检索结果-内蒙古大学图书馆

Feedback Shaping for Boolean Networks

IFAC-PapersOnLine 2023年第2期56卷 6684-6689页

作者： Hongsheng Qi Maria Elena Valcher Guodong Shi Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China Dipartimento di Ingegneria dell'Informazione Universita’ di Padova Padova 35131 Italy Australian Center for Robotics School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney NSW 2006 Australia

Boolean networks, as logical dynamical systems where the system states are Boolean variables, arise from applications in biology, computer networks, and social networks etc. In this paper, we present a framework to evaluate whether and how the closed-loop dynamics of a controlled Boolean network can be shaped into any prescribed form by state-feedback control. We refer to this problem as to the feedback shaping for Boolean networks. First of all, based on the linear representation of Boolean networks, we establish a necessary and sufficient rank condition for a controlled Boolean network to be feedback shapable or not. Next, we design an algorithm for the synthesis of closed-loop dynamics for a feedback shapable Boolean network, such that for any given controlled Boolean network and a desired closed-loop dynamics, one can always find a feedback control law so that the closed-loop dynamics is precisely realized.

关键词： Boolean networks feedback shaping

来源：评论

学校读者我要写书评

暂无评论

Communication-efficient Vertical Federated Learning via Compressed Error Feedback

arXiv

引用

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

来源：评论

学校读者我要写书评

暂无评论

Distilling Tiny and Ultra-fast Deep Neural Networks for Autonomous Navigation on Nano-UAVs

arXiv

引用

arXiv 2024年

作者： Lamberti, Lorenzo Bellone, Lorenzo Macan, Luka Natalizio, Enrico Conti, Francesco Palossi, Daniele Benini, Luca The Department of Electrical Electronic and Information Engineering University of Bologna Italy The Autonomous Robotics Research Center Technology Innovation Institute United Arab Emirates CNRS LORIA University of Lorraine France The Dalle Molle Institute for Artificial Intelligence USI-SUPSI Switzerland The Integrated Systems Laboratory ETH Zürich Switzerland

Nano-sized unmanned aerial vehicles (UAVs) are ideal candidates for flying Internet-of-Things smart sensors to collect information in narrow spaces. This requires ultra-fast navigation under very tight memory/computation constraints. The PULP-Dronet convolutional neural network (CNN) enables autonomous navigation running aboard a nano-UAV at 19 frame/s, at the cost of a large memory footprint of 320 kB - and with drone control in complex scenarios hindered by the disjoint training of collision avoidance and steering capabilities. In this work, we distill a novel family of CNNs with better capabilities than PULP-Dronet, but memory footprint reduced by up to 168× (down to 2.9 kB), achieving an inference rate of up to 139 frame/s;we collect a new open-source unified collision/steering 66 k images dataset for more robust navigation;and we perform a thorough in-field analysis of both PULP-Dronet and our tiny CNNs running on a commercially available nano-UAV. Our tiniest CNN, called Tiny-PULP-Dronet v3, navigates with a 100% success rate a challenging and never-seen-before path, composed of a narrow obstacle-populated corridor and a 180° turn, at a maximum target speed of 0.5 m/s. In the same scenario, the SoA PULP-Dronet consistently fails despite having 168× more parameters. Copyright © 2024, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Dehazing-aided Multi-Rate Multi-Modal Pose Estimation Framework for Mitigating Visual Disturbances in Extreme Underwater Domain

arXiv

引用

arXiv 2024年

作者： Sudevan, Vidya Zayer, Fakhreddine Hassan, Taimur Javed, Sajid Karki, Hamad De Masi, Giulia Dias, Jorge Center for Autonomous Robotic Systems Khalifa University Abu Dhabi United Arab Emirates College of Engineering Abu Dhabi University Al Ain United Arab Emirates Autonomous Robotics Research Center Technology Innovation Institute Abu Dhabi United Arab Emirates

This paper delves into the potential of DU-VIO, a dehazing-aided hybrid multi-rate multi-modal Visual-Inertial Odometry (VIO) estimation framework, designed to thrive in the challenging realm of extreme underwater environments. The cutting-edge DU-VIO framework is incorporating a Generative Adversarial Network (GAN)-based pre-processing module and a hybrid CNN-LSTM module for precise pose estimation, using visibility-enhanced underwater images and raw Inertial Measurement Unit (IMU) data. Accurate pose estimation is paramount for various underwater robotics and exploration applications. However, underwater visibility is often compromised by suspended particles and attenuation effects, rendering visualinertial pose estimation a formidable challenge. DU-VIO aims to overcome these limitations by effectively removing visual disturbances from raw image data, enhancing the quality of image features used for pose estimation. We demonstrate the effectiveness of DU-VIO by calculating Root Mean Square Error (RMSE) scores for translation and rotation vectors in comparison to their reference values. These scores are then compared to those of a base model using a modified AQUALOC Dataset. Our analysis encompasses RMSE scores related to pose error, as well as an evaluation of inference speed, power consumption, GPU utilization, GPU memory usage, and temperature during the inference phase. This study's significance lies in its potential to revolutionize underwater robotics and exploration. DU-VIO offers a robust solution to the persistent challenge of underwater visibility, significantly improving the accuracy of pose estimation. We validate DUVIO's capabilities through rigorous testing in diverse extreme underwater scenarios, showcasing its efficacy in mitigating the impact of visual disturbances on pose estimation accuracy. This research contributes valuable insights and tools for advancing underwater technology, with far-reaching implications for scientific research, environmen

关键词： Underwater visibility

来源：评论

学校读者我要写书评

暂无评论

Neurocontroller for vibrodrive control of adaptive vibration technological machines 2

Neurocontroller for vibrodrive control of adaptive vibration...

引用

2nd IEEE KhPI Week on Advanced Technology, KhPI Week 2021

作者： Chubyk, Roman Zelinsky, Igor Cherno, Oleksandr Lviv National Agrarian University Department of Information Systems and Technologies Lviv Ukraine Technologies Institute of Mechanical Engineering and Transport Lviv Polytechnic National University Department of Robotics and Integrated Mechanical Engineering Lviv Ukraine Admiral Makarov National University of Shipbuilding Department of Computerized Control Systems Mykolaiv Ukraine

A structure of the neurocontroller-based control system for the vibratory drive of adaptive vibration technological machines is proposed. It allows implementing a two-circuit system of neurocontrol of energy and techn... 详细信息

ISBN: (纸本)9781665412056

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

A Parallel and Asynchronous Blob Shape Descriptor Implemented in CMOS Technology

A Parallel and Asynchronous Blob Shape Descriptor Implemente...

引用

International Conference on Microelectronics, MIEL

作者： P. Bogacki M. Długosz T. Talaśka R. Długosz Aptiv Services Poland Kraków Poland Institute of Telecommunications Faculty of Computer Science Electronics and Telecommunications AGH University of Science and Technology Kraków Poland Faculty of Control Robotics and Electrical Engineering Institute of Automation and Robotics Division of Signal Processing and Electronic Systems Poznan University of Technology Poznan Poland Faculty of Telecommunication Computer Science and Electrical Engineering Bydgoszcz University of Science and Technology Bydgoszcz Poland

The paper presents a family of novel light blob shape descriptors for use in selected active safety algorithms used in Advanced Driver Assistance systems (ADAS). One of the motivations was to obtain a descriptor that would ensure low computational complexity. This makes it easy to implement both in software and hardware. One assumption is that the location of the center of a given light spot is approximately known. The principle of its operation is then to count white pixels in selected directions, starting from this central point. A key issue here is an efficient way of determining indexes of particular pixels belonging to the image patch, as well as the location of points representing places where the white area turns into black. In the case of a hardware implementation, this can be done using a parallel circuit operating in asynchronous mode, without the need for a control clock.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE International Conference on Image Processing

作者： Chaowei Han Gaofeng Meng Chunlei Huo State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation Chinese Academy of Sciences School of Information Engineering Capital Normal University Beijing China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Content-based video retrieval aims to retrieve near-duplicate entries from a database of a given query video. It plays an important role in combating video piracy. Robustness to video temporal dynamics is crucial for a representation model in video retrieval, as frames extracted from two copied videos are hardly temporally aligned in actual situations. However, current image retrieval datasets have difficulty in evaluating this robustness. To address this issue, we collect Similar Frame Dataset (SFD), which consists of 32,923 query-target pairs with 128,240 distraction images. The task of SFD is to retrieve the target frame from all items given a query frame. SFD is constructed by sampling frames from Kinetics-700 action classification dataset. An object detection model (Faster R-CNN) and a Multimodal Large Language Model (BLIP2) are used during sampling to select those valid frames. Besides, we propose Adjacent Frames Contrastive Learning (AFCL) framework. In AFCL, adjacent frames are sampled from unlabeled videos as positive pairs. An image representation model with robustness to changing frames can be trained under AFCL framework and achieve the state-of-the-art performance on SFD. The code will be released at https://***/Chuan-shanjia/Similar-Frame-Dataset.

关键词： Codes Databases Scalability Large language models Image retrieval Contrastive learning Object detection

来源：评论

学校读者我要写书评

暂无评论

Vibration Suppression of Non-Deformable Metal Strip for Robot Assisted Assembly Operation

Vibration Suppression of Non-Deformable Metal Strip for Robo...

引用

2020 IEEE International Conference on Emerging Trends in Communication, Control and Computing, ICONC3 2020

作者： Jalendra, Chetan Rout, B.K. Center for Robotics and Intelligent Systems Birla Institute of Technology and Science Department of Mechanical Engineering Pilani India

ISBN: (纸本)9781728114200

Current work presents a vibration suppression strategies of a Non-Deformable Metal Strip which is induced by rapid action of an industrial robot. In this case an external controller is designed as outer controller without any interruption in the robot internal controller to suppress the residual vibration in NDMS. The proposed controller is simulated in MATLAB/Simulink environment and designed in Python IDLE to validate the controller. The external controller is a closed-loop feedback Proportional Integral Derivative (PID) controller designed especially for an industrial robot that does not have control over acceleration. The robustness of the proposed controller is tested experimentally through the vibration control of a NDMS which is supposed to perform peg in hole assembly operation in various operating conditions. The designed controller suppresses vibration in less than 5 seconds and the stability time is reduced by 95% for in a Peg-in-hole assembly task. © 2020 IEEE.

关键词： Three term control systems

来源：评论

学校读者我要写书评

暂无评论

Adapting NIST Aerial Drone Tests for Thermal Identification, Inspection, and Suppression of Wildfires

Adapting NIST Aerial Drone Tests for Thermal Identification,...

引用

IEEE Annual Computing and Communication Workshop and Conference (CCWC)

作者： Alex Fraley Ethan Nowery McCarthy Devine Adam Jacoff Paul Y. Oh Robotics Research Engineer for the Emergency Response Robots (Ground Aerial Aquatic) Project in the Intelligent Systems Division of the Engineering Laboratory National Institute of Standards and Technology (NIST) Gaithersburg MD USA Department of Mechanical Engineering University of Nevada Las Vegas (UNLV) Las Vegas NV USA Department of Aerospace Engineering University of Colorado Boulder (CU Boulder) Boulder CO USA Project Leader for Emergency Response Robots (Ground Aerial Aquatic) in the Intelligent Systems Division of the Engineering Laboratory National Institute of Standards and Technology (NIST) Gaithersburg MD USA Faculty of Mechanical Engineering University of Nevada Las Vegas

ISBN: (数字)9798331507695

ISBN: (纸本)9798331507701

The National institute of Standards and Technology (NIST) has developed standard test methods to evaluate the capabilities of aerial drones, ground robots, and aquatic vehicles, as well as the proficiency of their operators. The aerial drone tests measure key capabilities such as maneuverability, visual acuity, and thermal acuity. With a rising demand for aerial drones among first responders, these tests are essential for assessing system performance, mitigating risk, and improving operational effectiveness to ensure the safety of responders and the public. Given the increasing prominence of wildfire threats and the widespread destruction they cause, aerial drones are being adapted to help detect, inspect, and contain them. This paper outlines how NIST-developed aerial drone tests can be adapted to simulate wildfire threats and provide a framework of reproducible tests that measure the system capabilities of aerial drones and the proficiency of operators in mitigating these threats.

关键词： Heating systems Visualization Wildfires System performance NIST Inspection Writing Object recognition Underwater vehicles Drones

来源：评论

学校读者我要写书评

暂无评论

Koopman Representation for Boolean Networks

引用

IFAC-PapersOnLine 2023年第2期56卷 6678-6683页

Boolean networks, as logical dynamical systems whose system states are Boolean variables, arise from applications in biology, computer networks, and social networks etc. The representation and control of Boolean networks have attracted a lot of attention in recent years. On a parallel line of research, Koopman developed an operator view of nonlinear dynamical systems in early 1930s, which shows that using observable functions all nonlinear dynamics can be represented as (infinite dimensional) linear systems. In this paper, we present a framework for representing Boolean networks via Koopman approach. First of all, we construct addition and scalar multiplication operations over the set of logical functions over the binary field, defining a linear Boolean function space. Then associated with any Boolean mapping, the induced Koopman operator is defined as an operator over such Boolean function space. Next, we show that if there exists a set of logical functions that are invariant in the Koopman sense, a Boolean network can be represented by a finite-dimensional linear system. This Koopman perspective for Boolean networks is also extended to controlled Boolean networks.

关键词： Boolean networks Koopman operator

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：