检索结果-内蒙古大学图书馆

14th International Conference on Human Haptic Sensing and Touch Enabled Computer Applications, EuroHaptics 2024

作者： KhalilianMotamed Bonab, Ali Camardella, Cristian Frisoli, Antonio Leonardis, Daniele Institute of Mechanical Intelligence and the Department of Excellence in Robotics and AI Scuola Superiore Sant’Anna Pisa Italy

ISBN: (纸本)9783031700606

Wearable haptic devices have been proposed to convey guidance and feedback information in a variety of applications, ranging from navigation to virtual interaction and prosthetics. A design approach for armband devices using an actuated fabric belt and gearmotors actuators has been proposed and widely experimented in the field. In this work we experiment whether the use of direct-drive actuation in place of servomotors proves effective in rendering lower intensity, but cleaner linear feedback. Interestingly, the method allows for modulation of vibrotactile feedback as well, with the same actuation design. Here we present the design of a wearable haptic device for the upper limb, implementing a 2 degrees of freedom direct drive transmission and a soft belt interface. Experiments evaluate the capability of the haptic feedback to guide participants in two different motor tasks, exploiting the two haptic modalities the device can render: clenching and lateral stretch. Moreover, the addition of modulated vibrotactile feedback to the conventional linear motor activation is explored as a viable modality to enhance the perception and effectiveness of the perceived stimuli. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Linear motors

来源：评论

学校读者我要写书评

暂无评论

ChordFormer: A Conformer-Based Architecture for Large-Vocabulary Audio Chord Recognition

arXiv

引用

arXiv 2025年

作者： Akram, Muhammad Waseem Dettori, Stefano Colla, Valentina Buttazzo, Giorgio Carlo Department of Excellence in Robotics and AI Sant’Anna School of Advanced Studies Italy Department of Excellence in Robotics and AI Sant’Anna School of Advanced Studies Italy

Chord recognition serves as a critical task in music information retrieval due to the abstract and descriptive nature of chords in music analysis. While audio chord recognition systems have achieved significant accuracy for small vocabularies (e.g., major/minor chords), large-vocabulary chord recognition remains a challenging problem. This complexity also arises from the inherent long-tail distribution of chords, where rare chord types are underrepresented in most datasets, leading to insufficient training samples. Effective chord recognition requires leveraging contextual information from audio sequences, yet existing models, such as combinations of convolutional neural networks, bidirectional long short-term memory networks, and bidirectional transformers, face limitations in capturing long-term dependencies and exhibit suboptimal performance on large-vocabulary chord recognition tasks. This work proposes ChordFormer, a novel conformer-based architecture designed to tackle structural chord recognition (e.g., triads, bass, sevenths) for large vocabularies. ChordFormer leverages conformer blocks that integrate convolutional neural networks with transformers, thus enabling the model to capture both local patterns and global dependencies effectively. By addressing challenges such as class imbalance through a reweighted loss function and structured chord representations, ChordFormer outperforms state-of-the-art models, achieving a 2% improvement in frame-wise accuracy and a 6% increase in class-wise accuracy on large-vocabulary chord datasets. Furthermore, ChordFormer excels in handling class imbalance, providing robust and balanced recognition across chord types. This approach bridges the gap between theoretical music knowledge and practical applications, advancing the field of large-vocabulary chord recognition. © 2025, CC BY-NC-SA.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Neuroethology of natural actions in freely moving monkeys

引用

Science (New York, N.Y.) 2025年第6730期387卷 214-220页

作者： Lanzarini, Francesca Maranesi, Monica Rondoni, Elena Hilary Albertini, Davide Ferretti, Elena Lanzilotto, Marco Micera, Silvestro Mazzoni, Alberto Bonini, Luca Department of Medicine and Surgery University of Parma Parma Italy Biorobotics Institute Department of Excellence in AI and Robotics Scuola Superiore Sant'Anna Pisa Italy Interdisciplinary Health Center and Department of Excellence in AI and Robotics Scuola Superiore Sant'Anna Pisa Italy Modular Implantable Neuroprostheses Laboratory Università Vita-Salute San Raffaele & Scuola Superiore Sant'Anna Milan Italy Bertarelli Foundation Chair in Translational Neuroengineering School of Engineering Ecole Polytechnique Federale de Lausanne Genève Switzerland

The current understanding of primate natural action organization derives from laboratory experiments in restrained contexts (RCs) under the assumption that this knowledge generalizes to freely moving contexts (FMCs). In this work, we developed a neurobehavioral platform to enable wireless recording of the same premotor neurons in both RCs and FMCs. Neurons often encoded the same hand and mouth actions differently in RCs and FMCs. Furthermore, in FMCs, we identified cells that selectively encoded actions untestable during RCs and others that displayed mixed selectivity for multiple actions, which is compatible with an organization based on cortical motor synergies at different levels of complexity. Cross-context decoding demonstrated that neural activity in FMCs is richer and more generalizable than in RCs, which suggests that neuroethological approaches are better suited to unveil the neural bases of behavior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Effect of User Learning for Online EEG Decoding of Upper-Limb Movement Intention

IEEE Transactions on Medical Robotics and Bionics

引用

IEEE Transactions on Medical robotics and Bionics 2025年第2期7卷 633-641页

作者： Ceradini, Matteo Tortora, Stefano Micera, Silvestro Tonin, Luca Scuola Superiore Sant’Anna BioRobotics Institute Department of Excellence in Robotics and AI Pisa56127 Italy University of Padova Department of Information Engineering Padua Neuroscience Center Padua35122 Italy Neuro-X Institute Ecole Poly-technique Federale de Lausanne Translational NeuroEngineering Laboratory Lausanne1015 Switzerland Università Vita-Salute San Raffaele Modular Implantable Neuroprostheses Laboratory Milan20132 Italy

Electroencephalography (EEG) based brain-computer interfaces (BCIs) offer a promising way for individuals with motor impairments to control prosthetic or rehabilitation devices. Accurately decoding movement intention (MI) is crucial for translating subjects’ motor execution plans into action. Common challenges in EEG-based BCIs include performance discrepancies, often requiring frequent recalibration of decoding algorithms. The objective of this study was enhancing BCI decoding performance of upper-limb MI identification by exploiting both machine and subjects’ learning and maintaining stable decoding algorithms. Significant performance improvements were observed across most subjects from the first to the last session of the experiment. Some subjects also demonstrated stable performance without requiring any model recalibration between sessions. All subjects achieved high efficacy in online decoding of movement intention, as reflected in improvement of the F1 score from 0.58±0.26 in the first session, to 0.84±0.13 in the final session. We emphasize the critical importance of allowing users sufficient time to improve their performance in BCIs for upper-limb MI decoding. Unlike existing studies, we specifically evaluate the effect of stable decoding strategies in online and longitudinal BCI sessions, which are key to achieving more reliable and effective BCIs. © 2018 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Physical Disturbance Rejection Methods in Myokinetic Control of Prosthetic Limbs

引用

IEEE Transactions on Biomedical Engineering 2025年 PP卷 PP页

作者： Paggetti, F. Gherardini, M. Ianniciello, V. Cirelli, S. Cipriani, C. Scuola Superiore Sant'Anna Italy Scuola Superiore Sant'Anna BioRobotics Institute Italy Scuola Superiore Sant'Anna Department of Excellence in Robotics and AI Italy

Objective: The myokinetic control interface for limb protheses involves implanting small permanent magnets in the residual muscles of the stump, retrieving their displacement induced by muscle contraction using external magnetic sensors, and mapping such displacements to motor commands. We have previously shown the feasibility of tracking several magnets implanted in an anatomically relevant workspace. However, to clinically translate the interface, strategies to address different kinds of external disturbances compromising its functioning are mandatory. Among these, physical disturbances, viz. relative displacement between the sensors and the magnets not due to voluntary contraction, could significantly hinder the interface usability. Methods: Here we propose three rejection methods sought to mitigate this problem: one aims to realign the sensors and the magnets when a disturbance is detected, through numerical approximation methods;the others exploit differential measurements. We applied these concepts to upper limb prostheses, by mimicking the presence of physical disturbances in simulations and through a physical setup, reproducing four target muscles of a human forearm to be potentially implanted. Finally, we evaluated the rejection ability of one of those methods during the first-in-human implementation of the myokinetic interface. Results: All methods proved capable of rejecting the disturbances, showing median localization errors below 10% the displacement undergone during contraction. Conclusion: Results suggest that the optimal rejection method is application-specific, and provide hints for assessing different factors influencing the best choice. Significance: Other than being crucial for the myokinetic interface development, these outcomes also provide interesting insights for many biomedical applications exploiting remote magnetic tracking. © 1964-2012 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Adaptive Drift Compensation for Soft Sensorized Finger Using Continual Learning

arXiv

引用

arXiv 2025年

作者： Kushawaha, Nilay Pathan, Radan Pagliarani, Niccolò Cianchetti, Matteo Falotico, Egidio The BioRobotics Institute Scuola Superiore Sant’Anna Pontedera Italy Department of Excellence in Robotics and AI Scuola Superiore Sant’Anna Pisa Italy

Strain sensors are gaining popularity in soft robotics for acquiring tactile data due to their flexibility and ease of integration. Tactile sensing plays a critical role in soft grippers, enabling them to safely interact with unstructured environments and precisely detect object properties. However, a significant challenge with these systems is their high non-linearity, time-varying behavior, and long-term signal drift. In this paper, we introduce a continual learning (CL) approach to model a soft finger equipped with piezoelectric-based strain sensors for proprioception. To tackle the aforementioned challenges, we propose an adaptive CL algorithm that integrates a Long Short-Term Memory (LSTM) network with a memory buffer for rehearsal and includes a regularization term to keep the model’s decision boundary close to the base signal while adapting to time-varying drift. We conduct nine different experiments, resetting the entire setup each time to demonstrate signal drift. We also benchmark our algorithm against two other methods and conduct an ablation study to assess the impact of different components on the overall performance. © 2025, CC BY.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

CORT: Class-Oriented Real-time Tracking for Embedded Systems

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Cittadini, Edoardo Siena, Alessandro De Buttazzo, Giorgio Sant’Anna School of Advanced Studies Department of Excellence on Robotics and AI PI Pisa56124 Italy Softsystem srl PI Pisa56020 Italy

The ever-increasing use of artificial intelligence in visual perception tasks for autonomous systems has significantly contributed to advance the research on multi-object tracking, which is a function required in several real-time applications (e.g., autonomous driving, surveillance drones, robotics) to localize and follow the trajectory of multiple objects moving in front of a camera. Most of current tracking algorithms introduce complex heuristics and re-identification models to improve the tracking accuracy and reduce the number of identification switches, without particular attention to the timing performance, whereas other approaches are aimed at reducing response times by removing the re-identification phase, thus penalizing the tracking accuracy. This work proposes a new approach to multi-class object tracking that allows achieving smaller and more predictable execution times with respect to traditional approaches, without penalizing the tracking performance. The idea is to divide the problem of matching predictions with detections into a number of smaller sub-problems by splitting the Hungarian association matrix by class and invoking the second re-identification stage only when strictly necessary, thus applying it to a smaller number of elements. Splitting the matching problem into a number of smaller sub-problems also allows parallelizing the Hungarian algorithm, further reducing the execution time in multi-core processing platforms. The proposed solution was evaluated in complex urban scenarios with different types of objects (as cars, buses, and motorbikes), and different number of instances, showing the effectiveness of the multi-class approach in reducing execution times without penalizing performance, with respect to state of the art trackers. © 2020 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Design of a Soft Robotic Artificial Cardiac Wall

引用

Artificial Organs 2025年第0期 2025 Mar 12页

作者： Zrinscak, Debora De Chirico, Claudia M. Lorenzon, Lucrezia Coluccia, Fabiola De Luca, Mauro Maselli, Martina Kluin, Jolanda Overvelde, Johannes T. B. Cianchetti, Matteo The BioRobotics Insitute and Department of Excellence of Robotics & AI Scuola Superiore Sant'Anna Pontedera Italy Department of Cardiothoracic Surgery Thorax Center Erasmus MC Rotterdam GD Rotterdam Netherlands AMOLF Amsterdam Netherlands

Background: In cardiovascular engineering, the recent introduction of soft robotic technologies sheds new light on the future of implantable cardiac devices, enabling the replication of complex bioinspired architectures and motions. To support human heart function, assistive devices and total artificial hearts have been developed. However, the system's functionality, hemocompatibility, and overall implantability are still open challenges. Methods: Here, the design of a soft robotic artificial cardiac wall is presented: the action of a bioinspired myocardium of pneumatic McKibben actuators in a double helix is coupled with an engineered passive and deformable endocardial layer made of silicone. The correlation between the helix angle of the actuators and the ejection fraction of the artificial cardiac wall was preliminarily studied with a simplified analytical model. A FEM model was introduced to represent the complex deformation of the endocardial layer during the actuation of the cardiac wall. Results: Experimental tests report an ejection fraction of 68%, i.e., 77.2 ± 0.4 mL against 90 mmHg, satisfying the minimum physiological requirements and, therefore, proving the concept's functionality. Conclusions: The conceived device paves the way for a new generation of innovative approaches where engineered bioinspiration might be the key to future artificial cardiac pumps that could support or even substitute the human failing heart. © 2025 The Author(s). Artificial Organs published by International Center for Artificial Organ and Transplantation (ICAOT) and Wiley Periodicals LLC.

关键词： Silicones

来源：评论

学校读者我要写书评

暂无评论

A Reliable, Time-Predictable Heterogeneous SoC for ai-Enhanced Mixed-Criticality Edge Applications

arXiv

引用

arXiv 2025年

作者： Garofalo, Angelo Ottaviano, Alessandro Perotti, Matteo Benz, Thomas Tortorella, Yvan Balas, Robert Rogenmoser, Michael Zhang, Chi Bertaccini, Luca Wistoff, Nils Ciani, Maicol Koenig, Cyril Sinigaglia, Mattia Valente, Luca Scheffler, Paul Eggimann, Manuel Cavalcante, Matheus Restuccia, Francesco Biondi, Alessandro Conti, Francesco Gurkaynak, Frank K. Rossi, Davide Benini, Luca D-ITET department ETH Zurich Switzerland University of Bologna Italy CA United States Department of Excellence in Robotics & AI Scuola Superiore Sant’Anna Pisa Italy

Next-generation mixed-criticality Systems-on-chip (SoCs) for robotics, automotive, and space must execute mixed-criticality ai-enhanced sensor processing and control workloads, ensuring reliable and time-predictable execution of critical tasks sharing resources with non-critical tasks, while also fitting within a sub-2W power envelope. To tackle these multi-dimensional challenges, in this brief, we present a 16nm, reliable, time-predictable heterogeneous SoC with multiple programmable accelerators. Within a 1.2W power envelope, the SoC integrates software-configurable hardware IPs to ensure predictable access to shared resources, such as the on-chip interconnect and memory system, leading to tight upper bounds on execution times of critical applications. To accelerate mixed-precision mission-critical ai, the SoC integrates a reliable multi-core accelerator achieving 304.9 GOPS peak performance at 1.6 TOPS/W energy efficiency. Non-critical, compute-intensive, floating-point workloads are accelerated by a dual-core vector cluster, achieving 121.8 GFLOPS at 1.1 TFLOPS/W and 106.8 GFLOPS/mm2 Copyright © 2025, The Authors. All rights reserved.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

T-REX: A Framework to Build Trustworthy Recommenders of Evidence Explanation

T-REX: A Framework to Build Trustworthy Recommenders of Evid...

引用

2024 Discovery Science Late Breaking Contributions, DS-LB 2024

作者： Fedele, Andrea de’ Cavalieri, Mattia Franchi Landi, Cristiano Punzi, Clara Tramacere, Stefano University of Pisa Pisa Italy KDD Lab ISTI-CNR Pisa Italy The BioRobotics Institute Scuola Superiore Sant’Anna Pisa Italy Department of Excellence in Robotics & AI Scuola Superiore Sant’Anna Pisa Italy Scuola Normale Superiore Pisa Italy LIDER-Lab Scuola Superiore Sant’Anna Pisa Italy

The initial enthusiasm for eXplainable Artificial Intelligence (Xai) has been tempered by concerns about the effectiveness and reliability of its explanations. Studies show that some explanations are no more reliable than random ones. Tim Miller suggests a paradigm shift in Xai to address issues of cognitive biases, such as automation bias, which can affect decision-making processes. He advocates for hypothesis-driven support systems to align ai explanations with human cognitive processes. Addressing these issues, we propose the Trustworthy Recommenders of Evidence eXplanations (T-REX) framework. This approach aims to enhance Xai by moving from statistical explanations to those based on trustworthy scientific evidence, enabling ai systems to tackle complex tasks more effectively. © 2022 Copyright for this paper by its authors.

关键词： Explainable ai Human-Machine Interaction Trustworthy ai

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：