Papers

This article develops an optical navigation (OPNAV) and station-keeping pipeline for the near-rectilinear halo orbit (NRHO) in high-fidelity ephemeris model dynamics, using synthetic images of the Moon in a non-iterative horizon-based OPNAV algorithm, applying the result in a navigation filter, and using the obtained estimates in a station-keeping control scheme that keeps the spacecraft in the vicinity of a reference orbit. We study differential correction-based and minimization-based implementations of the so-called x-axis and propose an improved targeting prediction scheme by incorporating the filter's state covariance with an unscented transform. We also introduce a hysteresis mechanism, which improves stationkeeping cost and provides insight into the difference in performance between the differential correction-based and minimization-based approaches. We perform Monte-Carlo experiments to assess the pipeline's tracking and Delta-V performances. We report several key findings, including the variability of the filter performance with the sensor field of view and measurement locations, station-keeping cost reduction achieved by the unscented transform-based prediction and hysteresis, as well as the variability of the cumulative Delta-V as a function of maneuver location due to the periodic structure in the OPNAV-based filter's estimation accuracy.

This study presents a reinforcement learning (RL)-based control strategy for adaptive lighting regulation in controlled environments using a low-power microcontroller. A model-free Q-learning algorithm was implemented to dynamically adjust the brightness of a Light-Emitting Diode (LED) based on real-time feedback from a light-dependent resistor (LDR) sensor. The system was trained to stabilize at 13 distinct light intensity levels (L1 to L13), with each target corresponding to a specific range within the 64-state space derived from LDR readings. A total of 130 trials were conducted, covering all target levels with 10 episodes each. Performance was evaluated in terms of convergence speed, steps taken, and time required to reach target states. Box plots and histograms were generated to analyze the distribution of training time and learning efficiency across targets. Experimental validation demonstrated that the agent could effectively learn to stabilize at varying light levels with minimal overshooting and smooth convergence, even in the presence of environmental perturbations. This work highlights the feasibility of lightweight, on-device RL for energy-efficient lighting control and sets the groundwork for multi-modal environmental control applications in resource-constrained agricultural systems.

Unmanned Aerial Vehicle (UAV) technologies are gaining high interest for many domains, which makes UAV security of utmost importance. ArduPilot is among the most widely used open-source autopilot UAV frameworks; yet, many studies demonstrate the vulnerabilities affecting such systems. Vulnerabilities within its communication subsystems (including WiFi, telemetry, or GPS) expose critical entry points, and vulnerabilities in Ardupilot can affect the control procedure. In this paper, we reconstruct the software architecture and the control models implemented by ArduPilot and then examine how these control models could potentially misused to induce malicious behaviors while relying on legitimate inputs.

Automatic speech recognition (ASR) for African languages remains constrained by limited labeled data and the lack of systematic guidance on model selection, data scaling, and decoding strategies. Large pre-trained systems such as Whisper, XLS-R, MMS, and W2v-BERT have expanded access to ASR technology, but their comparative behavior in African low-resource contexts has not been studied in a unified and systematic way. In this work, we benchmark four state-of-the-art ASR models across 13 African languages, fine-tuning them on progressively larger subsets of transcribed data ranging from 1 to 400 hours. Beyond reporting error rates, we provide new insights into why models behave differently under varying conditions. We show that MMS and W2v-BERT are more data efficient in very low-resource regimes, XLS-R scales more effectively as additional data becomes available, and Whisper demonstrates advantages in mid-resource conditions. We also analyze where external language model decoding yields improvements and identify cases where it plateaus or introduces additional errors, depending on the alignment between acoustic and text resources. By highlighting the interaction between pre-training coverage, model architecture, dataset domain, and resource availability, this study offers practical and insights into the design of ASR systems for underrepresented languages.

Automatic Speech Recognition (ASR) is increasingly used to document clinical encounters, yet its reliability in multilingual and demographically diverse Indian healthcare contexts remains largely unknown. In this study, we conduct the first systematic audit of ASR performance on real world clinical interview data spanning Kannada, Hindi, and Indian English, comparing leading models including Indic Whisper, Whisper, Sarvam, Google speech to text, Gemma3n, Omnilingual, Vaani, and Gemini. We evaluate transcription accuracy across languages, speakers, and demographic subgroups, with a particular focus on error patterns affecting patients vs. clinicians and gender based or intersectional disparities. Our results reveal substantial variability across models and languages, with some systems performing competitively on Indian English but failing on code mixed or vernacular speech. We also uncover systematic performance gaps tied to speaker role and gender, raising concerns about equitable deployment in clinical settings. By providing a comprehensive multilingual benchmark and fairness analysis, our work highlights the need for culturally and demographically inclusive ASR development for healthcare ecosystem in India.

Accurate and early diagnosis of Alzheimer's disease (AD) is critical for effective intervention and requires integrating complementary information from multimodal neuroimaging data. However, conventional fusion approaches often rely on simple concatenation of features, which cannot adaptively balance the contributions of biomarkers such as amyloid PET and MRI across brain regions. In this work, we propose MREF-AD, a Multimodal Regional Expert Fusion model for AD diagnosis. It is a Mixture-of-Experts (MoE) framework that models mesoscopic brain regions within each modality as independent experts and employs a gating network to learn subject-specific fusion weights. Utilizing tabular neuroimaging and demographic information from the Alzheimer's Disease Neuroimaging Initiative (ADNI), MREF-AD achieves competitive performance over strong classic and deep baselines while providing interpretable, modality- and region-level insight into how structural and molecular imaging jointly contribute to AD diagnosis. The source code is available at https://github.com/PennShenLab/mref-ad.

Self-supervised contrastive learning is among the recent representation learning methods that have shown performance gains in several downstream tasks including semantic segmentation. This paper evaluates strong data augmentation, one of the most important components for self-supervised contrastive learning's improved performance. Strong data augmentation involves applying the composition of multiple augmentation techniques on images. Surprisingly, we find that the existing data augmentations do not always improve performance for semantic segmentation for medical images. We experiment with other augmentations that provide improved performance.

Coordinating emergency responses in extreme environments, such as wildfires, requires resilient and high-bandwidth communication backbones. While autonomous aerial swarms can establish ad-hoc networks to provide this connectivity, the high risk of individual node attrition in these settings often leads to network fragmentation and mission-critical downtime. To overcome this challenge, we introduce and formalize the problem of Robust Task Networking Under Attrition (RTNUA), which extends connectivity maintenance in multi-robot systems to explicitly address proactive redundancy and attrition recovery. We then introduce Physics-Informed Robust Employment of Multi-Agent Networks ($\Phi$IREMAN), a topological algorithm leveraging physics-inspired potential fields to solve this problem. In our evaluations, $\Phi$IREMAN consistently outperforms baselines, and is able to maintain greater than $99.9\%$ task uptime despite substantial attrition in simulations with up to 100 tasks and 500 drones, demonstrating both effectiveness and scalability.

Multi-echo Gradient Echo (mGRE) sequences provide valuable quantitative parametric maps, such as Quantitative Susceptibility Mapping (QSM) and transverse relaxation rate (R2*), sensitive to tissue iron and myelin. However, structural morphometry typically relies on separate T1-weighted MPRAGE acquisitions, prolonging scan times. We propose a deep learning framework to synthesize high-contrast 3D T1w MPRAGE images directly from mGRE data, streamlining neuroimaging protocols. We developed a novel multi-parametric conditional diffusion model based on the Fast-DDPM architecture. Unlike conventional intensity-based synthesis, our approach integrates iron-sensitive QSM and R2* maps as physical priors to address contrast ambiguity in iron-rich deep gray matter. We trained and validated the model on 175 healthy subjects. Performance was evaluated against established U-Net and GAN-based baselines using perceptual metrics and downstream segmentation accuracy. Uniquely, we assessed the biological plausibility of synthesized images by replicating population-level statistical associations with age and sex. The proposed framework significantly outperformed baselines, achieving superior perceptual quality and segmentation accuracy, particularly in subcortical regions like the thalamus and pallidum. Crucially, synthesized images preserved essential biological dependencies: regression analyses showed high concordance in age-related atrophy rates, aging effect sizes, and sexual dimorphism patterns compared to ground truth. By effectively leveraging quantitative MRI priors, our diffusion-based method generates strictly biologically plausible T1w images suitable for reliable clinical morphometric analysis. This approach offers a promising pathway to reduce acquisition time by deriving structural contrasts retrospectively from quantitative mGRE sequences.

Neuromorphic engineering makes use of mixed-signal analog and digital circuits to directly emulate the computational principles of biological brains. Such electronic systems offer a high degree of adaptability, robustness, and energy efficiency across a wide range of tasks, from edge computing to robotics. Within this context, we investigate a key feature of biological neurons: their ability to carry out robust and reliable computation by adapting their input responses and spiking patterns to context through neuromodulation. Achieving analogous levels of robustness and adaptation in neuromorphic circuits through modulatory mechanisms is a largely unexplored path. We present a novel current-mode neuron design that supports robust neuromodulation with minimal model complexity, compatible with standard CMOS technologies. We first introduce a mathematical model of the circuit and provide tools to analyze and tune the neuron behavior; we then demonstrate both theoretically and experimentally the biologically plausible neuromodulation adaptation capabilities of the circuit over a wide range of parameters. All theoretical predictions were verified in experiments on a low-power 180 nm CMOS implementation of the proposed neuron circuit. Due to the analog underlying feedback structure, the proposed adaptive neuromodulable neuron exhibits a high degree of robustness, flexibility, and scalability across operating ranges of currents and temperatures, making it a perfect candidate for real-world neuromorphic applications.

As mission-critical (MC) services such as Unmanned Aerial Vehicles (UAVs) based emergency communication and Internet of Vehicles (IoVs) enabled autonomous driving emerge, the traditional communication framework can not meet the growing demands for higher reliability and lower latency and the increasing transmission loads. Semantic Communication (SemCom), an emerging communication paradigm that shifts the focus from bit-level data to its context and intended task at the receiver (i.e., semantic level), is envisioned to be a key revolution in Sixth Generation (6G) networks. However, an explicit and systematic SemCom framework specifically tailored for Vehicle-based MC (VbMC) services has yet to be proposed, primarily due to the complexity and lack of analysis on their MC characteristics. In this article, we first present the key information-critical and infrastructure-critical vehicle-based services within the SemCom framework. We then analyze the unique characteristics of MC services and the corresponding challenges they present for SemCom. Building on this, we propose a novel SemCom framework designed to address the specific needs of MC services in vehicle systems, offering potential solutions to existing challenges. Finally, we present a case study on UAV-based rapid congestion relief, utilizing eXplainable AI (XAI) to validate the effectiveness of the proposed SemCom framework.

In multilevel supervisor synthesis, dependency structure matrix techniques can be used to transform the models of plants and requirements into a tree-structured hierarchical decomposition of the synthesis problem and thus efficiently synthesize local supervisors. A bus component, which has many dependencies across a system, tends to lead to an undesirable clustering of many components in one synthesis subproblem. Prior work showed how to recognize and properly treat a global bus structure. In this paper we leverage this work from global to local bus structures through a novel multilevel discrete-event system (MLDES) architecture. Specifically, the hierarchical system decomposition is revisited by allowing bus detection not only on the top level but at each level of the system hierarchy. Given this architecture, an algorithm is introduced that constructs a tree-structured MLDES. A case study on a production line shows the effectiveness of the proposed method through significantly improved synthesis performance, measured by the sum of the controlled state-space sizes of the local supervisors.

In this paper we consider an interchange lane-swap scenario, a limited stretch of highway with two parallel lanes where most vehicles want to change lanes. We show that a particular decentralized Control Barrier Function based algorithm executes lane swaps efficiently, with minimal speed change, within the specified (short) road segment at high traffic densities (3,500 vehicles per hour per lane). Our main point is that controller tuning, the speed of inter-agent instability, plays a major role in the performance of the vehicle group. This is illustrated by comparing two different tunings of the controller and a third one where the lane swap is enforced by virtual guard rails. Like fighter jet dynamic instability improving maneuverability, the inter-agent instability improves agility of a group of vehicles. We emphasize that the controllers considered are decentralized: agents do not know if others want to change lanes or not.

Molecular communication (MC) studies biological signals that are found in nature. Most MC literature focuses on particle properties, even though many natural phenomena exhibit wave-like behavior. One such signal is sound waves. Understanding how sound waves are used in nature can help us better utilize this signal in our interactions with our environment. To take a step in this direction, in this paper, we examine how plants process incoming sound waves and take informed actions. Indeed, plants respond to sound, yet no quantitative communication-theoretic model currently explains this behavior. This study develops the first end-to-end acoustic communication framework for plants. The model is formed following the biological steps of the incoming signal, and a mathematical description is constructed at each step following basic biological models. The resulting end-to-end communication-theoretic model is analyzed using MATLAB. Simulations show that a $200$ $Hz$, $20$ $mu Pa$ stimulus elevates cytosolic $Ca^{2+}$ from $150$ $nM$ to $230 \pm 10$ $nM$ within $50$ seconds which can cause root bending in plants in the long run. This work establishes quantitative phytoacoustics, enabling bio-inspired acoustic connections for precision agriculture and plant signaling research.

Multipurpose batch processes become increasingly popular in manufacturing industries since they adapt to low-volume, high-value products and shifting demands. These processes often operate in a dynamic environment, which faces disturbances such as processing delays and demand changes. To minimise long-term cost and system nervousness (i.e., disruptive changes to schedules), schedulers must design rescheduling strategies to address such disturbances effectively. Existing methods often assume complete look-ahead information over the scheduling horizon. This assumption contrasts with realistic situations where schedulers can only access incomplete look-ahead information. Sticking with existing methods may lead to suboptimal long-term costs and high-level system nervousness. In this work we propose a Bayesian dynamic scheduling method. Our method relies on learning a Bayesian Network from the probability distribution of disturbances. Specifically, the Bayesian Network represents how likely each operation will be impacted by disturbances. During the online execution, when new disturbances become observed, this method updates the posterior distribution and therefore guides the rescheduling strategy. We compare our method with the existing periodic rescheduling strategy (which generates new schedules from scratch at fixed intervals) on four benchmark problems. Computational results show that our method achieves statistically better long-term costs and system nervousness. In the theoretical aspect, we prove that if disturbances are mutually independent, the impact-quantifying variables inherently satisfy the independence assumptions required by Bayesian Networks. As an implication, practitioners can extend the method to other scheduling problems (such as job shop scheduling and continuous processes), given that they define the problem-specific dependencies between operations.

In tropical semiarid regions, prickly pear cactus has emerged as a vital forage resource due to its high drought tolerance and minimal water requirements. However, even limited weed infestation can severely compromise cactus productivity, as the species are highly sensitive to competition for essential resources, which includes water, mineral nutrients, and sun exposure. Conventional herbicide-based weed control strategies face growing limitations due to resistance development and environmental concerns, underscoring the need for sustainable alternatives. This study revisits the historically underexplored application of linear Fresnel lenses for thermal weed control and establishes the technical feasibility of a contemporary autonomous weed management system that incorporates LFL technology within an unmanned ground vehicle platform. Leveraging real-time image processing, georeferencing, and mechanical actuation, the system can perform a two-phase operation-weed mapping during non-optimal solar hours and targeted solar termination during peak irradiance. Analytical modeling quantifies the effective area coverage and time constraints imposed by the solar window. Preliminary results indicate that, while unsuitable for dense weed infestations, the system presents a viable solution for precision, post-emergent weed control in sparse infestations. The favorable solar geometry in tropical zones, especially in the Brazilian semiarid region, and the targeted nature of the approach make this technology particularly well-suited for sustainable agriculture in under-resourced regions.

This paper presents the development of a control law, which is intended to be implemented on an optical guided glider. This guiding law follows an innovative approach, the reinforcement learning. This control law is used to make navigation more flexible and autonomous in a dynamic environment. The final objective is to track a target detected with the camera and then guide the glider to this point with high precision. Already applied on quad-copter drones, we wish by this study to demonstrate the applicability of reinforcement learning for fixed-wing aircraft on all of its axis.

Accurate remote state estimation is a fundamental component of many autonomous and networked dynamical systems, where multiple decision-making agents interact and communicate over shared, bandwidth-constrained channels. These communication constraints introduce an additional layer of complexity, namely, the decision of when to communicate. This results in a fundamental trade-off between estimation accuracy and communication resource usage. Traditional extensions of classical estimation algorithms (e.g., the Kalman filter) treat the absence of communication as 'missing' information. However, silence itself can carry implicit information about the system's state, which, if properly interpreted, can enhance the estimation quality even in the absence of explicit communication. Leveraging this implicit structure, however, poses significant analytical challenges, even in relatively simple systems. In this paper, we propose CALM (Communication-Aware Learning and Monitoring), a novel learning-based framework that jointly addresses the dual challenges of communication scheduling and estimator design. Our approach entails learning not only when to communicate but also how to infer useful information from periods of communication silence. We perform comparative case studies on multiple benchmarks to demonstrate that CALM is able to decode the implicit coordination between the estimator and the scheduler to extract information from the instances of 'silence' and enhance the estimation accuracy.

Particle filtering algorithms have enabled practical solutions to problems in autonomous robotics (self-driving cars, UAVs, warehouse robots), target tracking, and econometrics, with further applications in speech processing and medicine (patient monitoring). Yet, their inherent weakness at representing the likelihood of the observation (which often leads to particle degeneracy) remains unaddressed for real-time resource-constrained systems. Improvements such as the optimal proposal and auxiliary particle filter mitigate this issue under specific circumstances and with increased computational cost. This work presents a new particle filtering method and its implementation, which enables tunably-approximative representation of arbitrary likelihood densities as program transformations of parametric distributions. Our method leverages a recent computing platform thatcan perform deterministic computation on probability distributionrepresentations (UxHw) without relying on stochastic methods. For non-Gaussian non-linear systems and with an optimal-auxiliary particle filter, we benchmark the likelihood evaluation error and speed for a total of 294840 evaluation points. For such models, the results show that the UxHw method leads to as much as 37.7x speedup compared to the Monte Carlo alternative. For narrow uniform measurement uncertainty, the particle filter falsely assigns zero likelihood as much as 81.89% of the time whereas UxHw achieves 1.52% false-zero rate. The UxHw approach achieves filter RMSE improvement of as much as 18.9% (average 3.3%) over the Monte Carlo alternative.

Continuous energy monitoring is essential for identifying potential savings and predicting the energy requirements of buildings. Energy meters are often located in underground spaces that are difficult to reach with wireless technology. This paper presents an experimental study comparing different Low Power Wide Area Networks (LPWAN) technologies in terms of building penetration and radio coverage. The technologies Low Power Long Range Wide Area Networks (LoRaWAN), Narrow Band Internet of Things (NB-IoT), Sigfox 0G and Wireless Smart Ubiquitous Networks (Wi-SUN) are evaluated experimentally. It also proposes a distributed hybrid IoT architecture that combines multiple LPWAN technologies using an abstraction layer to optimize cost and coverage. Communication is message-based using the publish-subscribe messaging pattern. It is implemented using the MQTT protocol. The abstraction layer decodes the proprietary binary data and converts it to a normalized JSON format.

Faults and operational disturbances in Heat Recovery Steam Generators (HRSGs), such as valve leakage, present significant challenges, disrupting steam temperature regulation and potentially causing efficiency losses, safety risks, and unit shutdowns. Traditional PI controllers often struggle due to inherent system delays, nonlinear dynamics, and static gain limitations. This paper introduces a fault-tolerant temperature control framework by integrating a PI plus feedforward control strategy with Physics-Informed Neural Networks (PINNs). The feedforward component anticipates disturbances, preemptively adjusting control actions, while the PINN adaptively tunes control gains in real-time, embedding thermodynamic constraints to manage varying operating conditions and valve leakage faults. A Lyapunov-based stability analysis confirms the asymptotic convergence of temperature tracking errors under bounded leakage conditions. Simulation results using operational data from the Pareh-Sar combined cycle power plant demonstrate significantly improved response times, reduced temperature deviations, enhanced fault resilience, and smooth gain adjustments. The proposed adaptive, data-driven methodology shows strong potential for industrial deployment, ensuring reliable operation, autonomous fault recovery, and enhanced performance in HRSG systems.

The transition to prescriptive maintenance (PsM) in manufacturing is critically constrained by a dependence on predictive models. Such purely predictive models tend to capture statistical associations in the data without identifying the underlying causal drivers of failure, which can lead to costly misdiagnoses and ineffective measures. This fundamental limitation results in a key challenge: while we can predict that a failure may occur, we lack a systematic method to understand why a failure occurs. This paper proposes a model based on causal machine learning to bridge this gap. Our objective is to move beyond diagnosis to active prescription by simulating and evaluating potential fixes to optimise KPIs such as Overall Equipment Effectiveness (OEE). For this purpose, a pre-trained causal foundation model is used as a “what-if” simulator to estimate the effects of potential fixes. By estimating the causal effect of each intervention on system-level KPIs, specific actions can be recommended for the production line. This can help identify plausible root causes and quantify their operational impact. The model is evaluated using semi-synthetic manufacturing data and compared with non-causal and causal baseline machine learning models. This paper provides a technical basis for a human-centred approach, allowing engineers to test potential solutions in a causal environment to make more effective operational decisions and reduce costly downtimes.

Conventional electrical fault models, which rely on static thresholds and instantaneous trip mechanisms, fail to capture the time-evolving dynamics of real faults, creating vulnerabilities in modern power systems. This paper introduces a diode-clamp circuit architecture that reconceives short-circuits as governed, sustained processes and establishes a physics-consistent, measurement system. An Arduino-based data acquisition system recorded continuous fault evolution across multiple input voltages and durations. Multi-resolution sampling at 10ms, 50ms, and 100ms enabled high-fidelity capture of both transients and sustained-state dynamics. The clamped mechanism constrained the circuit to a bounded regime, enabling repeatable observation. Experiments yielded definitive, measurable minima and maxima for voltage, current, and resistance, empirically refuting the classical assumption of instantaneous, unbounded current. Newly introduced metrics quantify this performance: the Sustained-to-Capacitive Energy Ratio (SCER ~1.53x10^12) proves fault energy originates from sustained dynamics, not transient discharge. The Sustained Fault Efficiency (SFE>1) demonstrates that governed fault power can exceed nominal operating power. This work provides the first fully validated short-circuit quantification system, yielding empirical data for next-generation battery management, adaptive grid protection, and fault-tolerant electronics.

Arabic text-to-speech (TTS) remains challenging due to limited resources and complex phonological patterns. We present reproducible baselines for Arabic TTS built on the FastPitch architecture and introduce cepstral-domain metrics for analyzing oversmoothing in mel-spectrogram prediction. While traditional Lp reconstruction losses yield smooth but over-averaged outputs, the proposed metrics reveal their temporal and spectral effects throughout training. To address this, we incorporate a lightweight adversarial spectrogram loss, which trains stably and substantially reduces oversmoothing. We further explore multi-speaker Arabic TTS by augmenting FastPitch with synthetic voices generated using XTTSv2, resulting in improved prosodic diversity without loss of stability. The code, pretrained models, and training recipes are publicly available at: https://github.com/nipponjo/tts-arabic-pytorch.

This study presents mechatronic design, dynamic modeling, simulations and real-time control experiments of a new movable scaffolding system. The proposed system consists of a 3 degrees-of-freedom movable platform, which can be positioned on the outer surface of buildings. The platform is supported and driven by cords that are wound on pulleys and coupled to servo controlled dc-motors located at four corners of the building surface. A mathematical model considering the actuator dynamics for this cable-driven mechanism is obtained and its simulation results are presented. Design, manufacture and real-time control tests of a prototype has been done. Both numerical simulations and experiments provide good positioning performance of the proposed cable-driven mechanism.

Accurate direction-of-arrival estimation with hybrid analog–digital millimeter-wave sensor arrays is important for localization, environment sensing, and measurement beam control for sensing applications. However, the limited number of radio-frequency chains and training beams in practical hardware makes it difficult to approach the angular resolution of fully digital arrays. This paper develops a covariance-guided discrete Fourier transform (DFT) beam selection framework tailored to beamspace ESPRIT for hybrid millimeter-wave receivers. A short hybrid training phase realizes a virtual centro-symmetric subarray and yields a sample covariance that is processed by forward–backward averaging, nonnegative least-squares power and noise fitting, and a Toeplitz positive-semidefinite projection to reconstruct a denoised full-aperture covariance matrix. This covariance is then used to score and select, within each coarse sector, small contiguous blocks of DFT beams that concentrate signal energy and preserve effective aperture under a strict beam budget. The selected beams feed a sparse beamspace ESPRIT stage that operates only on actually available adjacent beam pairs, so that the overall complexity is dominated by a single low-dimensional ESPRIT call. Monte Carlo simulations for a thirty-two-element uniform linear array with three paths indicate that, in the considered scenarios, the proposed method can reduce the gap to the Cramér–Rao bound, lower the failure rate, and provide favorable accuracy–runtime trade-offs compared with a sectorization-based baseline built from the same codebook and estimator. For the unitary DFT codebook studied here, the fine-stage beam selector reduces to a covariance-guided contiguous energy-window rule; the broader score formulation also accommodates non-unitary effective beam dictionaries arising from hardware non-idealities.

Diffractive neural networks, where signal processing is embedded into wave propagation, promise light-speed and energy-efficient computation. However, existing three-dimensional structures, such as stacked intelligent metasurfaces (SIMs), face critical challenges in implementation and integration. In contrast, this work pioneers planar diffractive neural networks (PDNNs) empowered communications, a novel architecture that performs signal processing as signals propagate through artificially designed planar circuits. To demonstrate the capability of PDNN, we propose a PDNN-based space-shift-keying (PDNN-SSK) communication system with a single radio-frequency (RF) chain and a maximum power detector. In this system, PDNNs are deployed at both the transmitter and receiver to jointly execute modulation, beamforming, and detection. We conduct theoretical analyses to provide the maximization condition of correct detection probability and derive the closed-form expression of the symbol error rate (SER) for the proposed system. To approach these theoretical benchmarks, the phase shift parameters of PDNNs are optimized using a surrogate model-based training approach, which effectively navigates the high-dimensional, non-convex optimization landscape. Extensive simulations verify the theoretical analysis framework and uncover fundamental design principles for the PDNN architecture, highlighting its potential to revolutionize RF front-ends by replacing conventional digital baseband modules with this integrable RF computing platform.

This paper presents a scalable and fault-tolerant framework for unmanned aerial vehicle (UAV) mission management in complex and uncertain environments. The proposed approach addresses the computational bottleneck inherent in solving large-scale Markov Decision Processes (MDPs) by introducing a two-stage decomposition strategy. In the first stage, a factor-based algorithm partitions the global MDP into smaller, goal-specific sub-MDPs by leveraging domain-specific features such as goal priority, fault states, spatial layout, and energy constraints. In the second stage, a priority-based recombination algorithm solves each sub-MDP independently and integrates the results into a unified global policy using a meta-policy for conflict resolution. Importantly, we present a theoretical analysis showing that, under mild probabilistic independence assumptions, the combined policy is provably equivalent to the optimal global MDP policy. Our work advances artificial intelligence (AI) decision scalability by decomposing large MDPs into tractable subproblems with provable global equivalence. The proposed decomposition framework enhances the scalability of Markov Decision Processes, a cornerstone of sequential decision-making in artificial intelligence, enabling real-time policy updates for complex mission environments. Extensive simulations validate the effectiveness of our method, demonstrating orders-of-magnitude reduction in computation time without sacrificing mission reliability or policy optimality. The proposed framework establishes a practical and robust foundation for scalable decision-making in real-time UAV mission execution.

Linear Temporal Logic (LTL) provides a rigorous framework for specifying long-horizon robotic tasks, yet existing approaches face a trade-off: model-based synthesis relies on accurate labeled transition systems, whereas learning-based methods often require online interaction, task-specific rewards, or specification-conditioned training. We study LTL-specified robotic planning and execution in a stricter offline, model-free setting, where the agent is given only fixed, task-agnostic trajectory fragments, with no dynamics model, task demonstrations, or online data collection. To address this setting, we propose SAGAS, a framework that combines the compositionality of symbolic synthesis with the data-driven reachability structure learned from offline trajectories. SAGAS first learns a reusable latent reachability graph and a frozen goal-conditioned executor from fragmented offline data. For each new LTL formula, it performs task-time semantic graph augmentation to ground state-defined propositions on the learned graph, and applies Büchi product search to synthesize a cost-aware accepting prefix–suffix waypoint plan executed by the frozen executor. By shifting formula-specific reasoning from policy learning to test-time graph augmentation and symbolic search, SAGAS enables zero-shot generalization to unseen, data-supported LTL specifications without task-specific reward design, policy retraining, or online interaction. Experiments on LTL task suites constructed from OGBench locomotion domains show that this design produces executable and cost-efficient prefix–suffix behaviors for diverse unseen LTL tasks from fragmented offline data.

Recent successful lunar landing missions have generated significant interest among space agencies in establishing a permanent human settlement on the Moon. Building a lunar base requires multiple and frequent landing missions to support logistics and mobility applications. In these missions, maximizing payload mass defined as the useful cargo for human settlement is crucial. The landing mass depends on several factors, with the most critical being the maximum thrust available for braking and the engine's specific impulse (ISP). Generally, increasing engine thrust for braking reduces flight duration and, consequently, gravity losses. However, higher thrust also introduces trade-offs, such as increased engine weight and lower ISP, which can negatively impact payload capacity. Therefore, optimizing the descent trajectory requires careful consideration of these parameters to achieve a global solution that maximizes payload mass. Most existing research focuses on solving optimal control problems that minimize propellant consumption for a given thrust. These problems are typically addressed through trajectory optimization, where a minimum-fuel solution is obtained. The optimized trajectory is then executed onboard using polynomial guidance. In this paper, we propose an outer-layer optimization approach based on a Pareto-optimal solution. This method iterates on the maximum available thrust for descent trajectory optimization while incorporating a loss function that accounts for engine mass and ISP losses. By applying this approach, we identify a globally optimal solution that maximizes payload mass while ensuring an optimal landing trajectory.