This article studies an efficient nonlinear model-predictive control (NMPC) scheme for trajectory tracking control of a quadrotor unmanned aerial vehicle (UAV). By augmenting the desired trajectory to a reference dynamical system, we can make the tracking task fit into the standard NMPC framework. In order to alleviate the heavy computational burden caused by solving the corresponding NMPC optimization problem online, we develop an improved continuation/generalized minimal residual ( ${i}\text{C}$ /GMRES) algorithm. Compared with the standard C/GMRES method, the inequality constraint is relaxed by imposing the penalty term on the cost function. To guarantee the closed-loop system stability, we introduce a contraction constraint. Based on the proposed numerical algorithm and the stability constraint, we develop a novel efficient-NMPC algorithm to achieve acceptable control performance with reduced computational complexity. The numerical convergence of ${i}\text{C}$ /GMRES solutions and the closed-loop stability of efficient-NMPC are theoretically analyzed in the presence of the input constraint. Finally, the numerical simulations, software-in-the-loop (SIL) simulations, and the real-time experiment are given to demonstrate the effectiveness of the proposed ${i}\text{C}$ /GMRES algorithm and efficient-NMPC scheme.

With the development of artificial intelligence and integrated sensor technologies, unmanned aerial vehicles (UAVs) are more and more applied in the air combats. A bottleneck that constrains the capability of UAVs against manned vehicles is the autonomous maneuver decision, which is a very challenging problem in the short-range air combat undergoing highly dynamic and uncertain maneuvers of enemies. In this paper, an autonomous maneuver decision model is proposed for the UAV short-range air combat based on reinforcement learning, which mainly includes the aircraft motion model, one-to-one short-range air combat evaluation model and the maneuver decision model based on deep Q network (DQN). However, such model includes a high dimensional state and action space which requires huge computation load for DQN training using traditional methods. Then, a phased training method, called "basic-confrontation", which is based on the idea that human beings gradually learn from simple to complex is proposed to help reduce the training time while getting suboptimal but efficient results. Finally, one-to-one short-range air combats are simulated under different target maneuver policies. Simulation results show that the proposed maneuver decision model and training method can help the UAV achieve autonomous decision in the air combats and obtain an effective decision policy to defeat the opponent.

A key problem in the formation control of homogeneous multiagent systems is the collision-free convergence of the agent positions into a desired formation. It is a typical NP-hard problem by considering the problem as optimizing the assignment of multiple destinations to the same number of agents deployed in an open space. It becomes even harder if the collision avoidance is required during the motion of agents, and thus, a suboptimal but efficient solution is adequate. The traditional methods make it by accurate preplanning of the motion trajectory of each single agent, or simply letting them reach an equilibrium as a tradeoff between the collision avoidance and the desired formation. In this article, a distributed control algorithm embedded with an assignment switch scheme is proposed to guarantee that the asymptotic convergence to the desired formation is achieved with no collisions between agents. By the proposed algorithm, the agents keep moving in straight lines toward their respective destinations until they are going to collide if they do not stop, at which moment the agents will communicate their information locally to switch their destination assignments so that they will continue to move in different directions and avoid potential collisions. Distributed control rules are also defined to confine the motion space of each agent for collision avoidance. It has been rigorously proven that the positions of all agents converge to the desired formation with no collision under random initial deployment. In addition, a detailed parameter design procedure is provided for both setting and controlling of the formation. Finally, Monte Carlo simulations and actual experiments in the outdoor environment are implemented and the results verify the effectiveness of the proposed algorithm.

Autonomous maneuver decision making is the core of intelligent warfare, which has become the main research direction to enable unmanned aerial vehicles (UAVs) to independently generate control commands and complete air combat tasks according to environmental situation information. In this paper, an autonomous maneuver decision making method is proposed for air combat by two cooperative UAVs, which is showcased by using the typical olive formation strategy as a practical example. First, a UAV situation assessment model based on the relative situation is proposed, which uses the real-time target and UAV location information to assess the current situation or threat. Second, the continuous air combat state space is discretized into a 13 dimensional space for dimension reduction and quantitative description, and 15 typical action commands instead of a continuous control space are designed to reduce the difficulty of UAV training. Third, a reward function is designed based on the situation assessment which includes the real-time gain due to maneuver and the final combat winning/losing gain. Fourth, an improved training data sampling strategy is proposed, which samples the data in the experience pool based on priority to accelerate the training convergence. Fifth, a hybrid autonomous maneuver decision strategy for dual-UAV olive formation air combat is proposed which realizes the UAV capability of obstacle avoidance, formation and confrontation. Finally, the air combat task of dual-UAV olive formation is simulated and the results show that the proposed method can help the UAVs defeat the enemy effectively and outperforms the deep Q network (DQN) method without priority sampling in terms of the convergence speed.