检索结果-内蒙古大学图书馆

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Francesco Di Felice Alberto Remus Stefano Gasperini Benjamin Busam Lionel Ott Federico Tombari Roland Siegwart Carlo Alberto Avizzano Department of Excellence in Robotics & AI Mechanical Intelligence Institute Scuola Superiore Sant’Anna Pisa Italy TUM School of Computation Information and Technology Technical University of Munich Germany Department of Mechanical and Process Engineering Autonomous Systems Lab ETH Zurich Switzerland Google Zurich Switzerland

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Estimating the pose of objects through vision is essential to make robotic platforms interact with the environment. Yet, it presents many challenges, often related to the lack of flexibility and generalizability of state-of-the-art solutions. Diffusion models are a cutting-edge neural architecture transforming 2D and 3D computer vision, outlining remarkable performances in zero-shot novel-view synthesis. Such a use case is particularly intriguing for reconstructing 3D objects. However, localizing objects in unstructured environments is rather unexplored. To this end, this work presents Zero123-6D, the first work to demonstrate the utility of Diffusion Model-based novel-view-synthesizers in enhancing RGB 6D pose estimation at category-level, by integrating them with feature extraction techniques. Novel View Synthesis allows to obtain a coarse pose that is refined through an online optimization method introduced in this work to deal with intra-category geometric differences. In such a way, the outlined method shows reduction in data requirements, removal of the necessity of depth information in zero-shot category-level 6D pose estimation task, and increased performance, quantitatively demonstrated through experiments on the CO3D dataset.

关键词： Computer vision Three-dimensional displays Computational modeling Pose estimation Optimization methods Computer architecture Feature extraction Diffusion models Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Synthesis of Decoherence-Free Modes in Linear Quantum Passive systems via Robust Pole Placement

Synthesis of Decoherence-Free Modes in Linear Quantum Passiv...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Zibo Miao Yu Pan Qing Gao Guangdong Key Laboratory of Intelligent Morphing Mechanisms School of Mechanical Engineering and Automation Adaptive Robotics Harbin Institute of Technology Shenzhen China State Key Laboratory of Industrial Control Technology The Institute of Cyber-Systems and Control College of Control Science and Engineering Zhejiang University Hangzhou China The School of Automation Science and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In this paper we extend our previous research on coherent observer-based pole placement approach to study the synthesis of robust decoherence-free (DF) modes for linear quantum passive systems, which is aimed at preservation of quantum information. In particular, DF modes can be generated by placing the poles on the imaginary axis via a coherent feedback design scheme, and these modes can further be simultaneously made robust against perturbations to the system parameters by minimizing the condition number associated with imaginary poles. We develop explicit algebraic conditions for the existence of such a coherent quantum controller, with the corresponding deign procedure provided. Examples are given to illustrate the process of tuning the DF modes towards perfect robustness via the proposed pole placement technique.

关键词： Perturbation methods Design methodology Quantum optics Robustness Feedback control Closed loop systems Tuning Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Zero123-6D: Zero-shot Novel View Synthesis for RGB Category-level 6D Pose Estimation

arXiv

引用

arXiv 2024年

作者： Felice, Francesco Di Remus, Alberto Gasperini, Stefano Busam, Benjamin Ott, Lionel Tombari, Federico Siegwart, Roland Avizzano, Carlo Alberto Department of Excellence in Robotics & AI Mechanical Intelligence Institute Scuola Superiore Sant’Anna Pisa Italy TUM School of Computation Information and Technology Technical University of Munich Germany Department of Mechanical and Process Engineering Autonomous Systems Lab ETH Zurich Switzerland Google Zurich Switzerland

Estimating the pose of objects through vision is essential to make robotic platforms interact with the environment. Yet, it presents many challenges, often related to the lack of flexibility and generalizability of state-of-the-art solutions. Diffusion models are a cutting-edge neural architecture transforming 2D and 3D computer vision, outlining remarkable performances in zero-shot novel-view synthesis. Such a use case is particularly intriguing for reconstructing 3D objects. However, localizing objects in unstructured environments is rather unexplored. To this end, this work presents Zero123-6D, the first work to demonstrate the utility of Diffusion Model-based novel-view-synthesizers in enhancing RGB 6D pose estimation at category-level, by integrating them with feature extraction techniques. Novel View Synthesis allows to obtain a coarse pose that is refined through an online optimization method introduced in this work to deal with intracategory geometric differences. In such a way, the outlined method shows reduction in data requirements, removal of the necessity of depth information in zero-shot category-level 6D pose estimation task, and increased performance, quantitatively demonstrated through experiments on the CO3D dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Robust Stabilization of a Knee Exoskeleton Robot Using an LMI-Based Composite Controller

Robust Stabilization of a Knee Exoskeleton Robot Using an LM...

引用

Indian Control Conference (ICC)

作者： Sahar Jenhani Hassène Gritli Jyotindra Narayan Laboratory of Robotics Informatics and Complex Systems (RISC Lab - LR16ES07) National Engineering School of Tunis University of Tunis El Manar Tunis Tunisia RISC Lab. Higher Institute of Information and Communication Technologies University of Carthage Borj Cedria Tunis Tunisia Department of Mechanical Engineering Thapar Institute of Engineering and Technology Patiala Punjab India Department of Computing Imperial College London UK

ISBN: (数字)9798331517212

ISBN: (纸本)9798331517229

Rehabilitation exoskeleton robots are vital for restoring lower limb functionality in individuals with locomotor disorders. Extensive research has focused on optimizing the control of these robotic systems and make them more stable. However, there is still a considerable gap in developing robust controllers. This work introduces a robust control approach tailored for a one-degree-of-freedom (1-DoF) knee rehabilitation exoskeleton robot. Emphasizing position control, our method addresses challenges such as parameter uncertainties, solid and viscous frictions, external disturbances, and motion constraints. To effectively manage these issues, we propose a composite controller that integrates a linear state-feedback controller and a nonlinear control law. By employing a quadratic Lyapunov function, we derive the expression of the nonlinear controller and establish the LMI conditions required for calculating the matrix gain of the composite controller using two different design methods. To confirm the developed LMI conditions and demonstrate the proposed control method's ability to ensure robust position control of the knee exoskeleton robotic system, simulation results are finally provided.

关键词： Robust control Uncertain systems Limbs Friction Exoskeletons Position control Solids systems simulation Robots Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception

arXiv

引用

arXiv 2023年

作者： Yang, Dingkang Huang, Shuai Xu, Zhi Li, Zhenpeng Wang, Shunli Li, Mingcheng Wang, Yuzheng Liu, Yang Yang, Kun Chen, Zhaoyu Wang, Yan Liu, Jing Zhang, Peixuan Zhai, Peng Zhang, Lihua Academy for Engineering and Technology Fudan University China Institute of Meta-Medical United States Engineering Research Center of AI and Robotics Ministry of Education Shanghai China AI and Unmanned Systems Engineering Research Center of Jilin Province Changchun China Boli Technology Co. Ltd. Changchun China

Driver distraction has become a significant cause of severe traffic accidents over the past decade. Despite the growing development of vision-driven driver monitoring systems, the lack of comprehensive perception datasets restricts road safety and traffic security. In this paper, we present an AssIstive Driving pErception dataset (AIDE) that considers context information both inside and outside the vehicle in naturalistic scenarios. AIDE facilitates holistic driver monitoring through three distinctive characteristics, including multi-view settings of driver and scene, multi-modal annotations of face, body, posture, and gesture, and four pragmatic task designs for driving understanding. To thoroughly explore AIDE, we provide experimental benchmarks on three kinds of baseline frameworks via extensive methods. Moreover, two fusion strategies are introduced to give new insights into learning effective multi-stream/modal representations. We also systematically investigate the importance and rationality of the key components in AIDE and benchmarks. The project link is https://***/ydk122024/AIDE. Copyright © 2023, The Authors. All rights reserved.

关键词： Motor transportation

来源：评论

学校读者我要写书评

暂无评论

Hardware-in-the-Loop Simulation of Vehicle-Manipulator systems for Physical Interaction Tasks

Hardware-in-the-Loop Simulation of Vehicle-Manipulator Syste...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Hemjyoti Das Bjørn Kåre Sæbø Kristin Y. Pettersen Christian Ott Faculty of Electrical Engineering and Information Technology Automation and Control Institute (ACIN) Technical University of Vienna TU Wien Vienna Austria Department of Engineering Cybernetics Centre for Autonomous Marine Operations and Systems (NTNU AMOS) NTNU Norwegian University of Science and Technology Trondheim Norway German Aerospace Center Institute of Robotics and Mechatronics Wessling Germany

Hardware-in-the-loop simulation (HILS) allows a more realistic evaluation of control approaches than what is possible with pure software simulations, but without the actual complexity of the complete system. This is important for some complex systems such as orbital robots, where testing of the system is typically not possible after its launch, and an on-ground replica is used to validate the performance of such a system. In this article, an impedance-matching approach is presented to match the end-effector dynamics of a fixed-base robot manipulator with that of a target vehicle-manipulator system (VMS), while taking into account the redundant nullspace dynamics in a connected real-time simulation framework. This approach ensures that the forces and torques exerted by the system on the environment matches with that of the simulated system. The contact wrenches used in our approach are not obtained from numerical simulations, but rather from real physical interaction, which is one of the main advantages of our approach. The effectiveness of our method is validated by demonstrating various physical interaction tasks with the environment, using a suspended aerial manipulator as the target system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of Data Fusion Techniques and Adaptive Control for Mobile Robot Localization

Experimental Evaluation of Data Fusion Techniques and Adapti...

引用

International Carpathian Control Conference (ICCC)

作者： Wolmar Araújo Neto Daniel Khede Dourado Villa Mário Sarcinelli-Filho Murillo Ferreira Dos Santos José Lima Ana Isabel Pereira Maurício Herche Fófano De Morais Paolo Mercorelli Department of Electrical Engineering Federal University of Vitória (UFES) Vitória Brazil Department of Electroelectronics CEFET-MG Leopoldina Brasil IPB Research Centre in Digitalization and Intelligent Robotics (CeDRI) Bragança Portugal Institute for Production Technology and Systems Leuphana University of Lüneburg Lüneburg Germany

ISBN: (数字)9798331501273

ISBN: (纸本)9798331501280

This study presents an approach to improving the localization of mobile robots in a controlled test environment through sensor fusion. Currently, the position of the ground robot (Unmanned Ground Vehicle (UGV) P3DX) can be estimated using an optimization algorithm or another technique based on a previously known map. In contrast, the aerial robot (Unmanned Aerial Vehicle (UAV) Bebop Parrot 2) can determine its relative position by detecting a marker on the ground robot using the Robot Operating System (ROS) WhyCon package. However, ambiguities or disturbances may compromise the accuracy of the robots’ localization. To mitigate these limitations, Ultra-WideBand (UWB) sensors were incorporated into the system, enabling a more robust data fusion by integrating information from multiple sensors. Additionally, a filter was applied to reduce the impact of high-frequency noise on position estimation. Accurate localization test data were used to construct a simulated scenario and analyze the performance of the proposed approach. The simulation results demonstrate that sensor fusion, combined with noise filtering, significantly improves localization accuracy, making the approach promising for applications in mobile robot navigation.

关键词： Location awareness Accuracy Three-dimensional displays Navigation Noise Data integration Sensor fusion Robot sensing systems Autonomous aerial vehicles Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Reduced etch lag and high aspect ratios by deep reactive ion etching (DRIE)

arXiv

引用

arXiv 2021年

作者： Gerlt, Michael S. Läubli, Nino F. Manser, Michel Nelson, Bradley J. Dual, Jürg Department of Mechanical and Process Engineering Institute for Mechanical Systems Zurich8092 Switzerland Department of Mechanical and Process Engineering Institute of Robotics and Intelligent Systems Zurich8092 Switzerland

Deep reactive ion etching (DRIE) with the Bosch process is one of the key procedures used to manufacture micron-sized structures for MEMS and microfluidic applications in silicon and, hence, of increasing importance for miniaturization in biomedical research. While guaranteeing high aspect ratio structures and providing high design flexibility, the etching procedure suffers from reactive ion etching lag and often relies on complex oxide masks to enable deep etching. In this work, we introduce an optimized Bosch process that reduces the etch lag to below 1.5 %. Furthermore, we improved a three-step Bosch process, allowing the fabrication of structures with 6 µm thickness at depths up to 180 µm while maintaining their stability. © 2021, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Logarithmic Sliding-Mode Control for High-Precision Rigid-Body Attitude Tracking

Logarithmic Sliding-Mode Control for High-Precision Rigid-Bo...

引用

Annual Conference of Industrial Electronics Society

作者： Hanlin Dong Xuebo Yang Zhongbo Chen Xiyao Liu School of Automation Northwestern Polytechnical University Xi'an China Research Institute of Intelligent Control Systems Harbin Institute of Technology Harbin China College of Control Science and Engineering Bohai University Jinzhou China Research Center for Intelligent Robotics Northwestern Polytechnical University Xi'an China

The problem of high-precision attitude tracking is studied in this paper under model uncertainty and external disturbance risk. First of all, the kinematics and dynamics model of rigid body is derived based on the quaternion theory. Then, a standard logarithmic sliding-mode function is constructed using the attitude quaternion and its derivatives of the rigid spacecraft, and the corresponding logarithmic sliding-mode controller is also derived. Finally, the stability of the controlled closed-loop system is demonstrated. Consistenting with theoretical proof, the numerical simulation results showed that the controlled rigid body can quickly track its desired attitude command, even if there are model uncertainty and external disturbance risks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vertical Federated Learning with Missing Features During Training and Inference

arXiv

引用

arXiv 2024年

作者： Valdeira, Pedro Wang, Shiqiang Chi, Yuejie CMU IST United States IBM Research United States Department of Electrical and Computer Engineering Carnegie Mellon University United States Institute for Systems and Robotics Instituto Superior Técnico Portugal IBM T. J. Watson Research Center United States

Vertical federated learning trains models from feature-partitioned datasets across multiple clients, who collaborate without sharing their local data. Standard approaches assume that all feature partitions are available during both training and inference. Yet, in practice, this assumption rarely holds, as for many samples only a subset of the clients observe their partition. However, not utilizing incomplete samples during training harms generalization, and not supporting them during inference limits the utility of the model. Moreover, if any client leaves the federation after training, its partition becomes unavailable, rendering the learned model unusable. Missing feature blocks are therefore a key challenge limiting the applicability of vertical federated learning in real-world scenarios. To address this, we propose LASER-VFL, a vertical federated learning method for efficient training and inference of split neural network-based models that is capable of handling arbitrary sets of partitions. Our approach is simple yet effective, relying on the strategic sharing of model parameters and on task-sampling to train a family of predictors. We show that LASER-VFL achieves a O(1/√T) convergence rate for nonconvex objectives in general, O(1/T) for sufficiently large batch sizes, and linear convergence under the Polyak-Lojasiewicz inequality. Numerical experiments show improved performance of LASER-VFL over the baselines. Remarkably, this is the case even in the absence of missing features. For example, for CIFAR-100, we see an improvement in accuracy of 21.4% when each of four feature blocks is observed with a probability of 0.5 and of 12.2% when all features are observed. © 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

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：