Audio and Speech Processing · Cross-listed from cs.SD
AudioScene: Integrating Object-Event Audio into 3D Scenes
Shuaihang Yuan, Congcong Wen, Muhammad Shafique et al. (+2 more)
The rapid advances in audio analysis underscore its vast potential for humancomputer interaction, environmental monitoring, and public safety; yet, existing audioonly
datasets often lack spatial context. To address this gap, we present two novel audiospatial scene
datasets, AudioScanNet and AudioRoboTHOR, designed to explore audioconditioned tasks within 3D environments. By integrating audio clips with spatially aligned 3D scenes, our
datasets enable research on how audio signals interact with spatial context. To associate audio events with corresponding spatial information, we leverage the common sense
reasoning ability of large
language models and supplement them with rigorous human verification, This approach offers greater scalability compared to purely manual annotation while maintaining high standards of accuracy, completeness, and diversity, quantified through inter annotator agreement and performance on two
benchmark tasks audio based 3D visual grounding and audio based robotic zeroshot
navigation. The results highlight the limitations of current audiocentric methods and underscore the practical challenges and significance of our
datasets in advancing audio guided spatial learning.
Read the full abstract ▾
All authors Shuaihang Yuan, Congcong Wen, Muhammad Shafique, Anthony Tzes, Yi Fang
Image and Video Processing · Cross-listed from cs.CV
Adapter Shield: A Unified Framework with Built-in Authentication for Preventing Unauthorized Zero-Shot Image-to-Image Generation
Jun Jia, Hongyi Miao, Yingjie Zhou et al. (+8 more)
With the rapid progress in
diffusion models, image synthesis has advanced to the stage of zero-shot image-to-image generation, where high-fidelity replication of facial identities or artistic styles can be achieved using just one portrait or artwork, without modifying any model weights. Although these techniques significantly enhance creative possibilities, they also pose substantial risks related to intellectual property violations, including unauthorized identity cloning and stylistic imitation. To counter such threats, this work presents Adapter Shield, the first universal and authentication-integrated solution aimed at defending personal images from misuse in zero-shot generation scenarios. We first investigate how current zero-shot methods employ image encoders to extract
embeddings from input images, which are subsequently fed into the UNet of
diffusion models through cross-
attention layers. Inspired by this mechanism, we construct a reversible encryption system that maps original
embeddings into distinct encrypted representations according to different secret keys. The authorized users can restore the authentic
embeddings via a decryption module and the correct key, enabling normal usage for authorized generation tasks. For protection purposes, we design a multi-target
adversarial perturbation method that actively shifts the original
embeddings toward designated encrypted patterns. Consequently, protected images are embedded with a defensive layer that ensures unauthorized users can only produce distorted or encrypted outputs. Extensive evaluations demonstrate that our method surpasses existing state-of-the-art defenses in blocking unauthorized zero-shot image synthesis, while supporting flexible and secure access control for verified users.
Read the full abstract ▾
All authors Jun Jia, Hongyi Miao, Yingjie Zhou, Wangqiu Zhou, Jianbo Zhang, Linhan Cao, Dandan Zhu, Hua Yang, Xiongkuo Min, Wei Sun, Guangtao Zhai
Image and Video Processing
LAYER: A Quantitative Explainable AI Framework for Decoding Tissue-Layer Drivers of Myofascial Low Back Pain
Zixue Zeng, Anthony M. Perti, Tong Yu et al. (+13 more)
Myofascial pain (MP) is a leading cause of chronic low back pain, yet its tissue-level drivers remain poorly defined and lack reliable image biomarkers. Existing studies focus predominantly on muscle while neglecting fascia, fat, and other soft tissues that play integral biomechanical roles. We developed an anatomically grounded explainable artificial intelligence (AI) framework, LAYER (Layer-wise Analysis for Yielding Explainable Relevance Tissue), that analyses six tissue layers in three-dimensional (3D) ultrasound and quantifies their contribution to MP prediction. By utilizing the largest multi-model 3D ultrasound cohort consisting of over 4,000 scans, LAYER reveals that non-muscle tissues contribute substantially to pain prediction. In B-mode imaging, the deep fascial membrane (DFM) showed the highest saliency (0.420), while in combined B-mode and shear-wave images, the collective saliency of non-muscle layers (0.316) nearly matches that of muscle (0.317), challenging the conventional muscle-centric paradigm in MP research and potentially affecting the therapy methods. LAYER establishes a quantitative, interpretable framework for linking layer-specific anatomy to pain physiology, uncovering new tissue targets and providing a generalizable approach for explainable analysis of soft-tissue imaging.
Read the full abstract ▾
All authors Zixue Zeng, Anthony M. Perti, Tong Yu, Grant Kokenberger, Hao-En Lu, Jing Wang, Xin Meng, Zhiyu Sheng, Maryam Satarpour, John M. Cormack, Allison C. Bean, Ryan P. Nussbaum, Emily Landis-Walkenhorst, Kang Kim, Ajay D. Wasan, Jiantao Pu
Systems and Control
Distributionally Robust Cascading Risk in Multi-Agent Rendezvous: Extended Analysis of Parameter-Induced Ambiguity
Vivek Pandey and Nader Motee
Ensuring safety in autonomous multi-
agent systems during time-critical tasks such as rendezvous is a fundamental challenge, particularly under communication delays and uncertainty in system parameters. In this paper, we develop a theoretical framework to analyze the distributionally robust risk of cascading failures in multi-
agent rendezvous, where system parameters lie within bounded uncertainty sets around nominal values. Using a time-delayed dynamical network as a
benchmark model, we quantify how small deviations in these parameters impact collective safety. We introduce a conditional distributionally robust functional, grounded in a bivariate Gaussian model, to characterize risk propagation between
agents. This yields a closed-form risk expression that captures the complex interaction between time delays, network structure, noise statistics, and failure modes. These expressions expose key sensitivity patterns and provide actionable insight for the design of robust and resilient multi-
agent networks. Extensive simulations validate the theoretical results and demonstrate the effectiveness of our framework.
Read the full abstract ▾
Systems and Control
Adaptive Gradient Descent MPPT Algorithm With Complexity-Aware Benchmarking for Low-Power PV Systems
Kimia Ahmadi and Wouter A. Serdijn
This paper proposes a computationally efficient, real-time maximum power point tracking (MPPT)
algorithm tailored for low-power photovoltaic (PV) systems operating under fast-changing irradiance and partial shading conditions (PSC). The proposed method augments the classical perturb and observe (P&O)
algorithm with an adaptive gradient descent mechanism that dynamically scales the perturbation step size based on the instantaneous power-voltage slope, thereby minimizing tracking time and steady-state oscillations. An optional initialization routine enhances global MPP (GMPP) tracking under PSC. Extensive simulations, including irradiance recordings from freely moving rodent subjects relevant to the targeted application, and tests across varying converter
topologies and temperatures, demonstrate its robust,
topology-independent performance. The proposed
algorithm achieves 99.94 percent MPPT efficiency under standard test conditions (STC), 99.21 percent when applied to experimental data, and more than 99.6 percent for the tested temperature profiles. Under PSC, the initialization routine improves tracking efficiency by up to 7.8 percent. A normalized gate-level complexity analysis and a unified figure-of-merit (FoM) incorporating efficiency, tracking time, and computational cost demonstrate that the proposed
algorithm outperforms 35 state-of-the-art P&O-based MPPT
algorithms. These results underscore its suitability for integration in low-power power management integrated
circuits (PMICs) operating under dynamic and resource-constrained conditions.
Read the full abstract ▾
Systems and Control
Dynamic Modeling of Load Demand in Electrified Highways Based on the EV Composition
Ashutossh Gupta, Vassilis Kekatos, Dionysios Aliprantis et al. (+1 more)
Electrified roadways (ERs) equipped with the dynamic wireless power transfer (DWPT) technology can achieve longer driving range and reduce on-board battery requirements for electric vehicles (EVs). Due to the spatial arrangement of transmitter (Tx) coils embedded into the ER pavement, the power drawn by the EV's receiver (Rx) coil is oscillatory in nature. Therefore, understanding the dynamic behavior of the total DWPT load is important for power system dynamic studies. To this end, we model the load of individual EVs in the time and frequency domains for constant EV speed. We establish that a nonlinear control scheme implemented in existing DWPT-enabled EVs exhibits milder frequency harmonics compared to its linear alternative. According to this model, the harmonics of an EV load decrease in amplitude with the Rx coil length. We further propose and analyze
stochastic models for the total DWPT load served by an ER segment. Our models explain how the EV composition on the ER affects its frequency spectrum. Interestingly, we show that serving more EVs with longer Rx coils (trucks) does not necessarily entail milder harmonics. Our analytical findings are corroborated using realistic flows from a traffic simulator and offer valuable insights to grid operators and ER designers.
Read the full abstract ▾
All authors Ashutossh Gupta, Vassilis Kekatos, Dionysios Aliprantis, Steve Pekarek
Image and Video Processing · Cross-listed from cs.CV
MODEST: Multi-Optics Depth-of-Field Stereo Dataset
Nisarg K. Trivedi, Vinayaka A. Belludi and Li-Yun Wang
Training and evaluation of state-of-the-art computer
vision algorithms for reliable shallow depth of field (DoF) rendering and defocus deblurring remain constrained by a persistent lack of large-scale, full-frame, high fidelity, real-image
datasets. Optical effects of shallow DoF and defocus blur depend intimately on camera optical configuration set with focal length and aperture; requiring rigorous evaluation of the models when these parameters systematically change. Further, modern applications such as AR, VR, smartphones, industrial
robots, etc. deploy stereo or multi-camera systems. We present MODEST - the first ultra-high-resolution(5472x3648px, 20MP), multi-optics depth of field stereo DSLR
dataset that methodically varies focal length and aperture for a series of complex, real-world scenes, capturing the optical realism and complexity of professional camera systems. With 20,000 images across 50 distinct optical configurations, focal length in 28-70mm, aperture in f/22-f/2.8 for multiple stereo viewpoints for 10 scenes; this ultra-high-resolution, full-range optics coverage enables controlled analysis of
geometric and optical effects for shallow DoF rendering and defocus deblurring. Each scene is curated to have challenging visual elements: reflective surfaces, transparent glass walls, fine-grained details, point lights, and multi-scale depth illusions. In addition, we provide intrinsics and extrinsics calibration images to support ever-evolving calibration methods. We evaluate several SOTA DoF and defocus deblurring methods and demonstrate failure cases and limitations. Our comprehensive tuning analysis demonstrates how MODEST evaluates sensitivity of the SOTA DoF models for the actual focal configuration of input images. This work attempts to bridge the realism gap between synthetic, low-resolution training data and inference generalization on high-resolution real-camera optics.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.RO
NOIR 2.0: Neural Signal Operated Intelligent Robots for Everyday Activities
Tasha Kim, Yingke Wang, Hanvit Cho et al. (+1 more)
Neural Signal Operated Intelligent
Robots (NOIR) system is a versatile
brain-
robot interface that allows humans to control
robots for daily tasks using their
brain signals. This interface utilizes electroencephalography (
EEG) to translate human intentions regarding specific objects and desired actions directly into commands that
robots can execute. We present NOIR 2.0, an enhanced version of NOIR. NOIR 2.0 includes faster and more accurate
brain decoding
algorithms, which reduce task completion time by 46%. NOIR 2.0 uses few-shot
robot learning
algorithms to adapt to individual users and predict their intentions. The new learning
algorithms leverage foundation models for more sample-efficient learning and adaptation (15 demos vs. a single demo), significantly reducing overall human time by 65%.
Read the full abstract ▾
All authors Tasha Kim, Yingke Wang, Hanvit Cho, Alex Hodges
Systems and Control · Cross-listed from math.OC
A Review of Pseudospectral Optimal Control: From Theory to Flight
I. M. Ross and M. Karpenko
The home space for optimal control is a Sobolev space. The home space for pseudospectral theory is also a Sobolev space. It thus seems natural to combine pseudospectral theory with optimal control theory and construct “pseudospectral optimal control theory,” a term coined by Ross. In this paper, we review key theoretical results in pseudospectral optimal control that have proven to be critical for a successful flight. Implementation details of flight demonstrations onboard NASA spacecraft are discussed along with emerging trends and techniques in both theory and practice. The 2011 launch of pseudospectral optimal control in embedded platforms is changing the way in which we see solutions to challenging control problems in aerospace and autonomous systems.
Read the full abstract ▾
Systems and Control
Local Dissipativity Analysis of Nonlinear Systems
Amy K. Strong and Leila Bridgeman
Dissipativity is an input-output (IO) characterization of nonlinear systems that enables compositional robust control through Vidyasagar's Network Dissipativity
Theorem (VDNT). However, determining the dissipativity of a system is an involved and, often, model-specific process. We present a general method to determine the local dissipativity properties of smooth, nonlinear, control affine systems. We simultaneously search for the optimal IO characterization of a system and synthesize a continuous piecewise affine (CPA) storage function via a convex optimization problem. To do so, we reformulate the dissipation inequality as a
matrix inequality (MI) and develop novel linear
matrix inequality (LMI) bounds for a triangulation to impose the dissipativity conditions on the CPA storage function Further, we develop a method to synthesize a combined quadratic and CPA storage function to expand the systems the optimization problem is applicable to. Finally, we establish that our method will always find a feasible IO characterization and storage function given that the system is sufficiently strictly locally dissipative and demonstrate the efficacy of our method in determining the conic bounds and gain of various nonlinear systems.
Read the full abstract ▾
Signal Processing
A Fully Multivariate Multifractal Detrended Fluctuation Analysis Method for Fault Diagnosis
Khuram Naveed and Naveed ur Rehman
We propose a fully multivariate generalization of multifractal detrended fluctuation analysis (MFDFA) and leverage it to develop a fault diagnosis framework for multichannel machine vibration data. We introduce a novel covariance-weighted $L_{pq}$
matrix norm based on Mahalanobis distance to define a fully multivariate fluctuation function that uniquely captures cross-channel dependencies and variance biases in multichannel vibration data. This formulation, termed FM-MFDFA, allows for a more accurate characterization of the multiscale structure of multivariate signals. To enhance feature relevance, the proposed framework integrates multivariate variational mode decomposition (MVMD) to isolate fault-relevant components before applying FM-MFDFA. Results on wind turbine gearbox data demonstrate that the proposed method outperforms conventional MFDFA approaches by effectively distinguishing between healthy and faulty machine states, even under noisy conditions.
Read the full abstract ▾
Image and Video Processing
Adversarial Multi-Task Learning for Liver Tumor Segmentation, Dynamic Enhancement Regression, and Classification
Xiaojiao Xiao, Qinmin Vivian Hu, Tae Hyun Kim et al. (+1 more)
Liver tumor
segmentation, dynamic enhancement regression, and classification are critical for clinical assessment and diagnosis. However, no prior work has attempted to achieve these tasks simultaneously in an end-to-end framework, primarily due to the lack of an effective framework that captures inter-task relevance for mutual improvement and the absence of a mechanism to extract dynamic MRI information effectively. To address these challenges, we propose the Multi-Task Interaction
adversarial learning Network (MTI-Net), a novel integrated framework designed to tackle these tasks simultaneously. MTI-Net incorporates Multi-domain Information
Entropy Fusion (MdIEF), which utilizes
entropy-aware, high-frequency spectral information to effectively integrate features from both frequency and spectral domains, enhancing the extraction and utilization of dynamic MRI data. The network also introduces a task interaction module that establishes higher-order consistency between
segmentation and regression, thus fostering inter-task synergy and improving overall performance. Additionally, we designed a novel task-driven discriminator (TDD) to capture internal high-order relationships between tasks. For dynamic MRI information extraction, we employ a shallow
Transformer network to perform positional encoding, which captures the relationships within dynamic MRI sequences. In experiments on a
dataset of 238 subjects, MTI-Net demonstrates high performance across multiple tasks, indicating its strong potential for assisting in the clinical assessment of liver tumors. The code is available at: https://github.com/xiaojiao929/MTI-Net.
Read the full abstract ▾
All authors Xiaojiao Xiao, Qinmin Vivian Hu, Tae Hyun Kim, Guanghui Wang
Signal Processing · Cross-listed from astro-ph.IM
A Direct Calibration Algorithm for ADC Interleaving
Chi-kwan Chan, Hina Suzuki, David Forbes et al. (+4 more)
We introduce a novel direct calibration
algorithm to address phase delay, gain, and offset mismatches in Analog-to-Digital Converter (ADC) time interleaving systems. These mismatches, common in high-speed data acquisition, degrade system performance and signal integrity, particularly in applications such as
radio astronomy and very long baseline interferometry (VLBI). Our proposed
algorithm uses a sinusoidal reference signal and
Fourier analysis to isolate and correct each type of mismatch, providing a computationally efficient solution. Extensive numerical simulations validate the
algorithm's effectiveness and demonstrate its ability to significantly enhance signal reconstruction accuracy compared to existing methods. This work provides a robust and scalable solution for maintaining signal fidelity in interleaved ADC systems and has broad applications in fields that require high-speed data acquisition.
Read the full abstract ▾
All authors Chi-kwan Chan, Hina Suzuki, David Forbes, Andrew Thomas West, Arash Roshanineshat, Daniel P. Marrone, Amy Lowitz
Image and Video Processing · Cross-listed from q-bio.QM
Automated Histopathologic Assessment of Hirschsprung Disease Using a Multi-Stage Vision Transformer Framework
Youssef Megahed, Saleh Abou-Alwan, Anthony Fuller et al. (+3 more)
Hirschsprung Disease is characterized by the absence of ganglion
cells in the myenteric plexus. Therefore, the correct identification of ganglion
cells is crucial for diagnosing Hirschsprung disease. We introduce a three-stage analysis framework that mimics the pathologist's diagnostic approach. The framework, based on a
Vision Transformer model (ViT-B/16), sequentially segments the muscularis propria, segments the myenteric plexus, and detects ganglion
cells within anatomically valid regions. 30 whole-slide images of colon tissue were used, each containing manual annotations of muscularis, plexus, and ganglion
cells. A 5-fold cross-validation scheme was applied to each stage, along with resolution-specific tiling strategies and tailored postprocessing to ensure anatomical consistency. The proposed method achieved a Dice coefficient of 89.9% and a Plexus Inclusion Rate of 100% for muscularis
segmentation. Plexus
segmentation reached a recall of 94.8%, a precision of 84.2% and a Ganglia Inclusion Rate of 99.7%. For ganglion
cells annotated with high certainty, the model achieved 62.1% precision and 89.1% recall. When considering all annotated ganglion
cells, regardless of certainty level, the overall precision was 67.0%. These results indicate that ViT-based models are effective at leveraging global tissue context and capturing cellular morphology at small scales, even within complex histological tissue structures. This multi-stage methodology has great potential to support digital pathology workflows by reducing inter-observer variability and assisting in the evaluation of Hirschsprung disease. The clinical impact will be evaluated in future work with larger multi-center
datasets and additional expert annotations.
Read the full abstract ▾
All authors Youssef Megahed, Saleh Abou-Alwan, Anthony Fuller, Dina El Demellawy, Steven Hawken, Adrian D. C. Chan
Signal Processing · Cross-listed from cs.AI
Learning Multi-Access Point Coordination in Agentic AI Wi-Fi with Large Language Models
Yifan Fan, Le Liang, Peng Liu et al. (+5 more)
Multi-access point coordination (MAPC) is a key technology for enhancing throughput in next-generation Wi-Fi within dense overlapping basic service sets. However, existing MAPC protocols rely on static, protocol-defined rules, which limits their ability to adapt to dynamic network conditions such as varying interference levels and
topologies. To address this limitation, we propose a novel Agentic AI Wi-Fi framework where each access point, modeled as an autonomous large
language model
agent, collaboratively reasons about the network state and negotiates adaptive coordination strategies in real time. This dynamic collaboration is achieved through a cognitive workflow that enables the
agents to engage in natural
language dialogue, leveraging integrated
memory, reflection, and tool use to ground their decisions in past experience and environmental feedback. Comprehensive simulation results demonstrate that our agentic framework successfully learns to adapt to diverse and dynamic network environments, significantly outperforming the state-of-the-art spatial reuse baseline and validating its potential as a robust and intelligent solution for future wireless networks.
Read the full abstract ▾
All authors Yifan Fan, Le Liang, Peng Liu, Xiao Li, Ziyang Guo, Qiao Lan, Shi Jin, Wen Tong
Image and Video Processing · Cross-listed from cs.CV
Video Object Recognition in Mobile Edge Networks: Local Tracking or Edge Detection?
Kun Guo, Yun Shen, Xijun Wang et al. (+3 more)
Fast and accurate
video object recognition, which relies on frame-by-frame
video analytics, remains a challenge for resource-constrained devices such as traffic cameras. Recent advances in mobile edge computing have made it possible to offload computation-intensive object detection to edge servers equipped with high-accuracy neural networks, while lightweight and fast object tracking
algorithms run locally on devices. This hybrid approach offers a promising solution but introduces a new challenge: deciding when to perform edge detection versus local tracking. To address this, we formulate two long-term optimization problems for both single-device and multi-device scenarios, taking into account the temporal correlation of consecutive frames and the dynamic conditions of mobile edge networks. Based on the formulation, we propose the LTED-Ada in single-device setting, a deep reinforcement learning-based
algorithm that adaptively selects between local tracking and edge detection, according to the frame rate as well as recognition accuracy and delay requirement. In multi-device setting, we further enhance LTED-Ada using
federated learning to enable collaborative policy training across devices, thereby improving its generalization to unseen frame rates and performance requirements. Finally, we conduct extensive hardware-in-the-loop experiments using multiple Raspberry Pi 4B devices and a personal computer as the edge server, demonstrating the superiority of LTED-Ada.
Read the full abstract ▾
All authors Kun Guo, Yun Shen, Xijun Wang, Chaoqun You, Yun Rui, Tony Q. S. Quek
Systems and Control · Cross-listed from cs.LG
Sparse-to-Field Reconstruction via Stochastic Neural Dynamic Mode Decomposition
Yujin Kim and Sarah Dean
Many consequential real-world systems, like wind fields and ocean currents, are dynamic and hard to model. Learning their governing dynamics remains a central challenge in scientific machine learning. Dynamic Mode Decomposition (DMD) provides a simple, data-driven approximation, but practical use is limited by sparse/noisy observations from continuous fields, reliance on linear approximations, and the lack of principled uncertainty quantification. To address these issues, we introduce
Stochastic NODE-DMD, a probabilistic extension of DMD that models continuous-time, nonlinear dynamics while remaining interpretable. Our approach enables continuous spatiotemporal reconstruction at arbitrary coordinates and quantifies predictive uncertainty. Across four
benchmarks, a synthetic setting and three physics-based flows, it surpasses a baseline in reconstruction accuracy when trained from only 10% observation density. It further recovers the dynamical structure by aligning learned modes and continuous-time
eigenvalues with ground truth. Finally, on
datasets with multiple realizations, our method learns a calibrated distribution over latent dynamics that preserves ensemble variability rather than averaging across regimes. Our code is available at: https://github.com/sedan-group/
Stochastic-NODE-DMD
Read the full abstract ▾
Systems and Control
Exploring Urban Air Mobility Adoption Potential in San Francisco Bay Area Region: A Systems of Systems Level Case Study on Passenger Waiting Times and Travel Efficiency
Winfrey Paul Sagayam Dennis
Urban Air mobility has gained momentum with recent advancements in the electric vertical take-off and landing (eVTOL) vehicles, offering faster point-to-point air taxi services that could help relieve traffic congestion in chronically overburdened cities. The research assesses the feasibility and systems-of-systems level adoption potential of UAM operations in the San Francisco Bay Area by comparing passenger departure, waiting, travel, and arrival times across key regional nodes, including San Francisco, Oakland, San Jose, and Palo Alto airports, with conventional ground transportation. A multi-
agent simulation was developed in MATLAB to evaluate the fleet operations and to model demand arrival using a Poisson process under
stochastic passenger flows and turnaround constraints. Results indicate that utilizing UAM during peak demand could reduce total travel times up to eighty percent across the region. The findings of this paper highlight the critical operational factors for fleet schedule optimization. Especially how the fleet size, passengers' request volumes, and turnaround time directly influence waiting time, operating cost, and overall user acceptance.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.RO
Safe and Stable Neural Network Dynamical Systems for Robot Motion Planning
Allen Emmanuel Binny, Mahathi Anand, Hugo T. M. Kussaba et al. (+4 more)
Learning safe and stable
robot motions from demonstrations remains a challenge, especially in complex, nonlinear tasks involving dynamic, obstacle-rich environments. In this paper, we propose Safe and Stable Neural Network Dynamical Systems S$^2$-NNDS, a learning-from-demonstration framework that simultaneously learns expressive neural dynamical systems alongside neural Lyapunov stability and barrier safety certificates. Unlike traditional approaches with restrictive
polynomial parameterizations, S$^2$-NNDS leverages neural networks to capture complex
robot motions, providing probabilistic guarantees through split conformal prediction in learned certificates. Experimental results in various 2D and 3D
datasets – including LASA handwriting and demonstrations recorded kinesthetically from the Franka Emika Panda
robot – validate the effectiveness of S$^2$-NNDS in learning robust, safe, and stable motions from potentially unsafe demonstrations. The source code, supplementary material and experiment
videos can be accessed via https://github.com/allemmbinn/S2NNDS
Read the full abstract ▾
All authors Allen Emmanuel Binny, Mahathi Anand, Hugo T. M. Kussaba, Lingyun Chen, Shreenabh Agrawal, Fares J. Abu-Dakka, Abdalla Swikir
Signal Processing
Near-Field Multipath MIMO Channels: Modeling Reflectors and Exploiting NLOS Paths
Mohamadreza Delbari, George C. Alexandropoulos, Robert Schober et al. (+2 more)
Near-field (NF) communications is receiving renewed interest in the context of multiple-input multiple-output (
MIMO) systems involving large physical apertures with respect to the signal wavelength. While line-of-sight (LOS) links are typically expected to dominate in NF scenarios, the impact of non-LOS (NLOS) components at both in centimeter- and millimeter-wave frequencies may be in general non-negligible. Moreover, although weaker than the LOS path, NLOS links may be essential for achieving multiplexing gains in
MIMO systems. The commonly used NF channel models for NLOS links in the literature are based on the point scattering assumption, which is not valid for large reflectors such as walls, ceilings, and the ground. In this paper, we develop a generalized statistical NF
MIMO channel model that extends the widely adopted point scattering framework to account for imperfect reflections from large surfaces. This model is then leveraged to investigate how the physical characteristics of these reflectors influence the resulting NF
MIMO channel. In addition, using the proposed channel model, we analytically demonstrate for a multi-user scenario that, even when users are located within the NF regime, relying solely on LOS NF links may be insufficient to achieve multiplexing gains, thus exploiting NLOS links becomes essential. Our simulation results validate the accuracy of the proposed model and show that, in many practical settings, the contribution of NLOS components is non-negligible and must be carefully accounted for in the system design.
Read the full abstract ▾
All authors Mohamadreza Delbari, George C. Alexandropoulos, Robert Schober, H. Vincent Poor, Vahid Jamali
Systems and Control
From Features to States: Data-Driven Selection of Measured State Variables via RFE-DMDc
Haoyu Wang, Andrea Alfonsi, Roberto Ponciroli et al. (+1 more)
The behavior of a dynamical system under a given set of inputs can be captured by tracking the response of an optimal subset of process variables (state variables). For many engineering systems, however, first-principles, model-based identification is impractical, motivating data-driven approaches for Digital Twins used in control and diagnostics. In this paper, we present RFE-DMDc, a supervised, data-driven workflow that uses Recursive Feature Elimination (RFE) to select a minimal, physically meaningful set of variables to monitor and then derives a linear state-space model via Dynamic Mode Decomposition with Control (DMDc). The workflow includes a cross-subsystem selection step that mitigates feature overshadowing in multi-component systems. To corroborate the results, we implement a GA-DMDc baseline that jointly optimizes the state set and model fit under a common accuracy cost on states and outputs. Across a truth-known RLC
benchmark and a realistic Integrated Energy System (IES) with multiple thermally coupled components and thousands of candidate variables, RFE-DMDc consistently recovers compact state sets (\(\approx 10\) variables) that achieve test errors comparable to GA-DMDc while requiring an order of magnitude less computational time. The selected variables retain clear physical interpretation across subsystems, and the resulting models demonstrate competitive predictive accuracy, computational efficiency, and robustness to overfitting.
Read the full abstract ▾
All authors Haoyu Wang, Andrea Alfonsi, Roberto Ponciroli, Richard Vilim
Signal Processing
Time-Domain Linear Model-based Framework for Passive Acoustic Mapping of Cavitation Activity
Tatiana Gelvez-Barrera, Barbara Nicolas, Denis Kouamé et al. (+2 more)
Passive acoustic mapping enables the spatial mapping and temporal monitoring of cavitation activity, playing a crucial role in therapeutic ultrasound applications. Most conventional beamforming methods, whether implemented in the time or frequency domains, suffer from limited axial resolution due to the absence of a reference emission onset time. While frequency-domain methods, the most efficient of which are based on the cross-spectral
matrix, require long signals for accurate estimation, time-domain methods typically achieve lower spatial resolution. To address these limitations, we propose a linear model-based beamforming framework fully formulated in the time domain. The linear forward model relates a discretized spatiotemporal distribution of cavitation activity to the temporal signals recorded by a probe, explicitly accounting for time-of-flight delays dictated by the acquisition geometry. This model is then inverted using regularization techniques that exploit prior knowledge of cavitation activity in both spatial and temporal domains. Experimental results show that the proposed framework achieves enhanced or competitive cavitation map quality while using only 20% of the data typically required by frequency-domain methods. This highlights the substantial gain in data efficiency and the flexibility of our spatiotemporal regularization to adapt to diverse passive cavitation scenarios, outperforming state-of-the-art techniques.
Read the full abstract ▾
All authors Tatiana Gelvez-Barrera, Barbara Nicolas, Denis Kouamé, Bruno Gilles, Adrian Basarab
Systems and Control
Causal Feature Selection for Weather-Driven Residential Load Forecasting
Elise Zhang, François Mirallès, Stéphane Dellacherie et al. (+2 more)
Weather is a dominant external driver of residential electricity demand, but adding many meteorological
covariates can inflate model complexity and may even impair accuracy. Selecting appropriate exogenous features is non-trivial and calls for a principled selection framework, given the direct operational implications for day-to-day planning and reliability. This work investigates whether causal feature selection can retain the most informative weather drivers while improving parsimony and robustness for short-term load
forecasting. We present a case study on Southern Ontario with two open-source
datasets: (i) IESO hourly electricity consumption by Forward Sortation Areas; (ii) ERA5 weather reanalysis data. We compare different feature selection regimes (no feature selection, non-causal selection, PCMCI-causal selection) on city-level
forecasting with three different time series
forecasting models: GRU, TCN, PatchTST. In the feature analysis, non-causal selection prioritizes radiation and moisture variables that show correlational dependence, whereas PCMCI-causal selection emphasizes more direct thermal drivers and prunes the indirect
covariates. We detail the evaluation pipeline and report diagnostics on prediction accuracy and extreme-weather robustness, positioning causal feature selection as a practical complement to modern forecasters when integrating weather into residential load
forecasting.
Read the full abstract ▾
All authors Elise Zhang, François Mirallès, Stéphane Dellacherie, Di Wu, Benoit Boulet
Systems and Control · Cross-listed from cs.RO
Power-Efficient Autonomous Mobile Robots
Liangkai Liu, Weisong Shi and Kang G. Shin
This paper presents pNav, a novel power-management system that significantly enhances the power/energy-efficiency of Autonomous Mobile
Robots (AMRs) by jointly optimizing their physical/mechanical and cyber subsystems. By profiling AMRs' power consumption, we identify three challenges in achieving CPS (cyber-physical system) power-efficiency that involve both cyber (C) and physical (P) subsystems: (1) variabilities of system power consumption breakdown, (2) environment-aware
navigation locality, and (3) coordination of C and P subsystems. pNav takes a multi-faceted approach to achieve power-efficiency of AMRs. First, it integrates millisecond-level power consumption prediction for both C and P subsystems. Second, it includes novel real-time modeling and monitoring of spatial and temporal
navigation localities for AMRs. Third, it supports dynamic coordination of AMR software (
navigation, detection) and hardware (motors, DVFS driver) configurations. pNav is prototyped using the
Robot Operating System (ROS)
Navigation Stack, 2D
LiDAR, and camera. Our in-depth evaluation with a real
robot and Gazebo environments demonstrates a >96% accuracy in predicting power consumption and a 38.1% reduction in power consumption without compromising
navigation accuracy and safety.
Read the full abstract ▾