In this paper, a novel deep reinforcement learning (DRL) method, and robust deep deterministic policy gradient (Robust-DDPG), is proposed for developing a controller that allows robust flying of an unmanned aerial vehicle (UAV) in dynamic uncertain environments. This technique is applicable in many fields, such as penetration and remote surveillance. The learning-based controller is constructed with an actor-critic framework, and can perform a dual-channel continuous control (roll and speed) of the UAV. To overcome the fragility and volatility of original DDPG, three critical learning tricks are introduced in Robust-DDPG: (1) Delayed-learning trick, providing stable learnings, while facing dynamic environments; (2) adversarial attack trick, improving policy’s adaptability to uncertain environments; (3) mixed exploration trick, enabling faster convergence of the model. The training experiments show great improvement in its convergence speed, convergence effect, and stability. The exploiting experiments demonstrate high efficiency in providing the UAV a shorter and smoother path. While, the generalization experiments verify its better adaptability to complicated, dynamic and uncertain environments, comparing to Deep Q Network (DQN) and DDPG algorithms.

A pursuit–evasion game is a classical maneuver confrontation problem in the multi-agent systems (MASs) domain. An online decision technique based on deep reinforcement learning (DRL) was developed in this paper to address the problem of environment sensing and decision-making in pursuit–evasion games. A control-oriented framework developed from the DRL-based multi-agent deep deterministic policy gradient (MADDPG) algorithm was built to implement multi-agent cooperative decision-making to overcome the limitation of the tedious state variables required for the traditionally complicated modeling process. To address the effects of errors between a model and a real scenario, this paper introduces adversarial disturbances. It also proposes a novel adversarial attack trick and adversarial learning MADDPG (A2-MADDPG) algorithm. By introducing an adversarial attack trick for the agents themselves, uncertainties of the real world are modeled, thereby optimizing robust training. During the training process, adversarial learning was incorporated into our algorithm to preprocess the actions of multiple agents, which enabled them to properly respond to uncertain dynamic changes in MASs. Experimental results verified that the proposed approach provides superior performance and effectiveness for pursuers and evaders, and both can learn the corresponding confrontational strategy during training.

Autonomous motion planning (AMP) of unmanned aerial vehicles (UAVs) is aimed at enabling a UAV to safely fly to the target without human intervention. Recently, several emerging deep reinforcement learning (DRL) methods have been employed to address the AMP problem in some simplified environments, and these methods have yielded good results. This paper proposes a multiple experience pools (MEPs) framework leveraging human expert experiences for DRL to speed up the learning process. Based on the deep deterministic policy gradient (DDPG) algorithm, a MEP–DDPG algorithm was designed using model predictive control and simulated annealing to generate expert experiences. On applying this algorithm to a complex unknown simulation environment constructed based on the parameters of the real UAV, the training experiment results showed that the novel DRL algorithm resulted in a performance improvement exceeding 20% as compared with the state-of-the-art DDPG. The results of the experimental testing indicate that UAVs trained using MEP–DDPG can stably complete a variety of tasks in complex, unknown environments.

In deep reinforcement learning, network convergence speed is often slow and easily converges to local optimal solutions. For an environment with reward saltation, we propose a magnify saltatory reward (MSR) algorithm with variable parameters from the perspective of sample usage. MSR dynamically adjusts the rewards for experience with reward saltation in the experience pool, thereby increasing an agent’s utilization of these experiences. We conducted experiments in a simulated obstacle avoidance search environment of an unmanned aerial vehicle and compared the experimental results of deep Q‐network (DQN), double DQN, and dueling DQN after adding MSR. The experimental results demonstrate that, after adding MSR, the algorithms exhibit a faster network convergence and can obtain the global optimal solution easily.