Papers

This paper presents an electromagnetic investigation of the crosstalk between two bent microstrip lines (MLs) separated by a perforated planar shield. As an extension of our previous study, the effects of various discontinuities in either the MLs or the shield along the coupling path are analyzed through numerical simulations and validated by measurements. The underlying electromagnetic mechanisms are also discussed. Furthermore, multimodal wave theory in a rectangular waveguide is applied to predict crosstalk behavior when the shield contains an aperture. This study aims to conceptually elucidate complex crosstalk phenomena that are difficult to model using circuit theory, and successful predictions of crosstalk behavior are presented for different problem cases.

Existing semantic communication schemes primarily focus on single-hop scenarios, overlooking the challenges of multi-hop wireless image transmission. As semantic communication is inherently lossy, distortion accumulates over multiple hops, leading to significant performance degradation. To address this, we propose the multi-hop parallel image semantic communication (MHPSC) framework, which introduces a parallel residual compensation link at each hop against distortion accumulation. To minimize the associated transmission bandwidth overhead, a coarse-to-fine residual compression scheme is designed. A deep learning-based residual compressor first condenses the residuals, followed by the adaptive arithmetic coding (AAC) for further compression. A residual distribution estimation module predicts the prior distribution for the AAC to achieve fine compression performances. This approach ensures robust multi-hop image transmission with only a minor increase in transmission bandwidth. Experimental results confirm that MHPSC outperforms both existing semantic communication and traditional separated coding schemes.

Age-related macular degeneration (AMD) is one of the leading causes of irreversible vision impairment in people over the age of 60. This research focuses on semantic segmentation for AMD lesion detection in RGB fundus images, a non-invasive and cost-effective imaging technique. The results of the ADAM challenge - the most comprehensive AMD detection from RGB fundus images research competition and open dataset to date - serve as a benchmark for our evaluation. Taking the U-Net connectivity as a base of our framework, we evaluate and compare several approaches to improve the segmentation model's architecture and training pipeline, including pre-processing techniques, encoder (backbone) deep network types of varying complexity, and specialized loss functions to mitigate class imbalances on image and pixel levels. The main outcome of this research is the final configuration of the AMD detection framework, which outperforms all the prior ADAM challenge submissions on the multi-class segmentation of different AMD lesion types in non-invasive RGB fundus images. The source code used to conduct the experiments presented in this paper is made freely available.

CT reconstruction provides radiologists with images for diagnosis and treatment, yet current deep learning methods are typically limited to specific anatomies and datasets, hindering generalization ability to unseen anatomies and lesions. To address this, we introduce the Multi-Organ medical image REconstruction (MORE) dataset, comprising CT scans across 9 diverse anatomies with 15 lesion types. This dataset serves two key purposes: (1) enabling robust training of deep learning models on extensive, heterogeneous data, and (2) facilitating rigorous evaluation of model generalization for CT reconstruction. We further establish a strong baseline solution that outperforms prior approaches under these challenging conditions. Our results demonstrate that: (1) a comprehensive dataset helps improve the generalization capability of models, and (2) optimization-based methods offer enhanced robustness for unseen anatomies. The MORE dataset is freely accessible under CC-BY-NC 4.0 at our project page https://more-med.github.io/

Electroencephalography (EEG) acquisition is often affected by large-amplitude variations across subjects and sessions. This makes conventional front ends vulnerable to saturation and clipping. Modulo sampling addresses this limitation by folding the signal into a bounded range rather than truncating it. The recovery task is then to reconstruct the original waveform from periodic observations, which is a highly ill-posed inverse problem. In this work, we propose a compact signal-structured framework for modulo EEG recovery. The method combines phase-aware features, graph-temporal modeling, and structured fold-state decoding. A boundary-guided gating technique improves inference near wrap events, where uncertainty is highest. Experiments across two EEG datasets, over a wide range of folding thresholds, demonstrate consistent recovery performance. Ablation and noise studies further support the contribution of the structured decoding technique. The proposed signal-processing approach effectively recovers folded EEG recordings. These results show that structured fold-state decoding is effective for recovering folded EEG. The code is accessible at https://github.com/soujo/graphunwrapnet.

Over-the-air (OTA) federated learning (FL) has been well recognized as a scalable paradigm that exploits the waveform superposition of the wireless multiple-access channel to aggregate model updates in a single use. Existing OTA-FL designs largely enforce zero-bias model updates by either assuming homogeneous wireless conditions (equal path loss across devices) or forcing zero-bias updates to guarantee convergence. Under heterogeneous wireless scenarios, however, such designs are constrained by the weakest device and inflate the update variance. Moreover, prior analyses of biased OTA-FL largely address convex objectives, while most modern AI models are highly non-convex. Motivated by these gaps, we study OTA-FL with stochastic gradient descent (SGD) for general smooth non-convex objectives under wireless heterogeneity. We develop novel OTA-FL SGD updates that allow a structured, time-invariant model bias while facilitating reduced variance updates. We derive a finite-time stationarity bound (expected time average squared gradient norm) that explicitly reveals a bias-variance trade-off. To optimize this trade-off, we pose a non-convex joint OTA power-control design and develop an efficient successive convex approximation (SCA) algorithm that requires only statistical CSI at the base station. Experiments on a non-convex image classification task validate the approach: the SCA-based design accelerates convergence via an optimized bias and improves generalization over prior OTA-FL baselines.

This paper presents a time-optimal Model Predictive Control (MPC) scheme for linear discrete-time systems subject to multiplicative uncertainties represented by interval matrices. To render the uncertainty propagation computationally tractable, the set-valued error system dynamics are approximated using a matrix-zonotope-based bounding operator. Recursive feasibility and finite-time convergence are ensured through an adaptive terminal constraint mechanism. A key advantage of the proposed approach is that all the necessary bounding sets can be computed offline, substantially reducing the online computational burden. The effectiveness of the method is illustrated via a numerical case study on an orbital rendezvous maneuver between two satellites.

Guaranteeing stringent data freshness for low-altitude unmanned aerial vehicles (UAVs) in shared spectrum forces a critical trade-off between two operational costs: the UAV's own energy consumption and the occupation of terrestrial channel resources. The core challenge is to satisfy the aerial data freshness while finding a Pareto-optimal balance between these costs. Leveraging predictive channel models and predictive UAV trajectories, we formulate a bi-objective Pareto optimization problem over a long-term planning horizon to jointly optimize the sampling timing for aerial traffic and the power and spectrum allocation for fair coexistence. However, the problem's non-convex, mixed-integer nature renders classical methods incapable of fully characterizing the complete Pareto frontier. Notably, we show monotonicity properties of the frontier, building on which we transform the bi-objective problem into several single-objective problems. We then propose a new graph-based algorithm and prove that it can find the complete set of Pareto optima with low complexity, linear in the horizon and near-quadratic in the resource block (RB) budget. Numerical comparisons show that our approach meets the stringent timeliness requirement and achieves a six-fold reduction in RB utilization or a 6 dB energy saving compared to benchmarks.

Purpose: Medical foundation models (FMs) offer a path to build high-performance diagnostic systems. However, their application to prostate cancer (PCa) detection from micro-ultrasound ({\mu}US) remains untested in clinical settings. We present ProstNFound+, an adaptation of FMs for PCa detection from {\mu}US, along with its first prospective validation. Methods: ProstNFound+ incorporates a medical FM, adapter tuning, and a custom prompt encoder that embeds PCa-specific clinical biomarkers. The model generates a cancer heatmap and a risk score for clinically significant PCa. Following training on multi-center retrospective data, the model is prospectively evaluated on data acquired five years later from a new clinical site. Model predictions are benchmarked against standard clinical scoring protocols (PRI-MUS and PI-RADS). Results: ProstNFound+ shows strong generalization to the prospective data, with no performance degradation compared to retrospective evaluation. It aligns closely with clinical scores and produces interpretable heatmaps consistent with biopsy-confirmed lesions. Conclusion: The results highlight its potential for clinical deployment, offering a scalable and interpretable alternative to expert-driven protocols.

The proposed approach yields a numerical method that provably executes in linear time with respect to the number of nodes and edges in a graph. The graph, constructed from the power system model, requires only knowledge of the dependencies between state-to-state and output-to-state variables within a state-space framework. While graph-based observability analysis methods exist for power system static-state estimation, the approach presented here is the first for dynamic-state estimation (DSE). We examine decentralized and centralized DSE scenarios and compare our findings with a well-established, albeit non-scalable, observability analysis method in the literature. When compared to the latter in a centralized DSE setting, our method reduced computation time by 1440x.

Assessing the severity of artifacts in pediatric brain Magnetic Resonance Imaging (MRI) is critical for diagnostic accuracy, especially in low-field systems where the signal-to-noise ratio is reduced. Manual quality assessment is time-consuming and subjective, motivating the need for robust automated solutions. In this work, we propose BRIQA (Balanced Reweighting in Image Quality Assessment), which addresses class imbalance in artifact severity levels. BRIQA uses gradient-based loss reweighting to dynamically adjust per-class contributions and employs a rotating batching scheme to ensure consistent exposure to underrepresented classes. Through experiments, no single architecture performs best across all artifact types, emphasizing the importance of architectural diversity. The rotating batching configuration improves performance across metrics by promoting balanced learning when combined with cross-entropy loss. BRIQA improves average macro F1 score from 0.659 to 0.706, with notable gains in Noise (0.430), Zipper (0.098), Positioning (0.097), Contrast (0.217), Motion (0.022), and Banding (0.012) artifact severity classification. The code is available at https://github.com/BioMedIA-MBZUAI/BRIQA.

Summary: SAMRI is an MRI-specialized adaptation of the Segment Anything Model achieving superior whole-body MRI segmentation, particularly for small and clinically critical structures, through box and point prompts for rapid annotation. Purpose: Existing SAM adaptations treat MRI as a generic modality, overlooking variable tissue contrast, intensity inhomogeneity, and clinically important small structures. We propose an MRI-specialized foundation model with strong whole-body segmentation and zero-shot generalization for direct use on any MRI annotation task. Methods: SAMRI fine-tunes only the mask decoder of SAM (ViT-B/16), keeping encoders frozen to preserve pretrained representations and eliminate redundant passes-reducing training time by 94%, trainable parameters by 96%, and FLOPs by ~99% versus full-model retraining. Training used 1.1 million 2D slice-mask pairs from 30 datasets spanning 47 targets, T1/T2/FLAIR/DWI contrasts, and whole-body anatomy, with focal-Dice loss and bounding-box (with optional point) prompts. Sizes were stratified by mask area (small: <0.5%; medium: 0.5-3.5%; large: >3.5%), and significance assessed by the Wilcoxon signed-rank test. Results: SAMRI with box+point prompts achieved mean DSC 0.87 +/- 0.11 across 47 targets, outperforming MedSAM (0.74 +/- 0.24) by 17.6% (p < 0.05), with largest gains for small (+42.4%) and medium (+26.9%) structures. On six zero-shot datasets, SAMRI achieved mean DSC 0.85, outperforming baselines. Inference requires only ~4.5 GB VRAM through an interactive interface on standard hardware. Conclusion: Decoder-only fine-tuning on a large, MRI-specific corpus delivers superior whole-body segmentation with strong zero-shot generalization, particularly for small and clinically salient structures. Public code, pretrained models, and an interactive interface make SAMRI deployable for MRI segmentation research and clinical workflows.

The proliferation of Internet of Things (IoT) networks has created an urgent need for sustainable energy solutions, particularly for the battery-constrained spatially distributed IoT nodes. While low-altitude uncrewed aerial vehicles (UAVs) employed with wireless power transfer (WPT) capabilities offer a promising solution, the line-of-sight channels that facilitate efficient energy delivery also expose sensitive operational data to adversaries. This paper proposes a novel low-altitude UAV-carried movable antenna-enhanced transmission system joint WPT and covert communications, which simultaneously performs energy supplements to IoT nodes and establishes transmission links with a covert user by leveraging wireless energy signals as a natural cover. Then, we formulate a multi-objective optimization problem that jointly maximizes the total harvested energy of IoT nodes and sum achievable rate of the covert user, while minimizing the propulsion energy consumption of the low-altitude UAV. To address the non-convex and temporally coupled optimization problem, we propose a mixture-of-experts-augmented soft actor-critic (MoE-SAC) algorithm that employs a sparse Top-K gated mixture-of-shallow-experts architecture to represent multimodal policy distributions arising from the conflicting optimization objectives. We also incorporate an action projection module that explicitly enforces per-time-slot power budget constraints and antenna position constraints. Simulation results demonstrate that the proposed approach significantly outperforms some baseline approaches and other state-of-the-art deep reinforcement learning algorithms.

Accurate and timely crop yield prediction is crucial for global food security and modern agricultural management. Traditional methods often lack the scalability and granularity required for precision farming. This paper introduces FARM: Fine-tuning Agricultural Regression Models, a deep learning framework designed for high-resolution, intra-field canola yield prediction. FARM leverages a pre-trained, large-scale geospatial foundation model (Prithvi-EO-2.0-600M) and adapts it for a continuous regression task, transforming multi-temporal satellite imagery into dense, pixel-level (30 m) yield maps. Evaluated on a comprehensive dataset from the Canadian Prairies, FARM achieves a Root Mean Squared Error (RMSE) of 0.44 and an R^2 of 0.81. Using an independent high-resolution yield monitor dataset, we further show that fine-tuning FARM on limited ground-truth labels outperforms training the same architecture from scratch, confirming the benefit of pre-training on large, upsampled county-level data for data-scarce precision agriculture. These results represent improvement over baseline architectures like 3D-CNN and DeepYield, which highlight the effectiveness of fine-tuning foundation models for specialized agricultural applications. By providing a continuous, high-resolution output, FARM offers a more actionable tool for precision agriculture than conventional classification or county-level aggregation methods. This work validates a novel approach that bridges the gap between large-scale Earth observation and on-farm decision-making, offering a scalable solution for detailed agricultural monitoring.

The proliferation of inverter-based resources challenges traditional microgrid protection by introducing variable fault currents and complex transients. This paper presents a statistically adaptive differential protection scheme based on Kullback-Leibler divergence, implemented via a Bartlett-corrected G-statistic computed on logarithm-transformed current magnitudes. The method is a multivariate fault detection engine that employs the Mahalanobis distance to distinguish healthy and faulty states, enabling robust detection even in noisy environments. Detection thresholds are statistically derived from a chi-squared distribution for precise control over the false alarm rate. Upon detection, a lightweight classifier identifies the fault type by assessing per-phase G-statistics against dedicated thresholds, enhanced by a temporal persistence filter for security. Extensive simulations on a modified CIGRE 14-bus microgrid show high efficacy: sub-cycle average detection delays, high detection and classification accuracy across operating modes, resilience to high-impedance faults up to 250 Ohms, tolerance to 10 ms communication delay, and noise levels down to a 20 dB signal-to-noise ratio. These findings demonstrate a reproducible and computationally efficient solution for next-generation AC microgrid protection.

The electricity sector transition requires substantial increases in residential demand response capacity, yet Home Energy Management Systems (HEMS) adoption remains limited by user interaction barriers requiring translation of everyday preferences into technical parameters. While large language models have been applied to energy systems as code generators and parameter extractors, no existing implementation deploys LLMs as autonomous coordinators managing the complete workflow from natural language input to multi-appliance scheduling. This paper presents an agentic AI HEMS where LLMs autonomously coordinate multi-appliance scheduling from natural language requests to device control, achieving optimal scheduling without example demonstrations. A hierarchical architecture combining one orchestrator with three specialist agents uses the ReAct pattern for iterative reasoning, enabling dynamic coordination without hardcoded workflows while integrating Google Calendar for context-aware deadline extraction. Evaluation across three open-source models using real Austrian day-ahead electricity prices reveals substantial capability differences. Llama-3.3-70B successfully coordinates all appliances across all scenarios to match cost-optimal benchmarks computed via mixed-integer linear programming, while other models achieve perfect single-appliance performance but struggle to coordinate all appliances simultaneously. Progressive prompt engineering experiments demonstrate that analytical query handling without explicit guidance remains unreliable despite models' general reasoning capabilities. We open-source the complete system including orchestration logic, agent prompts, tools, and web interfaces to enable reproducibility, extension, and future research.

The increasing integration of renewable energy sources and distributed energy resources (DER) into modern power systems introduces significant uncertainty, posing challenges for maintaining grid flexibility and reliability. Hybrid energy systems (HES), composed of controllable generators, flexible loads, and battery storage, offer a decentralized solution to enhance flexibility compared to single centralized resources. This paper presents a two-level framework to enable HES participation in frequency regulation markets. The upper level performs a chance-constrained optimization to choose capacity bids based on historical regulation signals. At the lower level, a real-time control strategy disaggregates the regulation power among the constituent resources. This real-time control strategy is then benchmarked against an offline optimal dispatch to evaluate flexibility performance. Additionally, the framework evaluates the profitability of overbidding strategies and identifies thresholds beyond which performance degradation may lead to market penalties or disqualification. The proposed framework also compare the impact of imbalance of power capacities on performance and battery state of charge (SoC) through asymmetric HES configurations.

In post-disaster scenarios, the rapid deployment of adequate communication infrastructure is essential to support disaster search, rescue, and recovery operations. To achieve this, uncrewed aerial vehicle (UAV) has emerged as a promising solution for emergency communication due to its low cost and deployment flexibility. However, conventional untethered UAV (U-UAV) is constrained by size, weight, and power (SWaP) limitations, making it incapable of maintaining the operation of a macro base station. To address this limitation, we propose a heterogeneous UAV-based framework that integrates tethered UAV (T-UAV) and U-UAVs, where U-UAVs are utilized to enhance the throughput of cell-edge ground user equipments (G-UEs) and guarantee seamless connectivity during G-UEs' mobility to safe zones. It is noted that the integrated access and backhaul (IAB) technique is adopted to support the wireless backhaul of U-UAVs. Accordingly, we formulate a two-timescale joint user scheduling and trajectory control optimization problem, aiming to maximize the downlink throughput under asymmetric traffic demands and G-UEs' mobility. To solve the formulated problem, we proposed a two-timescale multi-agent deep deterministic policy gradient (TTS-MADDPG) algorithm based on the centralized training and distributed execution paradigm. Numerical results show that the proposed algorithm outperforms other benchmarks, including the two-timescale multi-agent proximal policy optimization (TTS-MAPPO) algorithm and MADDPG scheduling method, with robust and higher throughput. Specifically, the proposed algorithm obtains up to 12.2% average throughput gain compared to the MADDPG scheduling method.

Olive tree biovolume estimation is a key task in precision agriculture, supporting yield prediction and resource management, especially in Mediterranean regions severely impacted by climate-induced stress. This study presents a comparative analysis of three deep learning models U-Net, YOLOv11m-seg, and Mask RCNN for segmenting olive tree crowns and their shadows in ultra-high resolution UAV imagery. The UAV dataset, acquired over Vicopisano, Italy, includes manually annotated crown and shadow masks. Building on these annotations, the methodology emphasizes spatial feature extraction and robust segmentation; per-tree biovolume is then estimated by combining crown projected area with shadow-derived height using solar geometry. In testing, Mask R-CNN achieved the best overall accuracy (F1 = 0.86; mIoU = 0.72), while YOLOv11m-seg provided the fastest throughput (0.12 second per image). The estimated biovolumes spanned from approximately 4 to 24 cubic meters, reflecting clear structural differences among trees. These results indicate Mask R-CNN is preferable when biovolume accuracy is paramount, whereas YOLOv11m-seg suits large-area deployments where speed is critical; U-Net remains a lightweight, high-sensitivity option. The framework enables accurate, scalable orchard monitoring and can be further strengthened with DEM or DSM integration and field calibration for operational decision support.

People tend to walk in groups, and interactions with those groups have a significant impact on crowd behavior and pedestrian traffic dynamics. Social norms can be seen as unwritten rules regulating people interactions in social settings. This article studies people interactions with groups and the emergence of group proxemics. Group zones, zone occupancy counts and people clearance from the group are studied using naturalistic data. Analysis indicate potential presence of three different zones in addition to the public zone. People tend to remain in the public zone and only progressively get closer to groups, and those closer approaches happen in a low frequency and for brief periods of time.

This article investigates the pedestrian group as an emergent agent. The article explores empirical data to derive emergent agency and formation state spaces and outline recurring patterns of walking behavior. In this analysis, pedestrian trajectories extracted from surveillance videos are used along with manually annotated pedestrian group memberships. We conducted manual expert evaluation of observed groups, produced new manual annotations for relevant events pertaining to group behavior and extracted metrics relevant group formation. This information along with quantitative analysis was used to model the life-cycle and formation of the group agent. Those models give structure to expectations around walking behavior of groups; from pedestrian walking independently to the emergence of a collective intention where group members tended to maintain bounded distance between each other. Disturbances to this bounded distance often happened in association with changes in either their agency or their formation states. We summarized the patterns of behavior along with the sequences of state transitions into abstract patterns, which can aid in the development of more detailed group agents in simulation and in the design of engineering systems to interact with such groups.

In the classical setting, the training of a Hidden Markov Model (HMM) typically relies on a single, sufficiently long observation sequence that can be regarded as representative of the underlying stochastic process. In this context, the Expectation Maximization (EM) algorithm is applied in its specialized form for HMMs, namely the Baum Welch algorithm, which has been extensively employed in applications such as speech recognition. The objective of this work is to present pseudocode formulations for both the training and decoding procedures of HMMs in a different scenario, where the available data consist of multiple independent temporal sequences generated by the same model, each of relatively short duration, i.e., containing only a limited number of samples. Special emphasis is placed on the relevance of this formulation to longitudinal studies in population health, where datasets are naturally structured as collections of short trajectories across individuals with point data at follow up.

This article proposes a modular optimal control framework for local three-dimensional ellipsoidal obstacle avoidance, exemplarily applied to model predictive path-following control. Static as well as moving obstacles are considered. Central to the approach is a computationally efficient and continuously differentiable condition for detecting collisions with ellipsoidal obstacles. A novel two-stage optimization approach mitigates numerical issues arising from the structure of the resulting optimal control problem. The effectiveness of the approach is demonstrated through simulations and real-world experiments with the Crazyflie quadrotor. This represents the first hardware demonstration of an MPC controller of this kind for UAVs in a three-dimensional task.

We investigate the gain margin of a general nonlinear system under an inverse optimal input-to-state safe (ISSf) controller of the form u=u0(x)+u*(x,u0), where u0 is the nominal control and u* is the inverse optimal safety filter that minimally modifies the nominal controller's unsafe actions over the infinite horizon. By first establishing a converse ISSf-BF theorem, we reveal the equivalence among the achievability of ISSf by feedback, the achievability of inverse optimality, and the solvability of a Hamilton-Jacobi-Isaacs equation associated with the inverse optimal ISSf gain assignment. Then we develop a collection of safety margin results on the overall control u=u0+u*. In the absence of disturbances, we find that standard inverse optimal safe controllers have a certain degree of gain margin. Specifically, when f(x) acts safely but u0 acts unsafely, the gain can be decreased by up to half; and when f(x) acts unsafely, we establish that, if u0 acts safely, the gain can be increased arbitrarily, whereas if u0 acts unsafely, the control recovers the full gain margin [1/2,inf). It is shown, however, that under control gain variation, the safe set of these controllers is locally asymptotically stable, which implies that their safety is sensitive to large but bounded disturbances. To make inverse optimal ISSf controllers robust to gain variation, we propose a gain margin improvement approach at the expense of an increased control effort. This improvement allows the inverse optimal safe control to inherit the standard gain margin of [1/2,inf) without requiring prior knowledge of whether f(x) or u0 acts safely on the safety boundary, while simultaneously ensuring global asymptotic stability of the resulting safe set. In the presence of disturbances, this improvement idea renders inverse optimal ISSf controllers robust to gain variations with the same gain margin of [1/2,inf).

The manufacturing sector is moving from rigid, hardware-dependent systems toward flexible, software-driven environments. This transformation is shaped by the convergence of several Software-Defined technologies: Software-Defined Automation virtualizes industrial control, replacing proprietary PLCs with containerized, programmable solutions that enable scalability and interoperability. Software-Defined Compute and Communications provide a means to distribute intelligence seamlessly across devices, networks, and cloud platforms, reducing latency and enabling dynamic reconfiguration. Software-Defined Manufacturing Systems, usually implemented as Digital Twins, are real-time virtual models of machines and processes, allowing predictive analysis, optimization, and closer integration between human operators and intelligent systems. This work presents XWAVE, a project that unites these three Software-Defined paradigms to present a modular, fully software-defined manufacturing system.

Multi-organ segmentation is a critical task in computer-aided diagnosis. While recent deep learning methods have achieved remarkable success in image segmentation, huge variations in organ size and shape challenge their effectiveness in multi-organ segmentation. To address these challenges, we propose a Spatial Prior-Guided Cross Dual Encoder Network (SPG-CDENet), a novel two-stage segmentation paradigm designed to improve multi-organ segmentation accuracy. Our SPG-CDENet consists of two key components: a spatial prior network and a cross dual encoder network. The prior network generates coarse localization maps that delineate the approximate ROI, serving as spatial guidance for the dual encoder network. The cross dual encoder network comprises four essential components: a global encoder, a local encoder, a symmetric cross-attention module, and a flow-based decoder. The global encoder captures global semantic features from the entire image, while the local encoder focuses on features from the prior network. To enhance the interaction between the global and local encoders, a symmetric cross-attention module is proposed across all layers of the encoders to fuse and refine features. Furthermore, the flow-based decoder directly propagates high-level semantic features from the final encoder layer to all decoder layers, maximizing feature preservation and utilization. Extensive qualitative and quantitative experiments on two public datasets demonstrate the superior performance of SPG-CDENet compared to existing segmentation methods. Furthermore, ablation studies further validate the effectiveness of the proposed modules in improving segmentation accuracy.

We propose a command-filter backstepping controller that integrates a disturbance observer and a high-gain observer (HGO) to handle unknown internal and external disturbances acting on a quadrotor. To build the controller, we first define tracking errors between the measured and desired quadrotor outputs, which allow the system to be rewritten in a new set of state variables. Using this transformed model, we apply Lyapunov theory to derive a backstepping control law. To avoid repeated differentiation of states and virtual controls, a first-order command filter is introduced, and a nonlinear disturbance observer is added to provide disturbance estimates. Each state in the controller and observer is replaced with its estimate from the HGO. The resulting control law enables the quadrotor to follow its path despite internal and external disturbances, with each subsystem allowed its own disturbance type for realism. A new state transformation and Lyapunov-based derivation prevent the usual explosion of complexity, while the HGO reconstructs unmeasured states and their rates for output feedback. The nonlinear disturbance observer attenuates constant and nonlinear disturbances as well as band-limited white noise. The method reduces dependence on high-precision sensors and mitigates wind, model error, and rotor noise effects during flight. Unlike previous studies that treat either disturbance rejection or partial sensing, this work combines the command filter, disturbance observer, and HGO to address both challenges simultaneously while avoiding the complexity growth typical of backstepping designs.

Many tasks in human environments require collaborative behavior between multiple kinematic chains, either to provide additional support for carrying big and bulky objects or to enable the dexterity that is required for in-hand manipulation. Since these complex systems often have a very high number of degrees of freedom coordinating their movements is notoriously difficult to model. In this article, we present the derivation of the theoretical foundations for cooperative task spaces of multi-arm robotic systems based on geometric primitives defined using conformal geometric algebra. Based on the similarity transformations of these cooperative geometric primitives, we derive an abstraction of complex robotic systems that enables representing these systems in a way that directly corresponds to single-arm systems. By deriving the associated analytic and geometric Jacobian matrices, we then show the straightforward integration of our approach into classical control techniques rooted in operational space control. We demonstrate this using bimanual manipulators, humanoids and multi-fingered hands in optimal control experiments for reaching desired geometric primitives and in teleoperation experiments using differential kinematics control. We then discuss how the geometric primitives naturally embed nullspace structures into the controllers that can be exploited for introducing secondary control objectives. This work, represents the theoretical foundations of this cooperative manipulation control framework, and thus the experiments are presented in an abstract way, while giving pointers towards potential future applications.

This paper studies how to achieve accurate modeling and effective control in stochastic nonlinear dynamics with multiple interacting objects. However, non-uniform interactions and random topologies make this task challenging. We address these challenges by proposing Graph Controllable Embeddings (GCE), a general framework to learn stochastic multi-object dynamics for linear control. Specifically, GCE is built on Hilbert space embeddings, allowing direct embedding of probability distributions of controlled stochastic dynamics into a reproducing kernel Hilbert space (RKHS), which enables linear operations in its RKHS while retaining nonlinear expressiveness. We provide theoretical guarantees on the existence, convergence, and applicability of GCE. Notably, a mean field approximation technique is adopted to efficiently capture inter-object dependencies and achieve provably low sample complexity. By integrating graph neural networks, we construct data-dependent kernel features that are capable of adapting to dynamic interaction patterns and generalizing to even unseen topologies with only limited training instances. GCE scales seamlessly to multi-object systems of varying sizes and topologies. Leveraging the linearity of Hilbert spaces, GCE also supports simple yet effective control algorithms for synthesizing optimal sequences. Experiments on physical systems, robotics, and power grids validate GCE and demonstrate consistent performance improvement over various competitive embedding methods in both in-distribution and few-shot tests

Accurate Angle-of-arrival (AoA) estimation is essential for next-generation wireless communication systems to enable reliable beamforming, high-precision localization, and integrated sensing. Unfortunately, classical high-resolution techniques require multi-element arrays and extensive snapshot collection, while generic Machine Learning (ML) approaches often yield black-box models that lack physical interpretability. To address these limitations, we propose a Symbolic Regression (SR)-based ML framework. Namely, Symbolic Regression-based Angle of Arrival and Beam Pattern Estimator (SABER), a constrained symbolic-regression framework that automatically discovers closed-form beam pattern and AoA models from path loss measurements with interpretability. SABER achieves high accuracy while bridging the gap between opaque ML methods and interpretable physics-driven estimators. First, we validate our approach in a controlled free-space anechoic chamber, showing that both direct inversion of the known $\cos^n$ beam and a low-order polynomial surrogate achieve sub-0.5 degree Mean Absolute Error (MAE). A purely unconstrained SR method can further reduce the error of the predicted angles, but produces complex formulas that lack physical insight. Then, we implement the same SR-learned inversions in a real-world, Reconfigurable Intelligent Surface (RIS)-aided indoor testbed. SABER and unconstrained SR models accurately recover the true AoA with near-zero error. Finally, we benchmark SABER against the Cramér-Rao Lower Bounds (CRLBs). Our results demonstrate that SABER is an interpretable and accurate alternative to state-of-the-art and black-box ML-based methods for AoA estimation.