Small racing quadcopters carrying explosives, known as first-person-view drones or FPVs, have become the dominant weapon in the war in Ukraine. Now, some are fitted with solar cells so they can wait for extended periods to ambush targets, turning them into a new type of land mine. "The drone can sit by a road or choke point and when it acquires its target, it can then do a quick sprint to the target," says Robert Bunker at US consultancy firm C/O Futures. Drone ambushes, where the devices land beside a road or on a building and wait for a target, are already commonly carried out by both Russian and Ukrainian forces. But even with their engines turned off, their camera and radio communications drain the drones' battery, limiting waiting time to a few hours at best.

Though the underlying fields associated with vector-valued environmental data are continuous, observations themselves are discrete. For example, climate models typically output grid-based representations of wind fields or ocean currents, and these are often downscaled to a discrete set of points. By treating the area of interest as a two-dimensional manifold that can be represented as a triangular mesh and embedded in Euclidean space, this work shows that discrete intrinsic Gaussian processes for vector-valued data can be developed from discrete differential operators defined with respect to a mesh. These Gaussian processes account for the geometry and curvature of the manifold whilst also providing a flexible and practical formulation that can be readily applied to any two-dimensional mesh. We show that these models can capture harmonic flows, incorporate boundary conditions, and model non-stationary data. Finally, we apply these models to downscaling stationary and non-stationary gridded wind data on the globe, and to inference of ocean currents from sparse observations in bounded domains.

We study the problem of imitating an expert demonstrator in a continuous state-and-action dynamical system. While imitation learning in discrete settings such as autoregressive language modeling has seen immense success and popularity in recent years, imitation in physical settings such as autonomous driving and robot learning has proven comparably more complex due to the compounding errors problem, often requiring elaborate set-ups to perform stably. Recent work has demonstrated that even in benign settings, exponential compounding errors are unavoidable when learning solely from expert-controlled trajectories, suggesting the need for more advanced policy parameterizations or data augmentation. To this end, we present minimal interventions that provably mitigate compounding errors in continuous state-and-action imitation learning. When the system is open-loop stable, we prescribe "action chunking," i.e., predicting and playing sequences of actions in open-loop; when the system is possibly unstable, we prescribe "noise injection," i.e., adding noise during expert demonstrations. These interventions align with popular choices in modern robot learning, though the benefits we derive are distinct from the effects they were designed to target. Our results draw insights and tools from both control theory and reinforcement learning; however, our analysis reveals novel considerations that do not naturally arise when either literature is considered in isolation.

Solder joint reliability related to failures due to thermomechanical loading is a critically important yet physically complex engineering problem. As a result, simulated behavior is oftentimes computationally expensive. In an increasingly data-driven world, the usage of efficient data-driven design schemes is a popular choice. Among them, Bayesian optimization (BO) with Gaussian process regression is one of the most important representatives. The authors argue that computational savings can be obtained from exploiting thorough surrogate modeling and selecting a design candidate based on multiple acquisition functions. This is feasible due to the relatively low computational cost, compared to the expensive simulation objective. This paper addresses the shortcomings in the adjacent literature by providing and implementing a novel heuristic framework to perform BO with adaptive hyperparameters across the various optimization iterations. Adaptive BO is subsequently compared to regular BO when faced with synthetic objective minimization problems. The results show the efficiency of adaptive BO when compared any worst-performing regular Bayesian schemes. As an engineering use case, the solder joint reliability problem is tackled by minimizing the accumulated non-linear creep strain under a cyclic thermal load. Results show that adaptive BO outperforms regular BO by 3% on average at any given computational budget threshold, critically saving half of the computational expense budget. This practical result underlines the methodological potential of the adaptive Bayesian data-driven methodology to achieve better results and cut optimization-related expenses. Lastly, in order to promote the reproducibility of the results, the data-driven implementations are made available on an open-source basis.

-- Physics-based simulations and learning-based models are vital for complex robotics tasks like deformable object manipulation and liquid handling. For instance, accurately pouring liquid from one container to another poses challenges, particularly when models are trained on limited demonstrations and may perform poorly in novel situations. This paper proposes an uncertainty-aware Monte Carlo Tree Search (MCTS) algorithm designed to mitigate these inaccuracies. By incorporating estimates of model uncertainty, the proposed MCTS strategy biases the search towards actions with lower predicted uncertainty. This approach enhances the reliability of planning under uncertain conditions. Applied to a liquid pouring task, our method demonstrates improved success rates even with models trained on minimal data, outperforming traditional methods and showcasing its potential for robust decision-making in robotics. Physics-based simulations and learning-based models are extensively used in robotics to perform complex tasks such as deformable object manipulation [1]-[5], contact-rich manipulation [6]-[8], control of soft robots [9], [10], and liquid handling [11], [12]. These models are often inaccurate in predicting the outcome of actions (e.g., because of the epistemic uncertainty of learned models or the sim-to-real gap of physics simulators).

Due to the extensive retention of building operation data, data-driven building load prediction methods have demonstrated powerful capabilities in forecasting building energy loads. Buildings with similar operating conditions, physical characteristics, and types often exhibit similar energy usage patterns, which are reflected in their operation data showing similar trends and spatial dependencies. However, conventional building load prediction methods have significant limitations in extracting these spatial dependencies. To address this challenge, this paper proposes a multi-building load prediction method based on spatio-temporal graph neural networks, which is divided into three main steps: graph representation, graph learning, and method interpretation. First, a graph representation method is developed that identifies building correlations based on intrinsic characteristics and environmental factors. Next, a multi-level spatiotemporal graph convolu-tional architecture with an attention mechanism is designed to predict energy loads for multiple buildings. Finally, a model interpretation method based on the optimal graph structure obtained from the training process is devel-Corresponding author Email address: ychen@eitech.edu.cn Experiments on the Building Data Genome Project 2 dataset validate that the proposed method outperforms commonly used baseline models like XGBoost, SVR, FCNN, GRU, and Na ıve in terms of prediction accuracy. Additionally, the model demonstrates strong robustness and generalization, performing reliably under uncertainty and unseen data. Visualization of the building similarity matrix confirms the model's interpretability, revealing its ability to group similar buildings and establish meaningful spatial dependencies, proving that the proposed Att-GCN method for learning spatial dependencies between buildings with similar energy usage patterns is both reasonable and interpretable. Introduction With urbanization increasing, building energy consumption and carbon emissions are growing. Construction and operation of buildings account for 34% of global energy use, with 30% from operations.

At present, state-of-the-art forecasting models are short of the ability to capture spatio-temporal dependency and synthesize global information at the stage of learning. To address this issue, in this paper, through the adaptive fuzzified construction of temporal data, we propose a novel convolutional architecture with partially asymmetric design based on the scheme of sliding window to realize accurate time series forecasting. First, the construction strategy of traditional fuzzy time series is improved to further extract short and long term temporal interrelation, which enables every time node to automatically possess corresponding global information and inner relationships among them in a restricted sliding window and the process does not require human involvement. Second, a bilateral Atrous algorithm is devised to reduce calculation demand of the proposed model without sacrificing global characteristics of elements. And it also allows the model to avoid processing redundant information. Third, after the transformation of time series, a partially asymmetric convolutional architecture is designed to more flexibly mine data features by filters in different directions on feature maps, which gives the convolutional neural network (CNN) the ability to construct sub-windows within existing sliding windows to model at a more fine-grained level. And after obtaining the time series information at different levels, the multi-scale features from different sub-windows will be sent to the corresponding network layer for time series information fusion. Compared with other competitive modern models, the proposed method achieves state-of-the-art results on most of popular time series datasets, which is fully verified by the experimental results.

As the development of lightweight deep learning algorithms, various deep neural network (DNN) models have been proposed for the remote sensing scene classification (RSSC) application. However, it is still challenging for these RSSC models to achieve optimal performance among model accuracy, inference latency, and energy consumption on resource-constrained edge devices. In this paper, we propose a lightweight RSSC framework, which includes a distilled global filter network (GFNet) model and an early-exit mechanism designed for edge devices to achieve state-of-the-art performance. Specifically, we first apply frequency domain distillation on the GFNet model to reduce model size. Then we design a dynamic early-exit model tailored for DNN models on edge devices to further improve model inference efficiency. We evaluate our E3C model on three edge devices across four datasets. Extensive experimental results show that it achieves an average of 1.3x speedup on model inference and over 40% improvement on energy efficiency, while maintaining high classification accuracy.

Learning reduced models from data in a nonintrusive fashion is an important problem in science and engineering [1, 2, 3]. A typical approach is to first learn an encoder-decoder pair, embed the training snapshot trajectories with the learned encoder, and then fit a reduced dynamical-system model to the embedded trajectories. However, the decomposition of the training process into first learning an encoder-decoder pair for the embedding and only sub-sequentially learning a model of the dynamics typically means that the encoder-decoder pair are trained with the objective of accurately approximating the training data, rather than taking the reduced-model prediction error into account. Thus, the encoder-decoder pair can overfit to achieving a low reconstruction error on the training data by learning embeddings of the snapshot trajectories that are non-smooth, which means that learning a reduced model can become challenging. Correspondingly, it has been observed that learning embeddings and models together can be beneficial; see, e.g., [4, 5, 6, 7]. In the context of intrusive model reduction with linear approximations, there is work that optimizes the reduced basis with respect to the model prediction error [8], quantities of interest [9], and to achieve stability [10]; however, we focus here on the setting of nonintrusive model reduction and nonlinear approximations.

Autonomous Delivery Vehicles (ADVs) are increasingly used for transporting goods in 5G network-enabled smart factories, with the compute-intensive localization module presenting a significant opportunity for optimization. We propose ACCESS-AV, an energy-efficient Vehicle-to-Infrastructure (V2I) localization framework that leverages existing 5G infrastructure in smart factory environments. By opportunistically accessing the periodically broadcast 5G Synchronization Signal Blocks (SSBs) for localization, ACCESS-AV obviates the need for dedicated Roadside Units (RSUs) or additional onboard sensors to achieve energy efficiency as well as cost reduction. We implement an Angle-of-Arrival (AoA)-based estimation method using the Multiple Signal Classification (MUSIC) algorithm, optimized for resource-constrained ADV platforms through an adaptive communication-computation strategy that dynamically balances energy consumption with localization accuracy based on environmental conditions such as Signal-to-Noise Ratio (SNR) and vehicle velocity. Experimental results demonstrate that ACCESS-AV achieves an average energy reduction of 43.09% compared to non-adaptive systems employing AoA algorithms such as vanilla MUSIC, ESPRIT, and Root-MUSIC. It maintains sub-30 cm localization accuracy while also delivering substantial reductions in infrastructure and operational costs, establishing its viability for sustainable smart factory environments.