Unmanned Aerial Vehicles (UAVs) play a vital role in military warfare. In a variety of battlefield mission scenarios, UAVs are required to safely fly to designated locations without human intervention. Therefore, finding a suitable method to solve the UAV Autonomous Motion Planning (AMP) problem can improve the success rate of UAV missions to a certain extent. In recent years, many studies have used Deep Reinforcement Learning (DRL) methods to address the AMP problem and have achieved good results. From the perspective of sampling, this paper designs a sampling method with double-screening, combines it with the Deep Deterministic Policy Gradient (DDPG) algorithm, and proposes the Relevant Experience Learning-DDPG (REL-DDPG) algorithm. The REL-DDPG algorithm uses a Prioritized Experience Replay (PER) mechanism to break the correlation of continuous experiences in the experience pool, finds the experiences most similar to the current state to learn according to the theory in human education, and expands the influence of the learning process on action selection at the current state. All experiments are applied in a complex unknown simulation environment constructed based on the parameters of a real UAV. The training experiments show that REL-DDPG improves the convergence speed and the convergence result compared to the state-of-the-art DDPG algorithm, while the testing experiments show the applicability of the algorithm and investigate the performance under different parameter conditions. 相似文献
In this paper, the relative sliding motion between the target and the manipulator’s end-effector is considered and characterized as a unilateral contact constraint. A new possible solution is presented to estimate the inertial parameters of a non-cooperative target while the relative sliding motion exists. First, the detailed analysis of the dynamical model is presented, and a parameter-explicit linear time-varying model is obtained. Then, an extended state observer is constructed based on the new model, which can effectively estimate the unknown inertial parameters of the target when relative sliding motion exists. As the modified reactionless controller requires the knowledge of inertial parameters, a hybrid post-capture control scheme is also established based on the switch law between different controllers. The correctness and efficiency of the proposed algorithm are validated by numerical simulation, which proves a potential framework for the non-cooperative target post-capture operation. 相似文献