检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Lundell, Jens Verdoja, Francesco Le, Tran Nguyen Mousavian, Arsalan Fox, Dieter Kyrki, Ville Intelligent Robotics Group Department of Electrical Engineering and Automation School of Electrical Engineering Aalto University Finland KTH Royal Institute of Technology Sweden NVIDIA Corporation United States Paul G. Allen School of Computer Science & Engineering University of Washington Seattle United States

Most state-of-the-art data-driven grasp sampling methods propose stable and collision-free grasps uniformly on the target object. For bin-picking, executing any of those reachable grasps is sufficient. However, for completing specific tasks, such as squeezing out liquid from a bottle, we want the grasp to be on a specific part of the object’s body while avoiding other locations, such as the cap. This work presents a generative grasp sampling network, VCGS, capable of constrained 6-Degrees of Freedom (DoF) grasp sampling. In addition, we also curate a new dataset designed to train and evaluate methods for constrained grasping. The new dataset, called CONG, consists of over 14 million training samples of synthetically rendered point clouds and grasps at random target areas on 2889 objects. VCGS is benchmarked against GraspNet, a state-of-the-art unconstrained grasp sampler, in simulation and on a real robot. The results demonstrate that VCGS achieves a 10–15% higher grasp success rate than the baseline while being 2–3 times as sample efficient. Supplementary material is available on our project website. Copyright © 2023, The Authors. All rights reserved.

关键词： Bottles

来源：评论

学校读者我要写书评

暂无评论

Ethical Decision-making for Autonomous Driving based on LSTM Trajectory Prediction Network

引用

Procedia Computer Science 2023年 226卷 134-140页

作者： Wen Wei Jiankun Wang Shenzhen Key Laboratory of Robotics Perception and Intelligence Shenzhen China Department of Electronic and Electrical Engineering Southern University of Science and Technology Shenzhen China Jiaxing Research Institute Southern University of Science and Technology Jiaxing China

The development of autonomous vehicles has brought a great impact and changes to the transportation industry, offering numerous benefits in terms of safety and efficiency. How ever, one of the key challenges that autonomous driving faces is how to make ethical decisions in complex situations. To address this issue, in this article, a novel trajectory prediction method is proposed to achieve ethical decision-making for autonomous driving. Ethical considerations are integrated into the decision-making process of autonomous vehicles by quantifying the utility principle and incorporating them into mathematical formulas. Furthermore, trajectory prediction is optimized using LSTM network with an attention module, resulting in improved accuracy and reliability in trajectory planning and selection. Through extensive simulation experiments, we demonstrate the effectiveness of the proposed method in making ethical decisions and selecting optimal trajectories.

关键词： Autonomous Vehicles Decision-making Trajectory Prediction

来源：评论

学校读者我要写书评

暂无评论

FogROS2-FT: Fault Tolerant Cloud robotics

FogROS2-FT: Fault Tolerant Cloud Robotics

引用

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

作者： Kaiyuan Chen Kush Hari Trinity Chung Michael Wang Nan Tian Christian Juette Jeffrey Ichnowski Liu Ren John Kubiatowicz Ion Stoica Ken Goldberg Department of Electrical Engineering and Computer Science University of California Berkeley CA USA Robert Bosch Research and Technology Center North America Sunnyvale CA USA Robotics Institute Carnegie Mellon University Department of Industrial Engineering and Operations Research University of California Berkeley CA USA

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Cloud robotics enables robots to offload complex computational tasks to cloud servers for performance and ease of management. However, cloud compute can be costly, cloud services can suffer occasional downtime, and connectivity between the robot and cloud can be prone to variations in network Quality-of-Service (QoS). We present FogROS2-FT (Fault Tolerant) to mitigate these issues by introducing a multi-cloud extension that automatically replicates independent stateless robotic services, routes requests to these replicas, and directs the first response back. With replication, robots can still benefit from cloud computations even when a cloud service provider is down or there is low QoS. Additionally, many cloud computing providers offer low-cost "spot" computing instances that may shutdown unpredictably. Normally, these low-cost instances would be inappropriate for cloud robotics, but the fault tolerance nature of FogROS2-FT allows them to be used reliably. We demonstrate FogROS2-FT fault tolerance capabilities in 3 cloud-robotics scenarios in simulation (visual object detection, semantic segmentation, motion planning) and 1 physical robot experiment (scan-pick-and-place). Running on the same hardware specification, FogROS2-FT achieves motion planning with up to 2.2x cost reduction and up to a 5.53x reduction on 99 Percentile (P99) long-tail latency. FogROS2-FT reduces the P99 long-tail latency of object detection and semantic segmentation by 2.0x and 2.1x, respectively, under network slowdown and resource contention. Videos and code are available at https://***/view/fogros2-ft.

关键词： Fault tolerance Heavily-tailed distribution Semantic segmentation Fault tolerant systems Quality of service Object detection Planning Servers Robots Cloud robotics

来源：评论

学校读者我要写书评

暂无评论

Switching-Like Event-Based Formation Control for Multi-Agent Systems Against Denial of Service Attacks

引用

IEEE Transactions on Control of Network Systems 2025年

作者： Ru, Tingting Cai, Chenxiao Lin, Hong Rudas, Imre Shi, Peng Nanjing University of Science and Technology School of Automation Nanjing210094 China Shenzhen Polytechnic University Institute of Intelligence Science and Engineering Shenzhen518055 China University Research Innovation and Service Center Óbuda University Antal Bejczy Center for Intelligent Robotics Budapest1034 Hungary University of Adelaide School of Electrical and Mechanical Engineering AdelaideSA5005 Australia

This paper studies formation control for multi-agent systems in the presence of denial-of-service (DoS) attacks. The challenge is to address secure formation tracking and communication bandwidth-saving issues simultaneously. To tackle this, we propose a switching- like event-triggered mechanism that reduces excessive bandwidth consumption during interactions among multiple followers under DoS attacks. The triggering condition is allowed to be switched during the intervals when attacks are activated, ensuring that triggering can normally occur throughout the overall time interval by introducing an auxiliary variable depending on the success of the latest trigger moment. Based on this approach, we construct an event-based time-varying formation control scheme. Additionally, we establish sufficient conditions that reveal the relationship between exponential stability and the frequency/duration of the DoS attacks. Unlike other single-leader methods, a significant feature of the formation control scheme is its ability to achieve the desired formation tracking for multi-agent systems with multiple leaders. Finally, the validity of the proposed method is demonstrated through simulation and experimental results. © 2014 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

An Economic Dispatch Method for Power System Based on Distributed Mutual-Fed-Consensus

An Economic Dispatch Method for Power System Based on Distri...

引用

International Conference on Advanced Mechatronic Systems (ICAMechS)

作者： Xiangjun Li Panpan Zhang Bo Li National Key Laboratory of Renewable Energy Grid-Integration Energy Storage and Electrical Engineering Department China Electric Power Research Institute Beijing China School of Automation Engineering Northeast Electric Power University China

ISBN: (数字)9798350366204

ISBN: (纸本)9798350366211

This paper presents a distributed algorithm based on mutual feedback mechanism for economic dispatch problem of power system. In such a mutual feedback mechanism, the average of the load demand and power generated are estimated, respectively. Simulation results on standard test cases show the convergence and effectiveness of the proposed algorithm.

关键词： Economics Mechatronics Simulation Numerical simulation Generators Power systems Distributed algorithms Standards Power generation Convergence

来源：评论

学校读者我要写书评

暂无评论

State Estimation Using a Network of Observers for a Class of Nonlinear Systems with Communication Delay

State Estimation Using a Network of Observers for a Class of...

引用

European Control Conference (ECC)

作者： Ruixuan Zhao Guitao Yang Peng Li Thomas Parisini Boli Chen Department of Electronic and Electrical Engineering University College London London UK Department of Electrical and Electronic Engineering Imperial College London London UK KIOS Research and Innovation Center of Excellence University of Cyprus Cyprus School of Mechanical Engineering and Automation at Harbin Institute of Technology Shenzhen China Department of Engineering and Architecture University of Trieste Trieste Italy

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

Distributed observer design is critical for large-scale systems to collectively estimate the system state via networked sensors. In this paper, we propose a novel distributed observer scheme for estimating the states of a class of nonlinear systems. Unknown and time-varying communication delays are considered due to ubiquitous network latency when information is exchanged among observer nodes. Based on the Lyapunov stability criterion, a set of linear matrix inequalities (LMIs) are derived for the design of observer gains, which ensure asymptotic convergence of the state estimates to the true state trajectories in the presence of communication delays. Simulation results are given to validate the effectiveness of the proposed method and its advantage over a recent approach without considering communication delays.

关键词： Simulation Process control Observers Sensor systems Delays Large-scale systems Trajectory

来源：评论

学校读者我要写书评

暂无评论

THÖR-Magni: Comparative Analysis of Deep Learning Models for Role-conditioned Human Mtion Prediction

THÖR-Magni: Comparative Analysis of Deep Learning Models fo...

引用

International Conference on Computer Vision Workshops (ICCV Workshops)

作者： Tiago Rodrigues de Almeida Andrey Rudenko Tim Schreiter Yufei Zhu Eduardo Gutierrez Maestro Lucas Morillo-Mendez Tomasz P. Kucner Oscar Martinez Mozos Martin Magnusson Luigi Palmieri Kai O. Arras Achim J. Lilienthal Örebro University Sweden Robert Bosch GmbH Corporate Research Stuttgart Germany Department of Electrical Engineering and Automation Mobile Robotics Group Aalto University Finland FCAI Finnish Center for Artificial Intelligence Finland

Autonomous systems, that need to operate in human environments and interact with the users, rely on understanding and anticipating human activity and motion. Among the many factors which influence human motion, semantic attributes, such as the roles and ongoing activities of the detected people, provide a powerful cue on their future motion, actions, and intentions. In this work we adapt several popular deep learning models for trajectory prediction with labels corresponding to the roles of the people. To this end we use the novel THÖR-Magni dataset, which captures human activity in industrial settings and includes the relevant semantic labels for people who navigate complex environments, interact with objects and robots, work alone and in groups. In qualitative and quantitative experiments we show that the role-conditioned LSTM, Transformer, GAN and VAE methods can effectively incorporate the semantic categories, better capture the underlying input distribution and therefore produce more accurate motion predictions in terms of Top-K ADE/FDE and log-likelihood metrics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of dual-mode mobile LiDAR measurement system

Design and implementation of dual-mode mobile LiDAR measurem...

引用

2022 Applied Optics and Photonics China: Advanced Laser Technology and Applications, AOPC 2022

作者： Xian, Ren Ming, Guo Cai, Chen Yuquan, Zhou Dengke, Li Peng, Cheng School of Surveying and Urban Spatial Information Beijing University of Civiling Engineering And Architecture Beijing102616 China School of Automation and Electrical Engineering Zhejiang University of Science and Technology Zhejiang310023 China Key Institute of Robotics Industry of Zhejiang Province Zhejiang310023 China Engineering Research Center of Ministry of Education for Representative Building and Ancient Building Data Beijing100044 China Key Laboratory of National Surveying and Mapping Geographic Information Bureau of Modern City Surveying and Mapping Beijing100044 China

ISBN: (纸本)9781510662223

Most of the existing mobile LiDAR measurement systems adopt GNSS/INS combination method. This method requires GNSS signal to correct IMU positioning and attitude determination continuously. When GNSS signal is not received, IMU positioning and attitude determination accuracy rapidly increases from centimeter level to sub-meter level or even meter level. In order to solve the positioning defect of mobile measurement system when there is no GNSS signal, In this paper, a dual-mode mobile LiDAR measurement system integrating GNSS/INS positioning and INS/odometer positioning is proposed. It mainly judges whether there is GNSS signal input through the time synchronization controller and automatically switches between the two mode When there is GNSS signal, GNSS/INS positioning is used. When there is no GNSS signal, it automatically switches to INS/odometer positioning mode When there is no GNSS signal, The time synchronization controller simulate GNSS signal, collects its own high-precision quartz crystal oscillator to record time, and converts it into NEMA standard time signal and PPS signal for time synchronization of each sensor. The dual-mode mobile LiDAR measurement system can not only be used in highway measurement, but also solve the pose error in the case of GNSS unlocking such as subway and tunnel. It can be applied to point cloud measurement in a variety of scenes. © 2023 SPIE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

An EMG-Based Objective Function for Human-in-the-Loop Optimization

An EMG-Based Objective Function for Human-in-the-Loop Optimi...

引用

IEEE International Conference on Rehabilitation robotics (ICORR)

作者： María Alejandra Díaz Sander De Bock Philipp Beckerle Jan Babič Tom Verstraten Kevin De Pauw Human Physiology and Sports Physiotherapy Research Group Brussels Human Robotic Research Center Vrije Universiteit Brussel Brussels Belgium Department of Electrical Engineering and the Department of Artificial Intelligence in Biomedical Engineering Institute of Autonomous Systems and Mechatronics Friedrich-Alexander-Universität Erlangen-Nürnberg Erlangen Germany Department of Automation Biocybernetics and Robotics Laboratory for Neuromechanics and Biorobotics Jožef Stefan Institute Ljubljana Slovenia Faculty of Electrical Engineering University of Ljubljana Ljubljana Slovenia Robotics and Multibody Mechanics Research Group Vrije Universiteit Brussel and Flanders Make Brussels Belgium

Advancements in wearable robots aim to improve the users' motion, performance, and comfort by optimizing, mainly, energetic cost (EC). However, EC is a noisy measurement with a physiological delayed response that requires long evaluation periods and wearing an uncomfortable mask. This study aims to estimate and minimize an EMG-based objective function that describes the natural energetic expenditure of individuals walking. This objective is assessed by combining multiple electromyography (EMG) variables from the EMG intensity and muscle synergies. To evaluate this objective function simply and repeatedly, we prescribed step frequency (SF) via a metronome and optimized this frequency to minimize muscle activity demands. Further, a linear mixed-effects model was fitted for EC, with the EMG variables as fixed-effects and a random intercept that varies by participant. After the model was fitted to the data, a cubic polynomial was used to identify the optimal SF that reduces the overall EMG-based objective function. Our analysis outlines that the proposed objective function is comparable to the EC during walking, the primary objective function used in human-in-the-loop optimization. Thus, this EMG-based objective function could be potentially used to optimize wearable robots and improve human-robot interaction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Connectivity Determination Algorithm for Complex Directed Networks

引用

IEEE Transactions on Network Science and engineering 2025年

作者： Zhong, Zhiyi Lin, Lin Jiang, Zhihan Yuan, Xin Ngai, Edith Lam, James Kwok, Ka-Wai The University of Hong Kong Department of Computer Science Hong Kong The University of Hong Kong Department of Electrical and Electronic Engineering Pokfulam Hong Kong University of Adelaide School of Electrical and Electronic Engineering AdelaideSA5005 Australia The University of Hong Kong Department of Mechanical Engineering Hong Kong Hku Shenzhen Institute of Research and Innovation Shenzhen518057 China University of Hong Kong Department of Mechanical Engineering Hong Kong The Chinese University of Hong Kong Department of Mechanical and Automation Engineering Hong Kong

Connectivity characterizes the ability of information transmission in systems modeled by complex networks. It is essential to develop an efficient connectivity determination algorithm with low time complexity and minimal storage requirements. To fulfill this need, a connectivity determination algorithm is designed by incorporating Tarjan's algorithm to identify strongly connected components and leveraging a depth-first search idea to traverse the reachability. This algorithm can ascertain strong connectivity, unilateral connectivity, and weak connectivity of complex directed networks. Besides, the accessibility matrix of complex directed networks is computed and visualized through an interface. As this algorithm relies on only two depth-first searches to accomplish connectivity determination tasks, its computational complexity does not exceed O(n2), where n denotes the number of network nodes. Experiments carried out on some specific networks reveal that the probability of network connections decreases with the increasing number of nodes in directed injective graphs, while in Erdos-Rényi graphs, the likelihood of connections increases as the number of nodes increases. Finally, a comparative example and an application example are provided to demonstrate the effectiveness of the algorithm program. © 2013 IEEE.

关键词： Directed graphs

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：