Deep neural networks (DNNs) are known to be susceptible to various malicious attacks, such as adversarial and backdoor attacks. However, most of these attacks utilize additive adversarial perturbations (or backdoor tr...
详细信息
Robotic arm is a complex system with multiple inputs and outputs, strong nonlinearity and strong coupling, and the research of high precision trajectory tracking control technology for robotic arm has been an importan...
详细信息
Robotic arm is a complex system with multiple inputs and outputs, strong nonlinearity and strong coupling, and the research of high precision trajectory tracking control technology for robotic arm has been an important issue for scholars at home and abroad. This paper takes the six-degree-of-freedom (6-DOF) robotic arm as its study object and designs a fractional-order PID (FOPID) control method. To improve its control accuracy, a parameter tuning method of fractional-order beetle antennae particle swarm algorithm (FBPA) optimized FOPID controller is proposed. This method puts the beetle antennae search (BAS) algorithm together with the particle swarm optimization (PSO) algorithm, introduces the concept of fractional-order calculus into the algorithm, dynamically adjusts the inertial weights and fractional order and finally improves the optimization effect of the algorithm. The simulation experiments of MATLAB/Simulink indicate that in comparison with the traditional PID control method, the FOPID control method optimized by the FBPA has high control accuracy and small overshooting, which meets the high-precision control requirements of the 6-DOF robotic arm.
In this work, we present transformer-based powered descent guidance (T-PDG), a scalable algorithm for reducing the computational complexity of the direct optimization formulation of the spacecraft powered descent guid...
详细信息
In this work, we present transformer-based powered descent guidance (T-PDG), a scalable algorithm for reducing the computational complexity of the direct optimization formulation of the spacecraft powered descent guidance problem. T-PDG uses data from prior runs of trajectory optimization algorithms to train a transformer neural network, which accurately predicts the relationship between problem parameters and the globally optimal solution for the powered descent guidance problem. The solution is encoded as the set of tight constraints corresponding to the constrained minimum-cost trajectory and the optimal final landing time. By leveraging the attention mechanism of transformer neural networks, large sequences of time series data can be accurately predicted when given only the spacecraft state and landing site parameters. When applied to the real problem of Mars-powered descent guidance, T-PDG reduces the time for computing the 3-degree-of-freedom fuel-optimal trajectory when compared to lossless convexification, improving solution times by up to an order of magnitude. A safe and optimal solution is guaranteed by including a feasibility check in T-PDG before returning the final trajectory.
With the expansion of the scale of renewable energy units connected to the power system, the problems of volatility and instability brought about by them are becoming more and more prominent. Compressed air energy sto...
详细信息
Background and AimsSoil salinization is a major cause of land degradation and ecological damage. Traditional soil salinity monitoring techniques are limited in coverage and scalability, while remote sensing offers bro...
详细信息
Background and AimsSoil salinization is a major cause of land degradation and ecological damage. Traditional soil salinity monitoring techniques are limited in coverage and scalability, while remote sensing offers broader applicability and efficiency. This study addresses spatiotemporal variations in soil salt content (SSC) inversion across crop types in Tongliao City, Inner Mongolia, China, using an innovative integration of multi-temporal data and crop cover types, improving remote sensing monitoring *** sampling data and Sentinel-2 images from June to September in 2021 and 2022 were utilized. The deep learning U-net model classified key crops, including sunflower (33%), beet (12%), and maize (55%), and analyzed the effects of crop coverage on SSC across multiple time series. Six spectral variables were selected using the SVR-RFE model (R2 = 0.994, MAE = 0.016). SSC prediction models were developed using three machine learning methods (DBO-RF, PSO-SVM, BO-BP) and a deep learning method (Transformer).ResultsConsidering crop coverage variations improved the sensitivity of spectral variables to SSC response, enhancing predictive accuracy and model stability. Crop classification showed that the salinity index (SIs) correlated more strongly with SSC than the vegetation index (VIs), with SI6 having the highest correlation coefficient of 0.50. The Transformer model, using multi-time series data, outperformed other algorithms, achieving an average R2 of 0.71. The SSC inversion map from the Transformer model closely matched field survey *** research provides a novel approach to soil salinity prediction using satellite remote sensing, offering a scalable solution for monitoring salinization and valuable insights for environmental management and agricultural planning.
This paper considers an N-pursuer-M-evader scenario involving L virtual targets. The virtual targets serve as an intermediary target for the pursuers, allowing the pursuers to delay their final assignment to the evade...
详细信息
This paper considers an N-pursuer-M-evader scenario involving L virtual targets. The virtual targets serve as an intermediary target for the pursuers, allowing the pursuers to delay their final assignment to the evaders. However, upon reaching the virtual target, the pursuers must decide which evader to capture. It is assumed that there are more pursuers than evaders and that the pursuers are faster than the evaders. The objective is two-part: first, assign each pursuer to a virtual target and evader such that the pursuer team's energy is minimized, and, second, choose the virtual targets' locations for this minimization problem. The approach taken is to consider the Apollonius geometry between each pursuer's virtual target location and each evader. Using the constructed Apollonius circles, the pursuer's travel distance and maneuver at a virtual target are obtained. These metrics serve as a gauge for the total energy required to capture a particular evader and are used to solve the joint virtual target selection and pursuer-evader assignment problem. This paper provides a mathematical definition of this problem, the solution approach taken, and an example. Following the example, a Monte Carlo analysis is performed, demonstrating the efficacy of the algorithm and its suitability for real-time applications.
暂无评论