亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Control and planning of multi-agent systems is an active and increasingly studied topic of research, with many practical applications such as rescue missions, security, surveillance, and transportation. This thesis addresses the planning and control of multi-agent systems under temporal logic tasks. The considered systems concern complex, robotic, manipulator-endowed systems, which can coordinate in order to execute complicated tasks, including object manipulation/transportation. Motivated by real-life scenarios, we take into account high-order dynamics subject to model uncertainties and unknown disturbances. Our approach is based on the integration of tools from the areas of multi-agent systems, intelligent control theory, cooperative object manipulation, discrete abstraction design of multi-agent-object systems, and formal verification. The first part of the thesis is devoted to the design of continuous control protocols for cooperative object manipulation/transportation by multiple robotic agents, and the relation of rigid cooperative manipulation schemes to multi-agent formation. In the second part of the thesis, we develop control schemes for the continuous coordination of multi-agent complex systems with uncertain dynamics, focusing on multi-agent navigation with collision specifications in obstacle-cluttered environments. The third part of the thesis is focused on the planning and control of multi-agent and multi-agent-object systems subject to complex tasks expressed as temporal logic formulas. The fourth and final part of the thesis focuses on several extension schemes for single-agent setups, such as motion planning under timed temporal tasks and asymptotic reference tracking for unknown systems while respecting funnel constraints.

This paper presents a hierarchical reinforcement learning algorithm constrained by differentiable signal temporal logic. Previous work on logic-constrained reinforcement learning consider encoding these constraints with a reward function, constraining policy updates with a sample-based policy gradient. However, such techniques oftentimes tend to be inefficient because of the significant number of samples required to obtain accurate policy gradients. In this paper, instead of implicitly constraining policy search with sample-based policy gradients, we directly constrain policy search by backpropagating through formal constraints, enabling training hierarchical policies with substantially fewer training samples. The use of hierarchical policies is recognized as a crucial component of reinforcement learning with task constraints. We show that we can stably constrain policy updates, thus enabling different levels of the policy to be learned simultaneously, yielding superior performance compared with training them separately. Experiment results on several simulated high-dimensional robot dynamics and a real-world differential drive robot (TurtleBot3) demonstrate the effectiveness of our approach on five different types of task constraints. Demo videos, code, and models can be found at our project website: //sites.google.com/view/dscrl

In many histopathology tasks, sample classification depends on morphological details in tissue or single cells that are only visible at the highest magnification. For a pathologist, this implies tedious zooming in and out, while for a computational decision support algorithm, it leads to the analysis of a huge number of small image patches per whole slide image (WSI). Attention-based multiple instance learning (MIL), where attention estimation is learned in a weakly supervised manner, has been successfully applied in computational histopathology, but it is challenged by large numbers of irrelevant patches, reducing its accuracy. Here, we present an active learning approach to the problem. Querying the expert to annotate regions of interest in a WSI guides the formation of high-attention regions for MIL. We train an attention-based MIL and calculate a confidence metric for every image in the dataset to select the most uncertain WSIs for expert annotation. We test our approach on the CAMELYON17 dataset classifying metastatic lymph node sections in breast cancer. With a novel attention guiding loss, this leads to an accuracy boost of the trained models with few regions annotated for each class. Active learning thus improves WSIs classification accuracy, leads to faster and more robust convergence, and speeds up the annotation process. It may in the future serve as an important contribution to train MIL models in the clinically relevant context of cancer classification in histopathology.

This paper proposes a new framework using physics-informed neural networks (PINNs) to simulate complex structural systems that consist of single and double beams based on Euler-Bernoulli and Timoshenko theory, where the double beams are connected with a Winkler foundation. In particular, forward and inverse problems for the Euler-Bernoulli and Timoshenko partial differential equations (PDEs) are solved using nondimensional equations with the physics-informed loss function. Higher-order complex beam PDEs are efficiently solved for forward problems to compute the transverse displacements and cross-sectional rotations with less than 1e-3 percent error. Furthermore, inverse problems are robustly solved to determine the unknown dimensionless model parameters and applied force in the entire space-time domain, even in the case of noisy data. The results suggest that PINNs are a promising strategy for solving problems in engineering structures and machines involving beam systems.

We develop fast and scalable methods for computing reduced-order nonlinear solutions (RONS). RONS was recently proposed as a framework for reduced-order modeling of time-dependent partial differential equations (PDEs), where the modes depend nonlinearly on a set of time-varying parameters. RONS uses a set of ordinary differential equations (ODEs) for the parameters to optimally evolve the shape of the modes to adapt to the PDE's solution. This method has already proven extremely effective in tackling challenging problems such as advection-dominated flows and high-dimensional PDEs. However, as the number of parameters grow, integrating the RONS equation and even its formation become computationally prohibitive. Here, we develop three separate methods to address these computational bottlenecks: symbolic RONS, collocation RONS and regularized RONS. We demonstrate the efficacy of these methods on two examples: Fokker-Planck equation in high dimensions and the Kuramoto-Sivashinsky equation. In both cases, we observe that the proposed methods lead to several orders of magnitude in speedup and accuracy. Our proposed methods extend the applicability of RONS beyond reduced-order modeling by making it possible to use RONS for accurate numerical solution of linear and nonlinear PDEs. Finally, as a special case of RONS, we discuss its application to problems where the PDE's solution is approximated by a neural network, with the time-dependent parameters being the weights and biases of the network. The RONS equations dictate the optimal evolution of the network's parameters without requiring any training.

In conventional dual-function radar-communication (DFRC) systems, the radar and communication channels are routinely estimated at fixed time intervals based on their worst-case operation scenarios. Such situation-agnostic repeated estimations cause significant training overhead and dramatically degrade the system performance, especially for applications with dynamic sensing/communication demands and limited radio resources. In this paper, we leverage the channel aging characteristics to reduce training overhead and to design a situation-dependent channel re-estimation interval optimization-based resource allocation for performance improvement in a multi-target tracking DFRC system. Specifically, we exploit the channel temporal correlation to predict radar and communication channels for reducing the need of training preamble retransmission. Then, we characterize the channel aging effects on the Cramer-Rao lower bounds (CRLBs) for radar tracking performance analysis and achievable rates with maximum ratio transmission (MRT) and zero-forcing (ZF) transmit beamforming for communication performance analysis. In particular, the aged CRLBs and achievable rates are derived as closed-form expressions with respect to the channel aging time, bandwidth, and power. Based on the analyzed results, we optimize these factors to maximize the average total aged achievable rate subject to individual target tracking precision demand, communication rate requirement, and other practical constraints. Since the formulated problem belongs to a non-convex problem, we develop an efficient one-dimensional search based optimization algorithm to obtain its suboptimal solutions. Finally, simulation results are presented to validate the correctness of the derived theoretical results and the effectiveness of the proposed allocation scheme.

Many problems arising in control require the determination of a mathematical model of the application. This has often to be performed starting from input-output data, leading to a task known as system identification in the engineering literature. One emerging topic in this field is estimation of networks consisting of several interconnected dynamic systems. We consider the linear setting assuming that system outputs are the result of many correlated inputs, hence making system identification severely ill-conditioned. This is a scenario often encountered when modeling complex cybernetics systems composed by many sub-units with feedback and algebraic loops. We develop a strategy cast in a Bayesian regularization framework where any impulse response is seen as realization of a zero-mean Gaussian process. Any covariance is defined by the so called stable spline kernel which includes information on smooth exponential decay. We design a novel Markov chain Monte Carlo scheme able to reconstruct the impulse responses posterior by efficiently dealing with collinearity. Our scheme relies on a variation of the Gibbs sampling technique: beyond considering blocks forming a partition of the parameter space, some other (overlapping) blocks are also updated on the basis of the level of collinearity of the system inputs. Theoretical properties of the algorithm are studied obtaining its convergence rate. Numerical experiments are included using systems containing hundreds of impulse responses and highly correlated inputs.

Time series classification is an important problem in real world. Due to its non-stationary property that the distribution changes over time, it remains challenging to build models for generalization to unseen distributions. In this paper, we propose to view the time series classification problem from the distribution perspective. We argue that the temporal complexity attributes to the unknown latent distributions within. To this end, we propose DIVERSIFY to learn generalized representations for time series classification. DIVERSIFY takes an iterative process: it first obtains the worst-case distribution scenario via adversarial training, then matches the distributions of the obtained sub-domains. We also present some theoretical insights. We conduct experiments on gesture recognition, speech commands recognition, wearable stress and affect detection, and sensor-based human activity recognition with a total of seven datasets in different settings. Results demonstrate that DIVERSIFY significantly outperforms other baselines and effectively characterizes the latent distributions by qualitative and quantitative analysis. Code is available at: //github.com/microsoft/robustlearn.

For emergency response scenarios like firefighting in urban environments, there is a need to both localize emergency responders inside the building and also support a high bandwidth communication link between the responders and a command-and-control center. The emergency networks for such scenarios can be established with the quick deployment of Unmanned Aerial Vehicles (UAVs). Further, the 3D mobility of UAVs can be leveraged to improve the quality of the wireless link by maneuvering them into advantageous locations. This has motivated recent propagation measurement campaigns to study low-altitude air-to-ground channels in both 5G-sub6 GHz and 5G-mmWave bands. In this paper, we develop a model for the link in a UAV-assisted emergency location and/or communication system. Specifically, given the importance of Line-of-Sight (LoS) links in localization as well as mmWave communication, we derive a closed-form expression for the LoS probability. This probability is parameterized by the UAV base station location, the size of the building, and the size of the window that offers the best propagation path. An expression for coverage probability is also derived. The LoS probability and coverage probabilities derived in this paper can be used to analyze the outdoor UAV-to-indoor propagation environment to determine optimal UAV positioning and the number of UAVs needed to achieve the desired performance of the emergency network.

Classic algorithms and machine learning systems like neural networks are both abundant in everyday life. While classic computer science algorithms are suitable for precise execution of exactly defined tasks such as finding the shortest path in a large graph, neural networks allow learning from data to predict the most likely answer in more complex tasks such as image classification, which cannot be reduced to an exact algorithm. To get the best of both worlds, this thesis explores combining both concepts leading to more robust, better performing, more interpretable, more computationally efficient, and more data efficient architectures. The thesis formalizes the idea of algorithmic supervision, which allows a neural network to learn from or in conjunction with an algorithm. When integrating an algorithm into a neural architecture, it is important that the algorithm is differentiable such that the architecture can be trained end-to-end and gradients can be propagated back through the algorithm in a meaningful way. To make algorithms differentiable, this thesis proposes a general method for continuously relaxing algorithms by perturbing variables and approximating the expectation value in closed form, i.e., without sampling. In addition, this thesis proposes differentiable algorithms, such as differentiable sorting networks, differentiable renderers, and differentiable logic gate networks. Finally, this thesis presents alternative training strategies for learning with algorithms.