检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2023年第1期24卷 3762-3828页

作者： Xi Wang Zhipeng Tu Yiguang Hong Yingyi Wu Guodong Shi Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing P. R. China and Australian Center for Robotics School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney NSW Australia Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai P. R. China Department of Mathematics University of Chinese Academy of Sciences Beijing P. R. China Australian Center for Robotics School of Aerospace Mechanical and Mechatronic Engineering The University of Sydney NSW Australia

Online optimization has witnessed a massive surge of research attention in recent years. In this paper, we propose online gradient descent and online bandit algorithms over Riemannian manifolds in full information and bandit feedback settings respectively, for both geodesically convex and strongly geodesically convex functions. We establish a series of upper bounds on the regrets for the proposed algorithms over Hadamard manifolds. We also find a universal lower bound for achievable regret on Hadamard manifolds. Our analysis shows how time horizon, dimension, and sectional curvature bounds have impact on the regret bounds. When the manifold permits positive sectional curvature, we prove similar regret bound can be established by handling non-constrictive project maps. In addition, numerical studies on problems defined on symmetric positive definite matrix manifold, hyperbolic spaces, and Grassmann manifolds are provided to validate our theoretical findings, using synthetic and real-world data.

关键词： online optimization Riemannian manifolds Riemannian optimization gradient estimation Fréchet mean

来源：评论

学校读者我要写书评

暂无评论

基于自解耦三明治结构的横向运动栅场效应晶体管MEMS微力传感器

引用

Engineering 2023年第2期21卷 61-74,M0004页

作者：高文迪乔智霞韩香广王小章 Adnan Shakoor 刘存朗卢德江杨萍赵立波王永录王久洪蒋庄德孙东 State Key Laboratory for Manufacturing Systems Engineering International Joint Laboratory for Micro/Nano Manufacturing and Measurement TechnologiesOverseas Expertise Introduction Center for Micro/Nano Manufacturing and Nano Measurement Technologies Discipline InnovationXi’an Jiaotong University(Yantai)Research Institute for Intelligent Sensing Technology and SystemSchool of Mechanical EngineeringXi’an Jiaotong UniversityXi’an 710049China Shandong Laboratory of Yantai Advanced Materials and Green Manufacturing Yantai 265503China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of TechnologyBeijing 100081China State Key Laboratory of Robotics and Systems Harbin Institute of TechnologyHarbin 150006China Eleventh Research Institute Sixth Academy of China Aerospace Science and Technology Co.Xi’an 710100China Department of Control and Instrumentation Engineering King Fahd University of Petroleum and MineralsDhahran 31261Saudi Arabia Department of Biomedical Engineering City University of Hong KongHong Kong 999077China

本文介绍了一种基于横向可移动栅极场效应晶体管(LMGFET)的新型微型力传感器的开发。提出了一种精确的电气模型,用于小型LMGFET器件的性能评估,与以前的模型相比,其精度有所提高。采用了一种新型三明治结构,该结构由一个金交叉解耦栅阵... 详细信息

本文介绍了一种基于横向可移动栅极场效应晶体管(LMGFET)的新型微型力传感器的开发。提出了一种精确的电气模型,用于小型LMGFET器件的性能评估,与以前的模型相比,其精度有所提高。采用了一种新型三明治结构,该结构由一个金交叉解耦栅阵列层和两个软光阻层SU-8组成。通过所提出的双差分传感结构,LMGFET横向工作在垂直干扰下的输出电流被大大消除,所提出传感器的相对输出误差从4.53%(传统差分结构)降低到0.01%。提出了一种实用的传感器制造工艺,并对其进行了模拟。基于LMGFET的力传感器的灵敏度为4.65μA·nN^(-1),可与垂直可移动栅极场效应晶体管(VMGFET)器件相媲美,但非线性度提高了0.78%,测量范围扩大了±5.10μN。这些分析为LMGFET器件的电气和结构参数提供了全面的设计优化,并证明了所提出的传感器在生物医学显微操作应用中具有良好的力传感潜力。

关键词：力传感器场效应晶体管横向运动三明治结构电气模型显微操作非线性度双差分

来源：评论

学校读者我要写书评

暂无评论

Distributed Computation of Source, Target, and Mixed Strongly Connected Components in Multi-agent systems 16th

Distributed Computation of Source, Target, and Mixed Stron...

引用

16th APCA International Conference on Automatic Control and Soft Computing, CONTROLO 2024

作者： Ramos, Guilherme Pequito, Sérgio Department of Computer Science and Engineering Instituto Superior Técnico University of Lisbon Lisbon1049-001 Portugal Instituto de Telecomunicações Lisbon1049-001 Portugal Department of Electrical and Computer Engineering Instituto Superior Técnico University of Lisbon Lisbon1049-001 Portugal Institute for Systems and Robotics Instituto Superior Técnico University of Lisbon Lisbon1049-001 Portugal

ISBN: (纸本)9783031817236

Strongly Connected Components (SCCs) play a crucial role in understanding the structural properties of directed graphs, with a plethora of applications across various domains including engineering, computer science and social sciences. In this paper, we propose a method for computing both the source SCCs and target SCCs in a distributed fashion. Our method leverages the decentralized nature of distributed systems to efficiently identify SCCs within large-scale graphs. We illustrate the proposed methods with examples. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Distributed computer systems

来源：评论

学校读者我要写书评

暂无评论

Development of a Robotic Hand Glove System for Secure Grasp with AI Wireless Sensor Data

Development of a Robotic Hand Glove System for Secure Grasp ...

引用

IEEE International Conference on Mechatronics and Automation

作者： Ahmed Almassri Ken’Ichi Koyanagi Chikamune Wada Keiichi Horio Wan Zuha Wan Hasan Department of Intelligent Robotics Toyama Prefectural University 5180 Kurokawa Imizu Toyama Japan Israa Institute for Scientific Research (IISR) Israa University Gaza Palestine Department of Life Science and Systems Engineering Kyushu Institute of Technology 2-4 Hibikino Kitakyushu Fukuoka Japan Department of Electrical and Electronic Universiti Putra Malaysia Selangor Malaysia

Robotic Hand glove is one of the most commonly used technique in the rehabilitation systems. In this paper, we developed a robotic hand system with a proposed sensing mechanism-based AI algorithm, which can acquire grasping forces from human fingers. It is composed of five low-cost force sensors attached to the glove’s fingertips and wireless data logger. Several experiments including grasping a plastic bottle and squeezing a tennis ball are implemented to verify the efficiency of the proposed system using the developed glove. As a result, it accurately estimates the forces applied by each finger with the aim of achieving a secure grasp comparison with conventional methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Proprioception and Tail Control Enable Extreme Terrain Traversal by Quadruped Robots

arXiv

引用

arXiv 2023年

作者： Yang, Yanhao Norby, Joseph Yim, Justin K. Johnson, Aaron M. Department of Mechanical Engineering Carnegie Mellon University PittsburghPA15213 United States Collaborative Robotics and Intelligent Systems Institute Oregon State University CorvallisOR97331 United States Department of Mechanical Science and Engineering University of Illinois Urbana-Champaign UrbanaIL61801 United States

Legged robots leverage ground contacts and the reaction forces they provide to achieve agile locomotion. However, uncertainty coupled with contact discontinuities can lead to failure, especially in real-world environments with unexpected height variations such as rocky hills or curbs. To enable dynamic traversal of extreme terrain, this work introduces 1) a proprioception-based gait planner for estimating unknown hybrid events due to elevation changes and responding by modifying contact schedules and planned footholds online, and 2) a two-degree-of-freedom tail for improving contact-independent control and a corresponding decoupled control scheme for better versatility and efficiency. Simulation results show that the gait planner significantly improves stability under unforeseen terrain height changes compared to methods that assume fixed contact schedules and footholds. Further, tests have shown that the tail is particularly effective at maintaining stability when encountering a terrain change with an initial angular disturbance. The results show that these approaches work synergistically to stabilize locomotion with elevation changes up to 1.5 times the leg length and tilted initial states. Copyright © 2023, The Authors. All rights reserved.

关键词： Landforms

来源：评论

学校读者我要写书评

暂无评论

Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models

arXiv

引用

arXiv 2023年

作者： Schumacher, Pierre Geijtenbeek, Thomas Caggiano, Vittorio Kumar, Vikash Schmitt, Syn Martius, Georg Haeufle, Daniel F.B. Max-Planck Institute for Intelligent Systems Tübingen Germany Hertie Institute for Clinical Brain Research Center for Integrative Neuroscience Tübingen Germany Goatstream Netherlands Meta AI New York United States Institute for Modelling and Simulation of Biomechanical Systems University of Stuttgart Germany Department of Computer Science University of Tübingen Germany Institute of Computer Engineering Heidelberg University Germany

Humans excel at robust bipedal walking in complex natural environments. In each step, they adequately tune the interaction of biomechanical muscle dynamics and neuronal signals to be robust against uncertainties in ground conditions. However, it is still not fully understood how the nervous system resolves the musculoskeletal redundancy to solve the multiobjective control problem considering stability, robustness, and energy efficiency. In computer simulations, energy minimization has been shown to be a successful optimization target, reproducing natural walking with trajectory optimization or reflex-based control methods. However, these methods focus on particular motions at a time and the resulting controllers are limited when compensating for perturbations. In robotics, reinforcement learning (RL) methods recently achieved highly stable (and efficient) locomotion on quadruped systems, but the generation of human-like walking with bipedal biomechanical models has required extensive use of expert data sets. This strong reliance on demonstrations often results in brittle policies and limits the application to new behaviors, especially considering the potential variety of movements for high-dimensional musculoskeletal models in 3D. Achieving natural locomotion with RL without sacrificing its incredible robustness might pave the way for a novel approach to studying human walking in complex natural environments. Copyright © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Emergence of Natural and Robust Bipedal Walking by Learning to Control Up to Ninety Muscles from Biologically Plausible Objectives

SSRN

引用

SSRN 2023年

Humans show unparalleled ability when maneuvering diverse terrains. While motor control researchers have studied these skills in simulation for a long time, most control approaches are only able to generate single motions. Recently, reinforcement learning~(RL) has shown great promise in the development of robust controllers capable of generating complex behaviors. The application to highly complex biomechanical models was, however, only possible under extensive use of motion capture data, limiting the abilities of the resulting agents. In this paper, we demonstrate that the combination of a recent RL algorithm with a biologically plausible reward function is capable of learning controllers for 4 different musculoskeletal human models and achieves bipedal motion with up to 90 muscles without demonstrations. Our controllers are robust enough to generalize to diverse and unseen terrains, while only a single objective function is needed for training. We validate our findings on 4 models in 2 different simulators and 2 different tasks, walking and running. We see this as a first step for the motor control, biomechanics, and rehabilitation communities to generate highly complex human movements with RL, without needing to collect large amounts of experimental data or limiting themselves to simple models that are not representative of the diverse skills that human beings exhibit every day. © 2023, The Authors. All rights reserved.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

Realizing Emotional Interactions to Learn User Experience and Guide Energy Optimization for Mobile Architectures 22

Realizing Emotional Interactions to Learn User Experience an...

引用

Proceedings of the 55th Annual IEEE/ACM International Symposium on Microarchitecture

作者： Xueliang Li Zhuobin Shi Junyang Chen Yepang Liu National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China Research Institute of Trustworthy Autonomous Systems Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation and Department of Computer Science and Engineering Southern University of Science and Technology China

ISBN: (纸本)9781665462723

In the age of AI, mobile architectures such as smartphones are still "cold machines"; machines do not feel. If the architecture is able to feel users' feelings and runtime user experience (UX), it will accordingly adapt performance/energy to find the optimal system-operating state that consumes the least energy to satisfy users. In this paper, we will utilize users' facial expressions (FEs) to learn their runtime UX. We know that FEs are the natural and direct way for humans to convey their emotions and feelings. Our study reveals that FEs also reflect UX. Our research for the first time quantifies the link between FEs and UX. Leveraging this link, the architecture will be able to use the front camera to see FEs and feel users' UX. Based on UX, the architecture can appropriately provision computing resources. We propose Vi-energy system to realize the above idea. Our evaluation shows that Vi-energy reduces energy consumption by 52.9% at maximum and secures UX.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RDA: An Accelerated Collision Free Motion Planner for Autonomous Navigation in Cluttered Environments

arXiv

引用

arXiv 2022年

作者： Han, Ruihua Wang, Shuai Wang, Shuaijun Zhang, Zeqing Zhang, Qianru Eldar, Yonina C. Hao, Qi Pan, Jia The Department of Computer Science and Engineering Southern University of Science and Technology Guangdong Shenzhen China The Department of Computer Science The University of Hong Kong Hong Kong Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China The Department of Computer Science and Engineering Harbin Institute of Technology Guangdong Shenzhen China The Weizmann Institute of Science Rehovot Israel The Department of Computer Science and Engineering The Shenzhen Key Laboratory of Robotics and Computer Vision The Sifakis Research Institute for Trustworthy Autonomous Systems Southern University of Science and Technology Guangdong Shenzhen China

Autonomous motion planning is challenging in multi-obstacle environments due to nonconvex collision avoidance constraints. Directly applying numerical solvers to these nonconvex formulations fails to exploit the constraint structures, resulting in excessive computation time. In this paper, we present an accelerated collision-free motion planner, namely regularized dual alternating direction method of multipliers (RDADMM or RDA for short), for the model predictive control (MPC) based motion planning problem. The proposed RDA addresses nonconvex motion planning via solving a smooth biconvex reformulation via duality and allows the collision avoidance constraints to be computed in parallel for each obstacle to reduce computation time significantly. We validate the performance of the RDA planner through path-tracking experiments with car-like robots in both simulation and real-world settings. Experimental results show that the proposed method generates smooth collision-free trajectories with less computation time compared with other benchmarks and performs robustly in cluttered environments. The source code is available at https://***/hanruihua/ RDA_planner. Copyright © 2022, The Authors. All rights reserved.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Novel Surface Design of Deployable Reflector Antenna Based on Polar Scissor Structures

引用

Chinese Journal of Mechanical Engineering 2020年第5期33卷 4-18页

作者： Pengyuan Zhao Jinguo Liu Chenchen Wu Yangmin Li Keli Chen State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of ScienceShenyang 110016China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of SciencesShenyang 110169China University of Chinese Academy of Sciences Beijing 100049China Department of Industrial and Systems Engineering The Hong Kong Polytechnic UniversityHong Kong 999077China

Space-deployable mechanisms can be used as supporting structures for large-diameter antennas in space *** study proposes a novel method for constructing the surface design of space reflector antennas based on polar scissor *** concurrency and deployability equations of the space scissor unit with definite surface constraints are derived using the rod and vector *** equations of the spatial transformation for space n-edge polar scissor units are summarized.A new closed-loop deployable structure,called the polar scissor deployable antenna(PSDA),is designed by combining planar polar scissor units with spatial polar scissor *** overconstrained problem is solved by releasing the curve constraint that locates at the end-point of the planar scissor *** simulation and error analysis are *** results show that the PSDA can effectively fit the paraboloid of ***,deployment experiments verify the validity and feasibility of the proposed design method,which provides a new idea for the construction of large space-reflector antennas.

关键词： Deployable structures Polar scissor unit Reflector antenna Surface design

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：