检索结果-内蒙古大学图书馆

Communication-efficient Vertical Federated Learning via Compressed Error Feedback

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Valdeira, Pedro Xavier, João Soares, Cláudia Chi, Yuejie CMU IST United States IST NOVA CMU United States Department of Electrical and Computer Engineering Carnegie Mellon University United States Institute for Systems and Robotics Instituto Superior Técnico Portugal Department of Computer Science NOVA School of Science and Technology

Communication overhead is a known bottleneck in federated learning (FL). To address this, lossy compression is commonly used on the information communicated between the server and clients during training. In horizontal FL, where each client holds a subset of the samples, such communication-compressed training methods have recently seen significant progress. However, in their vertical FL counterparts, where each client holds a subset of the features, our understanding remains limited. To address this, we propose an error feedback compressed vertical federated learning (EF-VFL) method to train split neural networks. In contrast to previous communication-compressed methods for vertical FL, EF-VFL does not require a vanishing compression error for the gradient norm to converge to zero for smooth nonconvex problems. By leveraging error feedback, our method can achieve a O(1/T) convergence rate for a sufficiently large batch size, improving over the state-of-the-art O(1/√T) rate under O(1/√T) compression error, and matching the rate of uncompressed methods. Further, when the objective function satisfies the Polyak-Lojasiewicz inequality, our method converges linearly. In addition to improving convergence, our method also supports the use of private labels. Numerical experiments show that EF-VFL significantly improves over the prior art, confirming our theoretical results. The code for this work can be found at https://***/Valdeira/EF-VFL. © 2024, CC BY.

关键词： Federated learning

Modular Adaptive Aerial Manipulation under Unknown Dynamic Coupling Forces

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yadav, Rishabh Dev Dantu, Swati Pan, Wei Sun, Sihao Roy, Spandan Baldi, Simone Department of Computer Science The Univerity of Manchester United Kingdom Multi-robot systems group Faculty of Electrical Engineering Czech Technical University Prague Czech Republic Department of Cognitive Robotics Delft Univesrity of Technology Netherlands Robotics Research Center International Institute of Information Technology Hyderabad India School of Mathematics Southeast University Nanjing China

Successful aerial manipulation largely depends on how effectively a controller can tackle the coupling dynamic forces between the aerial vehicle and the manipulator. However, this control problem has remained largely unsolved as the existing control approaches either require precise knowledge of the aerial vehicle/manipulator inertial couplings, or neglect the state-dependent uncertainties especially arising during the interaction phase. This work proposes an adaptive control solution to overcome this long standing control challenge without any a priori knowledge of the coupling dynamic terms. Additionally, in contrast to the existing adaptive control solutions, the proposed control framework is modular, that is, it allows independent tuning of the adaptive gains for the vehicle position sub-dynamics, the vehicle attitude sub-dynamics, and the manipulator sub-dynamics. Stability of the closed loop under the proposed scheme is derived analytically, and real-time experiments validate the effectiveness of the proposed scheme over the state-of-the-art approaches. © 2024, CC BY.

关键词： Adaptive control systems

Bringing sensation to prosthetic hands-chronic assessment of implanted thin-film electrodes in humans

学校读者我要写书评

暂无评论

npj Flexible Electronics 2023年第1期7卷 32-45页

作者： PaulČvančara Giacomo Valle Matthias Müller Inga Bartels Thomas Guiho Arthur Hiairrassary Francesco Petrini Stanisa Raspopovic Ivo Strauss Giuseppe Granata Eduardo Fernandez Paolo M.Rossini Massimo Barbaro Ken Yoshida Winnie Jensen Jean-Louis Divoux David Guiraud Silvestro Micera Thomas Stieglitz Laboratory for Biomedical Microtechnology Department of Microsystems Engineering-IMTEKAlbert-Ludwig-University FreiburgFreiburgGermany Center for Neuroprosthetics and Institute of Bioengineering School of EngineeringÉcole Polytechnique Fédérale de Lausanne(EPFL)LausanneSwitzerland The Biorobotics Institute Scuola Superiore Sant’AnnaPisaItaly Camin Team INRIAUniversity of MontpellierMontpellierFrance Institute of Neurology Catholic University of the Sacred HeartRomaItaly Institute of Neurosurgery Catholic University of the Sacred HeartRomaItaly Department of Neuroscience&Neurorehabilitation IRCCS San Raffaele Roma00166 RomeItaly Department of Electrical and Electronic Engineering University of CagliariCagliariItaly Biomedical Engineering Department Indiana University-Purdue UniversityIndianapolisINUSA SMI Dept.Health Science and TechnologyAalborg UniversityAalborgDenmark AXONIC/Groupe MXM VallaurisFrance BrainLinks-BrainTools Albert-Ludwig-University FreiburgFreiburgGermany Bernstein Center Freiburg Albert-Ludwig-University FreiburgFreiburgGermany Present address:Laboratory for Neuroengineering Department of Health Sciences and TechnologyInstitute for Robotics and Intelligent SystemsETH ZürichZürichSwitzerland

Direct stimulation of peripheral nerves with implantable electrodes successfully provided sensory feedback to amputees while using hand *** of the electrodes is key to success,which we have improved for the polyimide-based transverse intrafascicular multichannel electrode(TIME).The TIMEs were implanted in the median and ulnar nerves of three trans-radial amputees for up to six *** present a comprehensive assessment of the electrical properties of the thin-film metallization as well as material status post *** TIMEs stayed within the electrochemical safe limits while enabling consistent and precise amplitude *** lead to a reliable performance in terms of eliciting *** signs of corrosion or morphological change to the thin-film metallization of the probes was observed by means of electrochemical and optical *** presented longevity demonstrates that thin-film electrodes are applicable in permanent implant systems.

关键词： film electrodes sensation

Land & Localize: An Infrastructure-free and Scalable Nano-Drones Swarm with UWB-based Localization

学校读者我要写书评

暂无评论

Land & Localize: An Infrastructure-free and Scalable Nano-Dr...

International Conference on Distributed Computing in Sensor systems (DCOSS)

作者： Mahyar Pourjabar Ahmed AlKatheeri Manuele Rusci Agata Barcis Vlad Niculescu Eliseo Ferrante Daniele Palossi Luca Benini Department of Electrical Electronic and Information Engineering (DEI) University of Bologna Italy Autonomous Robotics Research Center (ARRC) Technology Innovation Institute UAE Department of Electrical Engineering KU Leuven Belgium Integrated Systems Laboratory (IIS) ETH Zürich Switzerland Dalle Molle Institute for Artificial Intelligence (IDSIA) USI-SUPSI Switzerland

Relative localization is a crucial functional block of any robotic swarm. We address it in a fleet of nano-drones characterized by a 10 cm-scale form factor, which makes them highly versatile but also strictly limited in their onboard power envelope. State-of-the-Art solutions leverage Ultra-WideBand (UWB) technology, allowing distance range measurements between peer nano-drones and a stationary infrastructure of multiple UWB anchors. Therefore, we propose an UWB-based infrastructure-free nanodrones swarm, where part of the fleet acts as dynamic anchors, i.e., anchor-drones (ADs), capable of automatic deployment and landing. By varying the ADs' position constraint, we develop three alternative solutions with different trade-offs between flexibility and localization accuracy. In-field results, with four flying mission- drones (MDs), show a localization root mean square error (RMSE) spanning from 15.3 cm to 27.8 cm, at most. Scaling the number of MDs from 4 to 8, the RMSE marginally increases, i.e., less than 10 cm at most. The power consumption of the MDs' UWB module amounts to 342mW. Ultimately, compared to a fixed-infrastructure commercial solution, our infrastructure-free system can be deployed anywhere and rapidly by taking 5.7 s to self-localize 4 ADs with a localization RMSE of up to 12.3% in the most challenging case with 8 MDs.

关键词：

SAD-TIME: a Spatiotemporal-fused network for depression detection with Automated multi-scale Depth-wise and TIME-interval-related common feature extractor

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Han-Guang Hou, Hui-Rang Jin, Li-Cheng Xu, Chen-Yang Zhang, Zhong-Yi Meng, Qing-Hao Zhang, Yong-Hui Tianjin Key Laboratory of Process Measurement and Control Institute of Robotics and Autonomous Systems School of Electrical and Information Engineering Tianjin University Tianjin300072 China Department of Psychiatry Tianjin Anding Hospital Mental Health Center Tianjin Medical University China

Background and Objective: Depression is a severe mental disorder, and accurate diagnosis is pivotal to the cure and rehabilitation of people with depression. However, the current questionnaire-based diagnostic methods could bring subjective biases and may be denied by subjects. In search of a more objective means of diagnosis, researchers have begun to experiment with deep learning-based methods for identifying depressive disorders in recent years. Methods: In this study, a novel Spatiotemporal-fused network with Automated multi-scale Depth-wise and TIME-interval-related common feature extractor (SAD-TIME) is proposed. SAD-TIME incorporates an automated nodes’ common features extractor (CFE), a spatial sector (SpS), a modified temporal sector (TeS), and a domain adversarial learner (DAL). The CFE includes a multiscale depth-wise 1D-convolutional neural network and a time-interval embedding generator, where the unique information of each channel is preserved. The SpS fuses the functional connectivity with the distance-based connectivity containing spatial position of EEG electrodes. A multi-head-attention graph convolutional network is also applied in the SpS to fuse the features from different EEG channels. The TeS is based on long short-term memory and graph transformer networks, where the temporal information of different time-windows is fused. Moreover, the DAL is used after the SpS to obtain the domain-invariant feature. Results: Experimental results under tenfold cross-validation show that the proposed SAD-TIME method achieves 92.00% and 94.00% depression classification accuracies on two datasets, respectively, in cross-subject mode. Conclusion: SAD-TIME is a robust depression detection model, where the automatedly-generated features, the SpS and the TeS assist the classification performance with the fusion of the innate spatiotemporal information in the EEG signals. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolutional neural networks

TaSIL: Taylor Series Imitation Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pfrommer, Daniel Zhang, Thomas T.C.K. Tu, Stephen Matni, Nikolai Department of Electrical and Systems Engineering University of Pennsylvania United States Google Brain Robotics United States Massachusetts Institute of Technology United States

We propose Taylor Series Imitation Learning (TaSIL), a simple augmentation to standard behavior cloning losses in the context of continuous control. TaSIL penalizes deviations in the higher-order Taylor series terms between the learned and expert policies. We show that experts satisfying a notion of incremental input-to-state stability are easy to learn, in the sense that a small TaSIL-augmented imitation loss over expert trajectories guarantees a small imitation loss over trajectories generated by the learned policy. We provide generalization bounds for TaSIL that scale as Õ(1/n) in the realizable setting, for n the number of expert demonstrations. Finally, we demonstrate experimentally the relationship between the robustness of the expert policy and the order of Taylor expansion required in TaSIL, and compare standard Behavior Cloning, DART, and DAgger with TaSIL-loss-augmented variants. In all cases, we show significant improvement over baselines across a variety of MuJoCo tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Taylor series

AttDLNet: Attention-based DL Network for 3D LiDAR Place Recognition

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Barros, Tiago Garrote, Luís Pereira, Ricardo Premebida, Cristiano Nunes, Urbano J. University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Portugal

LiDAR-based place recognition is one of the key components of SLAM and global localization in autonomous vehicles and robotics applications. With the success of DL approaches in learning useful information from 3D LiDARs, place recognition has also benefited from this modality, which has led to higher re-localization and loop-closure detection performance, particularly, in environments with significant changing conditions. Despite the progress in this field, the extraction of proper and efficient descriptors from 3D LiDAR data that are invariant to changing conditions and orientation is still an unsolved challenge. To address this problem, this work proposes a novel 3D LiDAR-based deep learning network (named AttDLNet) that uses a range-based proxy representation for point clouds and an attention network with stacked attention layers to selectively focus on long-range context and inter-feature relationships. The proposed network is trained and validated on the KITTI dataset and an ablation study is presented to assess the novel attention network. Results show that adding attention to the network improves performance, leading to efficient loop closures, and outperforming an established 3D LiDAR-based place recognition approach. From the ablation study, results indicate that the middle encoder layers have the highest mean performance, while deeper layers are more robust to orientation change. The code is publicly available at:https://***/Cybonic/AttDLNet. © 2021, CC BY.

关键词： Ablation

Place recognition survey: An update on deep learning approaches

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Barros, Tiago Pereira, Ricardo Garrote, Luís Premebida, Cristiano Nunes, Urbano J. The University of Coimbra Institute of Systems and Robotics Department of Electrical and Computer Engineering Portugal

Autonomous Vehicles (AV) are becoming more capable of navigating in complex environments with dynamic and changing conditions. A key component that enables these intelligent vehicles to overcome such conditions and become more autonomous is the sophistication of the perception and localization systems. As part of the localization system, place recognition has benefited from recent developments in other perception tasks such as place categorization or object recognition, namely with the emergence of deep learning (DL) frameworks. This paper surveys recent approaches and methods used in place recognition, particularly those based on deep learning. The contributions of this work are twofold: surveying recent sensors such as 3D LiDARs and RADARs, applied in place recognition;and categorizing the various DL-based place recognition works into supervised, unsupervised, semi-supervised, parallel, and hierarchical categories. First, this survey introduces key place recognition concepts to contextualize the reader. Then, sensor characteristics are addressed. This survey proceeds by elaborating on the various DL-based works, presenting summaries for each framework. Some lessons learned from this survey include: the importance of NetVLAD for supervised end-to-end learning;the advantages of unsupervised approaches in place recognition, namely for cross-domain applications;or the increasing tendency of recent works to seek, not only for higher performance but also for higher efficiency. © 2021, CC BY.

关键词： Surveys

A high-accuracy, low-budget Sensor Glove for Trajectory Model Learning 20

学校读者我要写书评

暂无评论

A high-accuracy, low-budget Sensor Glove for Trajectory Mode...

20th International Conference on Advanced robotics, ICAR 2021

作者： Denz, Robin Demirci, Rabia Cansev, M. Ege Bliek, Adna Beckerle, Philipp Rueckert, Elmar Rottmann, Nils Institute For Robotics and Cognitive Systems University of Luebeck Luebeck23562 Germany Chair of Autonomous Systems and Mechatronics Friedrich-Alexander-University Department of Electrical Engineering Erlangen-Nürnberg Germany Chair of Cyber-Physical-Systems Montanuniversität Leoben Leoben Austria

ISBN: (纸本)9781665436847

Sensor gloves are gaining importance in tracking hand and finger movements in virtual reality applications as well as in scientific research. They introduce an unrestricted way of capturing motion without the dependence on direct line of sight as for visual tracking systems. With such sensor gloves, data of complex motion tasks can be recorded and used for modeling probabilistic trajectories or teleoperation of robotic arms. While a multitude of sensor glove designs relying on different functional principles exist, these approaches require either sensitive calibration and sensor fusion methods or complex manufacturing processes. In this paper, we propose a low-budget, yet accurate sensor glove system that uses flex sensors for fast and efficient motion tracking. We evaluate the performance of our sensor glove, such as accuracy and latency, and demonstrate the functionality by recording motion data for learning probabilistic movement models. © 2021 IEEE.

关键词： Budget control