Signal Processing · Cross-listed from cs.IT
DeepOFW: Deep Learning-Driven OFDM-Flexible Waveform Modulation for Peak-to-Average Power Ratio Reduction
Ran Greidi and Kobi Cohen
Peak-to-average power ratio (PAPR) remains a major limitation of multicarrier modulation schemes such as orthogonal frequency-division multiplexing (OFDM), reducing power amplifier efficiency and limiting practical transmit power. In this work, we propose DeepOFW, a deep learning-driven OFDM-flexible waveform modulation framework that enables data-driven waveform design while preserving the low-complexity hardware structure of conventional transceivers. The proposed architecture is fully differentiable, allowing end-to-end optimization of waveform generation and receiver processing under practical physical constraints. Unlike neural transceiver approaches that require deep learning inference at both ends of the link, DeepOFW confines the learning stage to an offline or centralized unit, enabling deployment on standard transmitter and receiver hardware without additional computational overhead. The framework jointly optimizes waveform representations and detection parameters while explicitly incorporating PAPR constraints during training. Extensive simulations over 3GPP multipath channels demonstrate that the learned waveforms significantly reduce PAPR compared with classical OFDM while simultaneously improving bit error rate (BER) performance relative to state-of-the-art transmission schemes. These results highlight the potential of data-driven waveform design to enhance multicarrier communication systems while maintaining hardware-efficient implementations. An open-source implementation of the proposed framework is released to facilitate reproducible research and practical adoption.
Read the full abstract ▾
Image and Video Processing
A Novel Framework using Intuitionistic Fuzzy Logic with U-Net and U-Net++ Architecture: A case Study of MRI Bain Image Segmentation
Hanuman Verma, Kiho Im, Akshansh Gupta et al. (+1 more)
Accurate
segmentation of
brain images from
magnetic resonance imaging (MRI) scans plays a pivotal role in
brain image analysis and the diagnosis of neurological disorders. Deep learning
algorithms, particularly U-Net and U-Net++, are widely used for image
segmentation. However, it finds difficult to deal with uncertainty in images. To address this challenge, this work integrates intuitionistic fuzzy logic into U-Net and U-Net++, propose a novel framework, named as IFS U-Net and IFS U-Net++. These models accept input data in an intuitionistic fuzzy representation to manage uncertainty arising from vague ness and imprecise data. This approach effectively handles tissue ambiguity caused by the partial volume effect and boundary uncertainties. To evaluate the effectiveness of IFS U-Net and IFS U-Net++, experiments are conducted on two publicly available MRI
brain datasets: the Internet
Brain Segmentation Repository (IBSR) and the Open Access Series of Imaging Studies (OASIS).
Segmentation performance is quantitatively assessed using Accuracy, Dice Coefficient, and Intersection over Union (IoU). The results demonstrate that the proposed architectures consistently improve
segmentation performance by effectively addressing uncertainty
Read the full abstract ▾
All authors Hanuman Verma, Kiho Im, Akshansh Gupta, M. Tanveer
Audio and Speech Processing
The Voice Behind the Words: Quantifying Intersectional Bias in SpeechLLMs
Shree Harsha Bokkahalli Satish, Christoph Minixhofer, Maria Teleki et al. (+5 more)
Speech Large
Language Models (SpeechLLMs) process spoken input directly, retaining cues such as accent and perceived gender that were previously removed in cascaded pipelines. This introduces speaker identity dependent variation in responses. We present a large-scale intersectional evaluation of accent and gender bias in three SpeechLLMs using 2,880 controlled interactions across six English accents and two gender presentations, keeping linguistic content constant through voice cloning. Using pointwise LLM-judge ratings, pairwise comparisons, and Best-Worst Scaling with human validation, we detect recurring directional disparities. Eastern European-accented
speech receives lower helpfulness scores, particularly for female-presenting voices. Responses remain polite but differ in helpfulness. While LLM judges capture the directional trend of these biases, human evaluators exhibit significantly higher sensitivity, showing stronger accent-level contrasts.
Read the full abstract ▾
All authors Shree Harsha Bokkahalli Satish, Christoph Minixhofer, Maria Teleki, James Caverlee, Ondřej Klejch, Peter Bell, Gustav Eje Henter, Éva Székely
Image and Video Processing
On the Degrees of Freedom of Gridded Control Points in Learning-Based Medical Image Registration
Wen Yan, Qianye Yang, Yipei Wang et al. (+5 more)
Many registration problems are ill-posed in homogeneous or noisy regions, and dense voxel-wise decoders can be unnecessarily high-dimensional. A sparse control-point parameterisation provides a compact, smooth deformation representation while reducing
memory and improving stability. This work investigates the required control points for learning-based registration network development. We present GridReg, a learning-based registration framework that replaces dense voxel-wise decoding with displacement predictions at a sparse grid of control points. This design substantially cuts the parameter count and
memory while retaining registration accuracy. Multiscale 3D encoder feature maps are flattened into a 1D
token sequence with positional encoding to retain spatial context. The model then predicts a sparse gridded deformation field using a cross-
attention module. We further introduce grid-adaptive training, enabling an adaptive model to operate at multiple grid sizes at inference without retraining. This work quantitatively demonstrates the benefits of using sparse grids. Using three data sets for registering prostate gland, pelvic organs and neurological structures, the results suggested a significant improvement with the usage of grid-controled displacement field. Alternatively, the superior registration performance was obtained using the proposed approach, with a similar or less computational cost, compared with existing
algorithms that predict DDFs or displacements sampled on scattered key points.
Read the full abstract ▾
All authors Wen Yan, Qianye Yang, Yipei Wang, Shonit Punwani, Mark Emberton, Vasilis Stavrinides, Yipeng Hu, Dean Barratt
Signal Processing
Two-Stage Heterogeneous Graph Neural Network for RIS-Aided Physical-Layer Security
Zihan Song, Yang Lu, Wei Chen et al. (+3 more)
This paper investigates physical-layer security (PLS) enabled by graph neural networks (GNNs). We propose a two-stage heterogeneous GNN (HGNN) to maximize the secrecy energy efficiency (SEE) of a reconfigurable intelligent surface (RIS)-assisted multi-input-single-output (MISO) system that serves multiple legitimate users (LUs) and eavesdroppers (Eves). The first stage formulates the system as a bipartite graph involving three types of nodes-RIS reflecting elements, LUs, and Eves-with the goal of generating the RIS phase shift
matrix. The second stage models the system as a fully connected graph with two types of nodes (LUs and Eves), aiming to produce beamforming and artificial noise (AN) vectors. Both stages adopt an HGNN integrated with a multi-head
attention mechanism, and the second stage incorporates two output methods: beam-direct and model-based approaches. The two-stage HGNN is trained in an unsupervised manner and designed to scale with the number of RIS reflecting elements, LUs, and Eves. Numerical results demonstrate that the proposed two-stage HGNN outperforms state-of-the-art GNNs in RIS-aided PLS scenarios. Compared with convex optimization
algorithms, it reduces the average running time by three orders of magnitude with a performance loss of less than $4\%$. Additionally, the scalability of the two-stage HGNN is validated through extensive simulations.
Read the full abstract ▾
All authors Zihan Song, Yang Lu, Wei Chen, Bo Ai, Zhiguo Ding, Arumugam Nallanathan
Image and Video Processing
LUMINA: A Multi-Vendor Mammography Benchmark with Energy Harmonization Protocol
Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas et al. (+9 more)
Publicly available full-field digital mammography (FFDM)
datasets remain limited in size, clinical annotations, and vendor diversity, hindering the development of robust models. We introduce LUMINA, a curated, multi-vendor FFDM
dataset that explicitly encodes acquisition energy and vendor metadata to capture clinically relevant appearance variations often overlooked in existing
benchmarks. This
dataset contains 1824 images from 468 patients (960 benign, 864 malignant), with pathology-confirmed labels, BI-RADS assessments, and breast-density annotations. LUMINA spans six acquisition systems and includes both high- and low-energy imaging styles, enabling systematic analysis of vendor- and energy-induced domain shifts. To address these variations, we propose a foreground-only pixel-space
alignment method (”energy harmonization”) that maps images to a low-energy reference while preserving lesion morphology. We
benchmark CNN and
transformer models on three clinically relevant tasks: diagnosis (benign vs. malignant), BI-RADS classification, and density estimation. Two-view models consistently outperform single-view models. EfficientNet-B0 achieves an AUC of 93.54% for diagnosis, while Swin-T achieves the best macro-AUC of 89.43% for density prediction. Harmonization improves performance across architectures and produces more localized Grad-CAM responses. Overall, LUMINA provides (1) a vendor-diverse
benchmark and (2) a model-agnostic harmonization framework for reliable and deployable mammography AI.
Read the full abstract ▾
All authors Hongyi Pan, Gorkem Durak, Halil Ertugrul Aktas, Andrea M. Bejar, Baver Tutun, Emre Uysal, Ezgi Bulbul, Mehmet Fatih Dogan, Berrin Erok, Berna Akkus Yildirim, Sukru Mehmet Erturk, Ulas Bagci
Audio and Speech Processing · Cross-listed from cs.SD
Nudging Hidden States: Training-Free Model Steering for Chain-of-Thought Reasoning in Large Audio-Language Models
Lok-Lam Ieong, Chia-Chien Chen, Chih-Kai Yang et al. (+3 more)
Chain-of-thought (CoT) prompting has been extended to large audio-
language models (LALMs) to elicit
reasoning, yet enhancing its effectiveness without training remains challenging. We study inference-time model steering as a training-free approach to improve LALM
reasoning. We introduce three strategies using diverse information sources and evaluate them across four LALMs and four
benchmarks. Results show general accuracy gains up to 4.4% over CoT prompting. Notably, we identify a cross-modal transfer where steering vectors derived from few text samples effectively guide
speech-based
reasoning, demonstrating high data efficiency. We also examine hyperparameter sensitivity to understand the robustness of these approaches. Our findings position model steering as a practical direction for strengthening LALM
reasoning.
Read the full abstract ▾
All authors Lok-Lam Ieong, Chia-Chien Chen, Chih-Kai Yang, Yu-Han Huang, An-Yu Cheng, Hung-yi Lee
Systems and Control · Cross-listed from cs.MA
EcoFair-CH-MARL: Scalable Constrained Hierarchical Multi-Agent RL with Real-Time Emission Budgets and Fairness Guarantees
Saad Alqithami
Global decarbonisation targets and tightening
market pressures demand maritime logistics solutions that are simultaneously efficient, sustainable, and equitable. We introduce EcoFair-CH-MARL, a constrained hierarchical multi-
agent reinforcement learning framework that unifies three innovations: (i) a primal-dual budget layer that provably bounds cumulative emissions under
stochastic weather and demand; (ii) a
fairness-aware reward
transformer with dynamically scheduled penalties that enforces max-min cost equity across heterogeneous fleets; and (iii) a two-tier policy architecture that decouples strategic routing from real-time vessel control, enabling linear scaling in
agent count. New theoretical results establish O(\sqrt{T}) regret for both constraint violations and
fairness loss. Experiments on a high-fidelity maritime digital twin (16 ports, 50 vessels) driven by automatic identification system traces, plus an energy-grid case study, show up to 15% lower emissions, 12% higher through-put, and a 45% fair-cost improvement over state-of-the-art hierarchical and constrained MARL baselines. In addition, EcoFair-CH-MARL achieves stronger equity (lower Gini and higher min-max welfare) than
fairness-specific MARL baselines (e.g., SOTO, FEN), and its modular design is compatible with both policy- and value-based learners. EcoFair-CH-MARL therefore advances the feasibility of large-scale, regulation-compliant, and socially responsible multi-
agent coordination in safety-critical domains.
Read the full abstract ▾
Systems and Control
Progress-Based Fault Detection and Health-Aware Task Allocation for Heterogeneous Multi-Robot Systems
Jack Cline, Christian Macaranas and Siavash Farzan
We present a progress-based fault detection module and its integration with dynamic task allocation for heterogeneous
robot teams. The detector monitors a normalized task-completion signal with a lightweight Kalman filter (KF) and a normalized innovation squared (NIS) test, augmented with a low-rate stall gate, an uncertainty gate, and debounce logic. Health estimates influence the allocator via health-weighted costs and health-dependent masks; reallocation is event-triggered and regularized with an $\ell_1$ assignment-change penalty to limit reassignment churn while preserving feasibility through slack variables. The detector has constant per-
robot update cost, and the allocation remains a convex quadratic program (QP). Experiments on a common team-task setup evaluate measurement-noise increases, velocity-slip biases, communication dropouts, and task abandonment. The results show timely detection in the noise and bias cases, maintained task completion with limited reassignment, and the expected observability delays under communication dropouts.
Read the full abstract ▾
Image and Video Processing
A Heterogeneous Ensemble for Multi-Center COVID-19 Classification from Chest CT Scans
Aadit Nilay, Bhavesh Thapar, Anant Agrawal et al. (+1 more)
The COVID-19 pandemic exposed critical limitations in diagnostic workflows: RT-PCR tests suffer from slow turnaround times and high false-negative rates, while CT-based screening offers faster complementary diagnosis but requires expert radiological interpretation. Deploying automated CT analysis across multiple hospital centres introduces further challenges, as differences in scanner hardware, acquisition protocols, and patient populations cause substantial domain shift that degrades single-model performance. To address these challenges, we present a heterogeneous ensemble of nine models spanning three inference paradigms: (1) a self-supervised DINOv2
Vision Transformer with slice-level sigmoid aggregation, (2) a RadImageNet-pretrained DenseNet-121 with slice-level sigmoid averaging, and (3) seven Gated
Attention Multiple Instance Learning models using EfficientNet-B3, ConvNeXt-Tiny, and EfficientNetV2-S backbones with scan-level softmax classification. Ensemble diversity is further enhanced through random-seed variation and
Stochastic Weight Averaging. We address severe overfitting, reducing the validation-to-training loss ratio from 35x to less than 3x, through a combination of Focal Loss,
embedding-level Mixup, and domain-aware augmentation. Model outputs are fused via score-weighted probability averaging and calibrated with per-source threshold optimization. The final ensemble achieves an average macro F1 of 0.9280 across four hospital centres, outperforming the best single model (F1=0.8969) by +0.031, demonstrating that heterogeneous architectures combined with source-aware calibration are essential for robust multi-site medical image classification.
Read the full abstract ▾
All authors Aadit Nilay, Bhavesh Thapar, Anant Agrawal, Mohammad Nayeem Teli
Systems and Control · Cross-listed from cs.ET
Functional Safety Analysis for Infrastructure-Enabled Depot Autonomy System
Gaurav Pandey, Gregory Stevens and Henry Liu
This paper presents the functional safety analysis for an Infrastructure-Enabled Depot Autonomy (IX-DA) system. The IX-DA system automates the marshalling of delivery vehicles within a controlled depot environment, navigating connected autonomous vehicles (CAVs) between drop-off zones, service stations (washing, calibration, charging, loading), and pick-up zones without human intervention. We describe the system architecture comprising three principal subsystems – the connected autonomous vehicle, the infrastructure sensing and compute layer, and the human operator interface – and derive their functional requirements. Using ISO 26262-compliant Hazard Analysis and Risk Assessment (HARA) methodology, we identify eight hazardous events, evaluate them across different operating scenarios, and assign Automotive Safety Integrity Levels~(ASILs) ranging from Quality Management (QM) to ASIL C. Six safety goals are derived and allocated to vehicle and infrastructure subsystems. The analysis demonstrates that high-speed uncontrolled operation imposes the most demanding safety requirements (ASIL C), while controlled low-speed operation reduces most goals to QM, offering a practical pathway for phased deployment.
Read the full abstract ▾
Image and Video Processing · Cross-listed from cs.CV
Make it SING: Analyzing Semantic Invariants in Classifiers
Harel Yadid, Meir Yossef Levi, Roy Betser et al. (+1 more)
All classifiers, including state-of-the-art
vision models, possess invariants, partially rooted in the geometry of their linear mappings. These invariants, which reside in the null-space of the classifier, induce equivalent sets of inputs that map to identical outputs. The semantic content of these invariants remains vague, as existing approaches struggle to provide human-interpretable information. To address this gap, we present Semantic Interpretation of the Null-space Geometry (SING), a method that constructs equivalent images, with respect to the network, and assigns semantic interpretations to the available variations. We use a mapping from network features to multi-modal
vision language models. This allows us to obtain natural
language descriptions and visual examples of the induced semantic shifts. SING can be applied to a single image, uncovering local invariants, or to sets of images, allowing a breadth of statistical analysis at the class and model levels. For example, our method reveals that ResNet50 leaks relevant semantic attributes to the null space, whereas DinoViT, a ViT pretrained with self-supervised DINO, is superior in maintaining class semantics across the invariant space.
Read the full abstract ▾
All authors Harel Yadid, Meir Yossef Levi, Roy Betser, Guy Gilboa
Systems and Control
Collective Grid: Privacy-Preserved Multi-Operator Energy Sharing Optimization via Federated Energy Prediction
Meysam Masoudi, Tahar Zanouda, Milad Ganjalizadeh et al. (+1 more)
Electricity consumption in mobile networks is increasing with the continued 5G expansion, rising data traffic, and more complex infrastructures. However, energy management is often handled independently by each mobile network operator (MNO), leading to limited coordination and missed opportunities for collective efficiency gains. To address this gap, we propose a
privacy-preserving framework for automated energy infrastructure sharing among co-located MNOs. Our framework consists of three modules: (i) a
federated learning-based
privacy-preserving site energy consumption
forecasting module, (ii) an orchestration module in which a mixed-integer linear program is solved to schedule energy purchases from the grid, utilization of renewable sources, and shared battery charging or discharging, based on real-time prices, forecasts, and battery state, and (iii) an energy source selection module which handles the selection of cost-effective power sources and storage actions based on predicted demand across MNOs for the next control window. Using data from operational networks, our experiments confirm that the proposed solution substantially reduces operational costs and outperforms non-sharing baselines, with gains that increase as network density rises in 5G-and-beyond deployments.
Read the full abstract ▾
All authors Meysam Masoudi, Tahar Zanouda, Milad Ganjalizadeh, Cicek Cavdar
Signal Processing
A Decoupling-based Approach for Signature Estimation of Wideband XL MIMO-FMCW Radars
Chandrashekhar Rai, Dibbendu Roy and Debarati Sen
Modern radars employing wideband signals and extremely large (XL) multiple-input multiple-output (
MIMO) arrays can significantly improve range and angular resolution. However, when large bandwidth and array aperture are used simultaneously, the spatial delay across the array becomes comparable to the radar range resolution, leading to the spatial wideband effect (SWE). The SWE introduces several distortions including range migration (range squint), beam squint, and range-angle coupling (RAC), which spread the target response in the range-angle domain and may cause physically separated targets to overlap and mask each other. In this work, we propose a decoupling-based target detection and parameter estimation framework for
MIMO frequency modulated continuous wave (FMCW) radar. The proposed method reformulates the joint range-angle estimation problem as a decoupled sequential frequency estimation problem, where the two-dimensional (2D) estimation is carried out through successive one-dimensional (1D) super-resolution estimations. Specifically, we employ orthogonal matching pursuit (OMP) to perform sparse recovery-based range and angle estimation with high resolution. The proposed decoupling strategy is further extended to spatial wideband XL-
MIMO FMCW radar systems, enabling reliable detection and separation of targets even when their responses overlap due to severe RAC. Simulation results demonstrate that the proposed approach accurately detects multiple targets and successfully resolves overlapping target responses in the presence of SWE, outperforming conventional
Fourier transform and clustering-based methods.
Read the full abstract ▾
Systems and Control
Consensus in Plug-and-Play Heterogeneous Dynamical Networks: A Passivity Compensation Approach
Yongkang Su, Sei Zhen Khong and Lanlan Su
This paper investigates output consensus in heterogeneous dynamical networks within a plug-and-play framework. The networks are interconnected through nonlinear diffusive couplings and operate in the presence of measurement and communication noise. Focusing on systems that are input feedforward passive (IFP), we propose a passivity-compensation approach that exploits the surplus passivity of coupling links to locally offset shortages of passivity at the nodes. This mechanism enables subnetworks to be interconnected without requiring global reanalysis, thereby preserving modularity. Specifically, we derive locally verifiable interface conditions, expressed in terms of passivity indices and coupling gains, to guarantee that consensus properties of individual subnetworks are preserved when forming larger networks.
Read the full abstract ▾
Systems and Control · Cross-listed from cs.LG
High-Probability Bounds for SGD under the Polyak-Lojasiewicz Condition with Markovian Noise
Avik Kar, Siddharth Chandak, Rahul Singh et al. (+3 more)
We present the first uniform-in-time high-probability bound for SGD under the PL condition, where the gradient noise contains both Markovian and martingale difference components. This significantly broadens the scope of finite-time guarantees, as the PL condition arises in many machine learning and deep learning models while Markovian noise naturally arises in decentralized optimization and online system identification problems. We further allow the magnitude of noise to grow with the function value, enabling the analysis of many practical sampling strategies. In addition to the high-probability guarantee, we establish a matching $1/k$ decay rate for the expected suboptimality. Our proof technique relies on the Poisson equation to handle the Markovian noise and a probabilistic induction argument to address the lack of almost-sure bounds on the objective. Finally, we demonstrate the applicability of our framework by analyzing three practical optimization problems:
token-based decentralized linear regression, supervised learning with subsampling for
privacy amplification, and online system identification.
Read the full abstract ▾
All authors Avik Kar, Siddharth Chandak, Rahul Singh, Eric Moulines, Shalabh Bhatnagar, Nicholas Bambos
Systems and Control
Bayesian and Classical Feature Ranking for Interpretable BLDC Fault Diagnosis
Waldemar Bauer and Jerzy Baranowski
This paper compares
Bayesian and classical feature ranking methods for interpretable fault diagnosis of brushless DC (BLDC) motors. Two
Bayesian approaches, spike-and-slab and ARD logistic ranking, are evaluated against three classical baselines on a public BLDC
benchmark in binary and multiclass settings using current-based, rotational-speed-based, and combined feature sets. The strongest overall results are obtained for the combined representation. In binary classification, ReliefF achieves the highest balanced accuracy of 0.923, while ARD logistic and spike-and-slab remain very close at 0.919 and 0.920 with much smaller subsets ($k=5$). In multiclass classification, ARD logistic performs best for the combined variant with balanced accuracy 0.914, followed closely by LASSO (0.913) and spike-and-slab (0.912). The results show that
Bayesian ranking is particularly competitive for current-only and combined descriptors, while ReliefF remains especially effective for speed-based ranking. Because the
benchmark consists of short segmented observations from a limited number of experimental conditions, the findings are interpreted primarily as
benchmark-specific evidence rather than strong claims of fault generalization.
Read the full abstract ▾
Image and Video Processing
CATFA-Net: A Trans-Convolutional Approach for Accurate Medical Image Segmentation
Siddhartha Mallick, Aayushman Ghosh, Jayanta Paul et al. (+1 more)
Convolutional blocks have played a crucial role in advancing medical image
segmentation by excelling in dense prediction tasks. However, their inability to effectively capture long-range dependencies has limited their performance.
Transformer-based architectures, leveraging
attention mechanisms, address this limitation by modeling global context and creating expressive feature representations. Recent research has explored this potential by introducing hybrid frameworks that combine
transformer encoders with convolutional decoders. Despite their advantages, these approaches face challenges such as limited inductive bias, high computational cost, and reduced robustness to data variability. To overcome these issues, this study introduces CATFA-Net, a novel and efficient
segmentation framework designed to produce high-quality
segmentation masks while reducing computational costs and increasing inference speed. CATFA-Net employs a hierarchical hybrid encoder architecture with a lightweight convolutional decoder backbone. Its
transformer-based encoder uses a new Context Addition
Attention mechanism that captures inter-image dependencies without the quadratic complexity of standard
attention mechanisms. Features from the
transformer branch are fused with those from the convolutional branch through a proposed Cross-Channel
Attention mechanism, which helps retain spatial and channel information during downsampling. Additionally, a Spatial Fusion
Attention mechanism in the decoder refines features while reducing background noise ambiguity. Extensive evaluations on five publicly available
datasets show that CATFA-Net outperforms existing methods in accuracy and efficiency. The framework sets new state-of-the-art Dice scores on GLaS (94.48%) and ISIC 2018 (91.55%). Robustness tests and external validation further demonstrate its strong ability to generalize in binary
segmentation tasks.
Read the full abstract ▾
All authors Siddhartha Mallick, Aayushman Ghosh, Jayanta Paul, Jaya Sil
Systems and Control
Surgi-HDTMR: Closing the Sensorimotor Loop in Bimanual Microsurgery via Haptics, Digital Twin, and Mixed Reality
Songming Ping, Shaoyue Wen, Junhong Chen et al. (+3 more)
Robotic microsurgery demands precise bimanual control, intuitive interaction, and informative force feedback. However, most training platforms for robotic microsurgery lack immersive 3D interaction and high-fidelity haptics. Here, we present Surgi-HDTMR, a mixed-reality (MR) and digital-twin (DT) training system that couples bimanual haptic teleoperation with a benchtop microsurgical robotic platform, and 3D-printed phantoms. A metrically co-registered, time-synchronized DT aligns in-situ MR guidance with the physical workspace and drives a depth-adaptive haptic model that renders contact, puncture, and tissue-retraction forces. In a within-subjects study of simulated cortical
navigation and tumor resection, Surgi-HDTMR shortened task time, reduced harmful contacts and collisions, and improved perceptual accuracy relative to non-haptic and non-adaptive baselines. These results suggest that tightly coupling MR overlays with a synchronized DT, together with depth-adaptive haptics, can accelerate skill acquisition and improve safety in
robot-assisted microsurgery, pointing toward next-generation
surgical training.
Read the full abstract ▾
All authors Songming Ping, Shaoyue Wen, Junhong Chen, Wen Fan, Lan Wei, Dandan Zhang