This paper presents an offline path planning strategy for unmanned ground vehicles (UGVs) using Q-learning. The proposed method addresses path optimization in warehouse-like environments, where tasks involve item pick...
详细信息
ISBN:
(数字)9798331508807
ISBN:
(纸本)9798331508814
This paper presents an offline path planning strategy for unmanned ground vehicles (UGVs) using Q-learning. The proposed method addresses path optimization in warehouse-like environments, where tasks involve item pickup and delivery to specific locations. The Q-learning algorithm trains an agent to determine the most efficient routes, with validation conducted in an $8 \times 5$ meter workspace equipped with an Optitrack motion capture system. The workspace was discretized into a $16 \times 10$ grid, allowing the Q-learning to effectively navigate through complex obstacle-laden scenarios. Experimental results indicate that the Q-learning approach outperforms traditional methods such as Dijkstra, A-star, and Breadth-First Search in terms of path length, number of turns, planning time, and overall success rate; being up to 7 times faster to plan a path and reducing the number of bends by up to 41%. The Q-learning based paths feature more linear segments, which contribute to energy savings and improved navigational efficiency. Future work will explore applications in heterogeneous multi-agent systems and enhancements in training time and agent collaboration.
Comparing the structures of current neural networks and the biological brain, it can be observed that many mechanisms correspond to each other according to their functions. From the perspective of the biological brain...
详细信息
ISBN:
(数字)9798350394085
ISBN:
(纸本)9798350394092
Comparing the structures of current neural networks and the biological brain, it can be observed that many mechanisms correspond to each other according to their functions. From the perspective of the biological brain, different components have different long-term or short-term memory effects, such as the hippopotamus. However, current neural networks do not pay much attention to this aspect. In this work, we incorporated many hypotheses or theories inspired by the territory of neurobiology to retain the learned knowledge. To start with, we follow the inspiration of the synaptic homeostasis hypothesis (SHY) [1] and add an additional training stage to the training process of the model, which can ensure that only the most important information remains intact and the insignificant synapse can be pruned. In other words, we divide the overall training process into two learning stages: synaptogenesis and synaptic sparsifying. We experimentally demonstrate that our novel learning strategy significantly outperforms the traditional solution in training a sequence of tasks at different times on three public datasets, which supports that the proposed method is more efficient for resource-limited edge devices.
We developed a dual optical/x-ray ultrafast photodetector based on in-house grown Cdo * Mg0.03Te single crystals. The detector is characterized by ~200 ps full-width-at-half-maximum, readout-electronics limited photor...
详细信息
Feeding the training data to neural networks in a specific sequence, from the simple data to the difficult data, utilizing curriculum learning can enhance performance improvements over the typical learning strategy ba...
详细信息
ISBN:
(数字)9798350394085
ISBN:
(纸本)9798350394092
Feeding the training data to neural networks in a specific sequence, from the simple data to the difficult data, utilizing curriculum learning can enhance performance improvements over the typical learning strategy based on shuffling training samples randomly, without any additional computational costs. This training approach has been successfully applied in all fields of machine learning. However, the current curriculum learning will gradually introduce difficult samples until the model eventually performs joint training. In addition, our experimental results find and demonstrate how the order of training tasks arranged according to the difficulty of different tasks influences the reuse percentage of model capacity, allowing us to observe the impact of curriculum learning on model performance from different perspectives. Finally, we also separately conduct three ablations analyses of our model to comprehensively enhance the understanding of the impacts of the proposed approach and further demonstrate its scalability to a standard large-scale dataset, i.e., the ImageNet dataset.
Cobalt titanate, CoTiO3, is a honeycomb antiferromagnet recently confirmed experimentally to host Dirac magnons, topological spin-orbit excitons, and chiral phonons. Here, we investigate a magnon gap at the zone cente...
详细信息
Cobalt titanate, CoTiO3, is a honeycomb antiferromagnet recently confirmed experimentally to host Dirac magnons, topological spin-orbit excitons, and chiral phonons. Here, we investigate a magnon gap at the zone center which calls for a refined spin Hamiltonian. We propose a microscopic model for the magnon gap and attribute it to a lattice-distortion (phonon)-induced higher-order spin interaction. Strong magnetoelastic coupling in CoTiO3 is also evident in Raman spectra, in which the magnetic order exerts a stronger influence on phonons corresponding to in-plane ionic motions than those with out-of-plane motions. We further examine the evolution of the zone-center magnons in a high magnetic field up to 18.5 T via THz absorption spectroscopy measurements. Based on this field dependence, we propose a spin Hamiltonian that not only agrees with magnon dispersion measured by inelastic neutron scattering but also includes fewer exchange constants and a realistic anisotropy term. Our work highlights the broad implications of magnetoelastic coupling in the study of topologically protected bosonic excitations.
We propose a novel robust nonlinear $\mathcal{W}_{\infty}$ optimal control method for dynamical systems with nonaffine control inputs. The nonlinear $\mathcal{W}_{\infty}$ control formulation extends the classic n...
详细信息
ISBN:
(数字)9783907144107
ISBN:
(纸本)9798331540920
We propose a novel robust nonlinear
$\mathcal{W}_{\infty}$
optimal control method for dynamical systems with nonaffine control inputs. The nonlinear
$\mathcal{W}_{\infty}$
control formulation extends the classic nonlinear
$\mathcal{H}_{\infty}$
one, considering a weighted Sobolev norm of the cost variable. This approach assumes that the cost variable belongs to the weighted Sobolev space
$\mathcal{W}_{m,p,\mathbf{\Gamma}}$
, ensuring continuity and differentiability up to degree
$m$
in a certain domain
$\Omega$
. Consequently, in addition to the well-known features provided by the
$\mathcal{H}_{\infty}$
approach in terms of disturbance attenuation, the closed-loop system benefits from the enhanced transient performance. Here, the robust nonlinear
$\mathcal{W}_{\infty}$
optimal control problem is formulated via dynamic programming for increased-order systems, and a particular solution is proposed to the resulting Hamilton-Jacobi equation, along with the corresponding stability analysis. To validate the proposed method and its versatility, we provide numerical results for the control of a quadrotor. Additionally, leveraging the inherent
$\mathcal{L}_{2}$
-gain properties of our approach, we demonstrate that the resulting controller can achieve trajectory tracking with guaranteed asymptotic stability for the whole closed-loop system.
We experimentally demonstrate reduced dimensionality in a interacting ensemble of emitters. The well-known stretched exponential decay dynamics, (Equation presented) with β = 0.5 in 3D geometries, is strikingly modif...
详细信息
The Neural Networks (NN) model which is incorporated in the control system design has been studied, and the results show better performance than the mathematical model approach. However, some studies consider that onl...
详细信息
In general, public or private organizations or companies have used information-based technology as a support to improve business performance to be more effective and efficient in order to achieve a company’s business...
详细信息
In general, public or private organizations or companies have used information-based technology as a support to improve business performance to be more effective and efficient in order to achieve a company’s business goals. Given the large contribution of information technology in the application of hotel applications as a supporting information system, it is a vital system that must avoid risks that can hinder and cause harm to the hotel management business processes. Therefore, it is necessary to carry out risk management using the COBIT 5 framework to manage possible risks that may occur based on the APO12 (Manage Risk) domain. From the evaluation results of the data obtained through observation and interviews as well as the calculation of the results of the questionnaire based on 6 APO12 subdomains, the results of the risk management level capability assessment in hotel applications are still at level 3 or have reached the level of established process with the target to be achieved at level 4 resulting in a gap of 1 level. Based on the results obtained, it is necessary to propose recommendations that can be used by hotels in improving the application of information technology risk management so that in the future it can achieve the expected target level so that the APO12 level of capability can increase and become more optimal.
A fiber Bragg grating sensor is used to monitor the temperature of an air-cooled combustion motorcycle engine in this study. The sensor is attached to one of the aluminum cylinders fins of the motorcycle to characteri...
详细信息
A fiber Bragg grating sensor is used to monitor the temperature of an air-cooled combustion motorcycle engine in this study. The sensor is attached to one of the aluminum cylinders fins of the motorcycle to characterize the heat transfer process. We present the results of the heating and cooling curves during tests with the motorcycle at rest and in motion. A better understanding of the air-cooling process can lead to the optimization of designs in this area.
暂无评论