary images are then obtained. Finally, fires are located in each binary image using the blob counter method. Experiments are conducted, and the experimental results validate that the proposed method can effectively extract and track fire pixels in aerial video sequences. Good performance is expected to significantly improve the accuracy of fire detection and reduce false alarm rates.

Unmanned aerial vehicle based forest fire monitoring and detection using image processing technique

Early forest fire alarm systems are critical in making prompt response in the event of unexpected hazards. Cost-effective cameras, improvements in memory, and enhanced computation power have all enabled the design and real-time application of fire detecting algorithms using light and small-size embedded surveillance systems. This is vital in situations where the performance of traditional forest fire monitoring and detection techniques are unsatisfactory. This paper presents a forest fire monitoring and detection method with visual sensors onboard unmanned aerial vehicle (UAV). Both color and motion features of fire are adopted for the design of the studied forest fire detection strategies. This is for the purpose of improving fire detection performance, while reducing false alarm rates. Indoor experiments are conducted to demonstrate the effectiveness of the studied forest fire detection methodologies.