Wilderness search and rescue entails performing a wide-range of work in complex environments and large regions. Given the concerns inherent in large regions due to limited rescue distribution, unmanned aerial vehicle (UAV)-based frameworks are a promising platform for providing aerial imaging. In recent years, technological advances in areas such as micro-technology, sensors and navigation have influenced the various applications of UAVs. In this study, an all-in-one camera-based target detection and positioning system is developed and integrated into a fully autonomous fixed-wing UAV. The system presented in this paper is capable of on-board, real-time target identification, post-target identification and location and aerial image collection for further mapping applications. Its performance is examined using several simulated search and rescue missions, and the test results demonstrate its reliability and efficiency.

Having an exciting array of applications, the scope of unmanned aerial vehicle (UAV) application could be far wider one if its flight endurance can be prolonged. Solar-powered UAV, promising notable prolongation in flight endurance, is drawing increasing attention in the industries’ recent research and development. This work arose from a Bachelor’s degree capstone project at Hong Kong Polytechnic University. The project aims to modify a 2-metre wingspan remote-controlled (RC) UAV available in the consumer market to be powered by a combination of solar and battery-stored power. The major objective is to greatly increase the flight endurance of the UAV by the power generated from the solar panels. The power system is first designed by selecting the suitable system architecture and then by selecting suitable components related to solar power. The flight control system is configured to conduct flight tests and validate the power system performance. Under fair experimental conditions with desirable weather conditions, the solar power system on the aircraft results in 22.5% savings in the use of battery-stored capacity. The decrease rate of battery voltage during the stable level flight of the solar-powered UAV built is also much slower than the same configuration without a solar-power system.

This paper focuses on the transition process optimization for a vertical takeoff and landing (VTOL) tail-sitter unmanned aerial vehicle (UAV). For VTOL UAVs that can fly with either hover or cruise mode, transition refers to the intermediate phases between these two modes. This work develops a transition strategy with the trajectory optimization method. The strategy is a reference maneuver enabling the vehicle to perform transition efficiently by minimizing the cost of energy and maintaining a small change of altitude. The simplified 3-degree-of-freedom (3-DOF) longitudinal aerodynamic model is used as a dynamic constraint. The transition optimization problem is then modeled by nonlinear programming (NLP) and solved by the collocation method to obtain the reference trajectory of the pitch angle and throttle offline. Simulations with the Gazebo simulator and outdoor flight experiments are carried out with the optimized forward (hover-cruise) and backward (cruise-hover) transition solutions. The simulation and experimental results show that the optimized transition strategy enables the vehicle to finish transition with less time and change of altitude compared with that by using traditional linear transition methods.

The ever-burgeoning growth of autonomous unmanned aerial vehicles (UAVs) has demonstrated a promising platform for utilization in real-world applications. In particular, a UAV equipped with a vision system could be leveraged for surveillance applications. This paper proposes a learning-based UAV system for achieving autonomous surveillance, in which the UAV can be of assistance in autonomously detecting, tracking, and following a target object without human intervention. Specifically, we adopted the YOLOv4-Tiny algorithm for semantic object detection and then consolidated it with a 3D object pose estimation method and Kalman filter to enhance the perception performance. In addition, UAV path planning for a surveillance maneuver is integrated to complete the fully autonomous system. The perception module is assessed on a quadrotor UAV, while the whole system is validated through flight experiments. The experiment results verified the robustness, effectiveness, and reliability of the autonomous object tracking UAV system in performing surveillance tasks. The source code is released to the research community for future reference.

A dynamic model that considers both linear and complex nonlinear effects extensively benefits the model-based controller development. However, predicting a detailed aerodynamic model with good accuracy for unmanned aerial vehicles (UAVs) is challenging due to their irregular shape and low Reynolds number behavior. This work proposes an approach to model the full translational dynamics of a quadrotor UAV by a feedforward neural network, which is adopted as the prediction model in a model predictive controller (MPC) for precise position control. The raw flight data are collected by tracking various pre-designed trajectories with PX4 autopilot. The neural network model is trained to predict the linear accelerations from the flight log. The neural network-based model predictive controller is then implemented with the automatic control and dynamic optimization toolkit (ACADO) to achieve real-time online optimization. Software in the loop (SITL) simulation and indoor flight experiments are conducted to verify the controller performance. The results indicate that the proposed controller leads to a 40% reduction in the average trajectory tracking error compared to the traditional PID controller.

This paper presents a model predictive controller (MPC) for position control of a vertical take-off and landing (VTOL) tail-sitter unmanned aerial vehicle (UAV) in hover flight. A ‘cross’ configuration quad-rotor tail-sitter UAV is designed with the capabilities for both hover and high efficiency level flight. The six-degree-of-freedom (DOF) nonlinear dynamic model of the UAV is built based on aerodynamic data obtained from wind tunnel experiments. The model predictive position controller is then developed with the augmented linearized state-space model. Measured and unmeasured disturbance model are introduced into the modeling and optimization process to improve disturbance rejection ability. The MPC controller is first verified and tuned in the hardware-in-loop (HIL) simulation environment and then implemented in an on-board flight computer for real-time indoor experiments. The simulation and experimental results show that the proposed MPC position controller has good trajectory tracking performance and robust position holding capability under the conditions of prevailing and gusty winds.