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.
Inhibitory control dysfunction was considered a universal characteristic of violent offenders. The aim of this study was to examine differences in inhibitory control between two subtypes of violent youth; those displaying predominantly impulsive and those presenting predominantly premeditated aggression (PM). Forty-four juvenile offenders, defined on the basis of the Procedures for the Classification of Aggressive/Violent Acts (Stanford and Barratt, 2001) participated (N = 23: impulsive; N = 21 premeditated). A visual Go/NoGo task was used to compare behavioral responses and event-related potentials (ERPs) between groups. The task contained two letters (W and M), W was the Go stimulus and M the NoGo stimulus. The impulsive youth showed a significantly greater decrease in N2 latency for Go relative to NoGo trials than the premeditated aggressive youth. The differentiation in N2 amplitude between Go and NoGo (N2d) was negatively correlated with impulsivity of aggression. Both groups showed no significant central NoGo P3. Our findings suggest that impulsive violent youth show stronger prepotent responses and impaired conflict monitoring during early inhibitory control processing relative to premeditated aggressive youth. Both impulsive and premeditated violent youth may show impaired response inhibition at the late processing stage of inhibitory control.
In the aerospace industry, spacecraft often serve in harsh operating environments, so the design of ultra-lightweight and high-performance structures is a major requirement in aerospace structure design. In this article, a lightweight aerospace bracket considering fatigue performance was designed by topology optimization and manufactured by 3D-printing. Considering the requirements of assembly with a fixture for fatigue testing and avoiding stress concentration, a reconstructed model was presented by CAD software before manufacturing. To improve the fatigue performance of the structure, this article proposes the design idea of abstracting the practiced working condition of the bracket subjected to cycle loads in the vertical direction via a multiple load-case topology optimization problem by minimizing compliance under a variety of asymmetric extreme loading conditions. Parameter sweeping was used to improve the computational efficiency. The mass of the new bracket was reduced by 37% compared to the original structure. Both numerical simulation and the fatigue test were implemented to support the validity of the new bracket. This work indicates that the integration of the proposed topology optimization design method and additive manufacturing can be a powerful tool for the design of lightweight structures considering fatigue performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.