This paper explores the equivalence among proportional-integral-derivative (PID) control and several robust control methods, including an adaptive backstepping control, an improved backstepping control, 'P+PI'...
详细信息
This study aims to explore the application of lower limb exoskeleton robots in rehabilitation therapy to meet the increasing demands of disabled individuals for rehabilitation. At present, exoskeleton robot research r...
详细信息
We propose a demonstration-efficient strategy to compress a computationally expensive Model Predictive Controller (MPC) into a more computationally efficient representation based on a deep neural network and Imitation...
详细信息
ISBN:
(纸本)9781728196817
We propose a demonstration-efficient strategy to compress a computationally expensive Model Predictive Controller (MPC) into a more computationally efficient representation based on a deep neural network and Imitation Learning (IL). By generating a Robust Tube variant (RTMPC) of the MPC and leveraging properties from the tube, we introduce a data augmentation method that enables high demonstration-efficiency, capable of compensating the distribution shifts typically encountered in IL. Our approach opens the possibility of zero-shot transfer from a single demonstration collected in a nominal domain, such as a simulation or a robot in a lab/controlled environment, to a domain with bounded model errors/perturbations. Numerical and experimental evaluations performed on a trajectory tracking MPC for a multirotor show that our method outperforms strategies commonly employed in IL, such as DAgger and Domain Randomization, in terms of demonstration-efficiency and robustness to perturbations unseen during training.
The dehaze methods are limited because authenticity of the synthesized dataset has not yet met the requirements for dehazing in real-world scenarios. The traditional image domain migration methods exhibit an uneven pr...
详细信息
ISBN:
(纸本)9798350344738;9798350344721
The dehaze methods are limited because authenticity of the synthesized dataset has not yet met the requirements for dehazing in real-world scenarios. The traditional image domain migration methods exhibit an uneven problem in fog generation. We propose a characteristic transfer fog generative model (FogGAN) for the synthesis of haze datasets. Firstly, we propose a multi-feature fusion strategy for haze distribution based on the principle of atmospheric scattering. We use transmission maps, depth maps, and mask maps to obtain the distribution of haze and transfer the fused information to the source domain. Secondly, in order to improve the error fitting phenomenon of multicommon information in the target domain, we designed a multi-layer attention module (MAConv). It focuses the neural network on the features of fog and excludes interference from other content. To address the issue of missing details in generated images. We conducted experiments on the VOC2007 dataset. It demonstrates the effectiveness and the ability to improve existing dehaze methods.
With a large increase in the amount of data that are transferred via publicly available computer networks, the global demand for new protection and prevention methods could be observed in recent studies of many resear...
详细信息
ISBN:
(数字)9781665468589
ISBN:
(纸本)9781665468596;9781665468589
With a large increase in the amount of data that are transferred via publicly available computer networks, the global demand for new protection and prevention methods could be observed in recent studies of many research groups. The paper deals with anomaly detection, focusing on cybersecurity applications, as there are only few papers that address this topic. Four methods, such as DBSCAN, One-class SVM, LSTM and Isolation forest were used to solve this problem. During the experimental part, the implementation and experiments were performed to examine the performance on common dataset to assess the ability and further possible applications.
In this paper we take into account the variation of the model parameters, during the regulation process, in the discrete time sliding mode control approach. Moreover, the system is affected by unknown, but bounded ext...
详细信息
ISBN:
(数字)9781665468589
ISBN:
(纸本)9781665468596;9781665468589
In this paper we take into account the variation of the model parameters, during the regulation process, in the discrete time sliding mode control approach. Moreover, the system is affected by unknown, but bounded external disturbances that do not need to satisfy the matching conditions. The controller guarantees the fastest, monotonic and finite time convergence of the representative point to the switching hyperplane, simultaneously ensuring constraints satisfaction on both state and input signal. Sufficient condition that assures all mentioned properties is formally proved and the simulation example demonstrates advantages of the theoretical considerations.
The practical predefined-time (PPT) output feedback control issue of higher-order nonlinear systems is investigated in this paper. First, a state observer was designed to ensure the observer error to be PPT stable via...
详细信息
The rapid growth of financial markets has necessitated developing more precise and efficient frameworks to predict stock price movements. This paper introduces MiniBert24, a lightweight, transformer-based architecture...
详细信息
This paper employs an iterative learning control (ILC) approach to achieve tracking task for non-repetitive time-varying systems (NTVSs). In industrial production tasks, the actual model of the system is usually unkno...
详细信息
This paper introduces an innovative design for robotic operating platforms, underpinned by a transformative Internet of Things (IoT) architecture, seamlessly integrating cutting-edge technologies such as large languag...
详细信息
暂无评论