Common vulnerabilities in typical intelligent cyber-physical systems such as unmanned aerial vehicles (UAVs) can be easily exploited by cyber attackers to cause serious accidents and harm. For successful UAV operations, security against cyber attacks is imperative. In this paper, we propose a modified sliding innovation sequences (MSIS) detector, based on the extended Kalman filter optimal state estimation, for a dynamic quadrotor system to detect cyber attacks inflicted on both its actuators and sensors in real time. These cyber attacks include random attacks, false data injection (FDI) attacks and denial-of-service (DoS) attacks. The MSIS detector computes the operator norm of the normalized innovation (residual) sequence within a sliding time window and triggers the alarm if the value is above the preset threshold. For a quadrotor undergoing rapid turns in a complex trajectory, the detector observes a reduced false alarm rate as compared to other state estimation-based detectors. To address the initial estimation error problem, we implement an iteration procedure to initiate and calibrate the detector. By evaluating the sample covariance of the normalized innovation sequence, the MSIS detector has the capability to isolate cyber attacks. Finally, simulation results of a quadrotor in a periodic, complex trajectory flight are provided to verify the effectiveness of the MSIS detection and isolation method.

Equipping drones with target search capabilities is highly desirable for applications in disaster rescue and smart warehouse delivery systems. Multiple intelligent drones that can collaborate with each other and maneuver among obstacles show more effectiveness in accomplishing tasks in a shorter amount of time. However, carrying out collaborative target search (CTS) without prior target information is extremely challenging, especially with a visual drone swarm. In this work, we propose a novel data-efficient deep reinforcement learning (DRL) approach called adaptive curriculum embedded multistage learning (ACEMSL) to address these challenges, mainly 3-D sparse reward space exploration with limited visual perception and collaborative behavior requirements. Specifically, we decompose the CTS task into several subtasks including individual obstacle avoidance, target search, and inter-agent collaboration, and progressively train the agents with multistage learning. Meanwhile, an adaptive embedded curriculum (AEC) is designed, where the task difficulty level (TDL) can be adaptively adjusted based on the success rate (SR) achieved in training. ACEMSL allows data-efficient training and individual-team reward allocation for the visual drone swarm. Furthermore, we deploy the trained model over a real visual drone swarm and perform CTS operations without fine-tuning. Extensive simulations and real-world flight tests validate the effectiveness and generalizability of ACEMSL. The project is available at https://github.com/NTU-UAVG/CTS-visual-drone-swarm.git.

Drones, as advanced cyber-physical systems (CPSs), are undergoing a transformative shift with the advent of vision-based learning, a field that is rapidly gaining prominence due to its profound impact on drone autonomy and functionality. Unlike existing task-specific surveys, this work offers a comprehensive overview of vision-based learning for drones, emphasizing its pivotal role in enhancing their operational capabilities across various scenarios. First, the fundamental principles of vision-based learning are elucidated, demonstrating how it significantly improves drones’ visual perception and decision-making processes. Vision-based control methods are then categorized into indirect, semidirect, and end-to-end approaches from the perception-control perspective. Various applications of vision-based drones with learning capabilities are further explored, ranging from single-agent systems to more complex multiagent and heterogeneous system scenarios, while highlighting the challenges and innovations characterizing each domain. Finally, open questions and potential solutions are discussed to guide future research and development in this dynamic and rapidly evolving field. With the growth of large language models (LLMs) and embodied intelligence, vision-based learning for drones provides a promising yet challenging road toward achieving artificial general intelligence (AGI) in the 3-D physical world.

Various quadrotor drones have been developed in recent years, mainly focusing on either improving maximum thrust per platform area or flight maneuverability. Evidently, achieving both advantages simultaneously is a challenging task, since they call for opposing rotor requirements. Specifically, improving the drone's maximum thrust per platform area mainly requires reducing the number of rotors to make way for larger and more powerful rotors. While this can be an effective method to increase overall thrust, improving flight maneuverability requires a greater number of rotors to generate larger rotating torques or to increase the thrust vectoring capability. To address this challenge, we design a novel coaxial drone with two contra-rotating rotors for high thrust efficiency while enabling independent dual-axis rotor rotation to maintain maneuverability along the roll and pitch axes. The thrust vectoring capability is provided by two dedicated servo motors connected vertically in series with the coaxial propellers to produce a compact and elongated fuselage frame. A nonlinear flight model in six degrees of freedom is developed for the underactuated system, incorporating four control inputs from the two propellers and servos respectively. Consequently, a nonlinear control allocation approach is proposed such that the drone can produce a desired control force and yaw torque to stabilize the drone's position and yaw angle. For the uncontrolled roll and pitch dynamics, a damping component is added such that the roll and pitch angular velocities can also be stabilized. Both numerical simulations and real experiments are conducted to validate the design of the drone and the effectiveness of the proposed control strategy.

In a global positioning system (GPS)-denied environment, unmanned aerial vehicles (UAVs) rely on local sensing-based formation maneuvering approaches for collective motion. To improve mission efficiency by reducing the total sensing requirements on all UAVs, this article proposes a leader–follower formation maneuvering framework with two leaders, where the followers will track the two leaders and maintain a desired angle-constrained formation with respect to the leaders using direction-only measurements, i.e., removing the need for inter-UAV distance measurements for the followers. To enable the UAV formation to maneuver in translation, rotation, and scaling simultaneously, the desired formation shape is specified by a set of interior angle constraints. By assigning each UAV’s yaw angle and position as the four controllable variables, an estimation-based attitude control algorithm is designed. For the UAVs’ position control, the designed formation maneuvering algorithm consists of a velocity tracking part and a formation shape control part that enables the first leader UAV to control the translational maneuvering, the second leader UAV to control the rotational and scaling maneuvering, and all the follower UAVs to maintain the formation shape. Simulations and experiments on UAVs’ formation maneuvering are conducted to illustrate the effectiveness of the proposed approach.

Safe navigation of drones in the presence of adversarial physical attacks from multiple pursuers is a challenging task. This paper proposes a novel approach, asynchronous multistage deep reinforcement learning (AMS-DRL), to train adversarial neural networks that can learn from the actions of multiple evolved pursuers and adapt quickly to their behavior, enabling the drone to avoid attacks and reach its target. Specifically, AMS-DRL evolves adversarial agents in a pursuit-evasion game where the pursuers and the evader are asynchronously trained in a bipartite graph way during multiple stages. Our approach guarantees convergence by ensuring Nash equilibrium among agents from the game-theory analysis. We evaluate our method in extensive simulations and show that it outperforms baselines with higher navigation success rates. We also analyze how parameters such as the relative maximum speed affect navigation performance. Furthermore, we have conducted physical experiments and validated the effectiveness of the trained policies in real-time flights. A success rate heatmap is introduced to elucidate how spatial geometry influences navigation outcomes. Project website: https://github.com/NTU-ICG/AMS-DRL-for-Pursuit-Evasion .