检索结果-内蒙古大学图书馆

IEEE International Workshop on Robot and Human Communication (ROMAN)

作者： Philipp Kratzer Niteesh Balachandra Midlagajni Marc Toussaint Jim Mainprice Machine Learning and Robotics Lab University of Stuttgart Germany Humans to Robots Motions Research Group HRM University of Stuttgart Germany Learning and Intelligent Systems Lab Technical University of Berlin Germany

ISBN: (数字)9781728160757

ISBN: (纸本)9781728160764

Motion prediction in unstructured environments is a difficult problem and is essential for safe and efficient human-robot space sharing and collaboration. In this work, we focus on manipulation movements in environments such as homes, workplaces or restaurants, where the overall task and environment can be leveraged to produce accurate motion prediction. For these cases we propose an algorithmic framework that accounts explicitly for the environment geometry based on a model of affordances and a model of short-term human dynamics both trained on motion capture data. We propose dedicated function networks for graspability and placebility affordances and we make use of a dedicated RNN [1] for short-term motion prediction. The prediction of grasp and placement probability densities are used by a constraint-based trajectory optimizer to produce a full-body motion prediction over the entire horizon. We show by comparing to ground truth data that we achieve similar performance for full-body motion predictions as using oracle grasp and place locations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anticipating Human Intention for Full-Body Motion Prediction in Object Grasping and Placing Tasks

arXiv

引用

arXiv 2020年

作者： Kratzer, Philipp Midlagajni, Niteesh Balachandra Toussaint, Marc Mainprice, Jim Machine Learning and Robotics Lab University of Stuttgart Germany Humans to Robots Motions Research Group HRM University of Stuttgart Germany Learning and Intelligent Systems Lab Technical University of Berlin Germany

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Low-cost Scalable People Tracking System for Human-Robot Collaboration in Industrial Environment

引用

Procedia Manufacturing 2020年 51卷 116-124页

作者： Matteo Terreran Edoardo Lamon Stefano Michieletto Enrico Pagello Intelligent Autonomous Systems Laboratory (IAS-Lab) Dept. of Information Engineering (DEI) University of Padova Padova Italy Robotics and Automation Dept. of Information Engineering Universitä degli Studi di Pisa Pisa Italy

Human-robot collaboration is one of the key elements in the Industry 4.0 revolution, aiming to a close and direct collaboration between robots and human workers to reach higher productivity and improved ergonomics. The first step toward such kind of collaboration in the industrial context is the removal of physical safety barriers usually surrounding standard robotic cells, so that human workers can approach and directly collaborate with robots. Anyway, human safety must be granted avoiding possible collisions with the robot. In this work, we propose the use of a people tracking algorithm to monitor people moving around a robot manipulator and recognize when a person is too close to the robot while performing a task. The system is implemented by a camera network system positioned around the robot workspace, and thoroughly evaluated in different industry-like settings in terms of both tracking accuracy and detection delay.

关键词： People tracking human-robot collaboration low-cost industrial

来源：评论

学校读者我要写书评

暂无评论

A bottom-up paradigm for traffic scene graph representation 9

A bottom-up paradigm for traffic scene graph representation

引用

9th International Conference on Computing and Pattern Recognition, ICCPR 2020

作者： Zhang, Zhixuan Zhang, Chi Liu, Yuehu Su, Yuanqi Li, Ping Zheng, Jinzi School of Software Engineering Xi'An Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'An Jiaotong University Xi'an China Shaanxi Key Lab of Digital Technology and Intelligent Systems Xi'an China School of Computer Science and Technology Xi'An Jiaotong University Xi'an China China Academy of Railway Sciences Corporation Limited Beijing China

ISBN: (纸本)9781450387835

With increasing hardware computing power and model capacity, visual tasks for scene cognitive understanding have attracted more attention, such as visual relationships inference. The scene graph representation formed by a coupling of objects, attributes and relationships nodes displayed by different modalities of information, including original image, foreground things, background stuff and scene attributes, strongly promotes the progress of research area. In this paper, we address the scene graph representation of traffic scenarios for autonomous driving. It should be noted that the universal representation are the specific needs of cognitive understanding of traffic scenes: on the one hand, there is a lack of fine-grained description of key objects and attributes;on the other hand, there are redundant descriptions of objects and relationships. To tackle these problems, we take advantage of the fine-grained instance-level annotation of the traffic scene, proposing a bottom-up representation paradigm. It makes full use of the hierarchical structure of the traffic scene and the sparsity of element classes. In addition, on the basis of the existing methods, we optimize the relationship list of traffic scene graph representation. Moreover, we improve the scene graph annotation methods, proposing a "ground-vision joint location method"to better describe the spatially-distributed visual knowledge. The case analysis showed that compared with existing methods, our paradigm for scene graph can represent more abundant traffic scene information. © 2020 ACM.

关键词： Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Control for gravity compensation in tendon-driven upper limb exosuits

Control for gravity compensation in tendon-driven upper limb...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Anna-Maria Georgarakis Jaeyong Song Peter Wolf Robert Riener Michele Xiloyannis Sensory-Motor Systems (SMS) Lab Institute of Robotics and Intelligent Systems (IRIS) ETH Zurich Switzerland Reharobotics Group Spinal Cord Injury Center Balgrist University Hospital Medical Faculty University of Zurich Switzerland

ISBN: (数字)9781728159072

ISBN: (纸本)9781728159089

Soft wearable robots, or exosuits, area promising technology to assist the upper limb during daily life activities. So far, several exosuit concepts have been proposed, some of which were successfully tested in open-loop control. However, though simple and robust, open-loop control is cumbersome and unintuitive for use in daily life. Here, we closed the control loop on the human-robot interface of the Myoshirt. The Myoshirt is an upper limb exosuit that supports the shoulder joint during functional arm elevation. A direct three controller (DF) as well as an indirect farce controller (IF) were implemented on the Myoshirt to assess their suitability for autonomously tracking human movement. In a preceding testbench analysis, a direct force controller with linear friction compensation (DFF) could be excluded, as linearly compensating friction aggravated the force tracking error in the ramp response (RMSE mean|sd: 32.75|10.95 N) in comparison to the OF controller ramp response (27.61|9.38N). In the same analysis, the IF controller showed substantially better tracking performance (17.12|0.91). In the subsequent movement tracking analysis including five participants (one female), the position tracking error and smoothness (median(RMSI ), median(SPARC)) were similar with the DF (3.9°, -4.3) and lF (3.4°, -4.1) controllers and in an unpowered condition (3.7 , -4.2). However, the force tracking error and smoothness were substantially better when the IF controller (3.41,-4.5) was active than with the DF controller (10.4 N, -6.6). The magnitude response in the Bode analysis indicated that both controllers were obstructing the human movement at higher frequencies, however with 0.75 Hz, the IF controller satisfied the bandwidth requirement for daily life assistance, while the DF controller (0.83 Hz) did not. It can he concluded that the IF controller is most suitable for assisting human movement in daily life with the Myoshirt.

关键词： Shoulder Friction Gravity Tracking Torque Tendons Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Increasing exercise intensity during outside walking training with a wearable robot

Increasing exercise intensity during outside walking trainin...

引用

IEEE/RAS-EMBS International Conference on Biomedical robotics and Biomechatronics (BioRob)

作者： Florian L. Haufe Peter Wolf Jaime E. Duarte Robert Riener Michele Xiloyannis Sensory-Motor Systems Lab Institute of Robotics and Intelligent Systems ETH Zurich Zurich Switzerland Spinal Cord Injury Center University Hospital Balgrist University of Zurich Zurich Switzerland MyoSwiss AG Zurich Switzerland

ISBN: (数字)9781728159072

ISBN: (纸本)9781728159089

For many neuromuscular conditions including spinal cord injury, physical exercise training is a recommended part of treatment. High intensity exercise has been found to more effectively promote ambulatory function than moderate intensity exercise. To reach optimal intensity levels, fully ambulatory individuals can adjust their walking speed. In contrast, individuals with neuromuscular deficits may not be able to walk, or only at slow speeds that elicit an insufficient cardiovascular response. In our case study with one spinal cord injured patient, we investigated if assistance from a wearable robot, the Myosuit, can increase exercise intensity towards more effective training. During outside uphill-walking trials, assistance from the Myosuit allowed the patient to increase his walking speed by 30 % to 0.48 m/s and increased energy expenditure by 17 % compared to not wearing the suit. An analysis of gait kinematics suggests that the Myosuit facilitated faster walking by replacing missing hip extensor function and promoting a more upright posture. The metabolic equivalents (METS) during walking with the Myosuit of 7.15 indicate a consistently high exercise intensity. In contrast, one of two unassisted trials only reached a moderate intensity (METS

关键词： Legged locomotion Hip Knee Training Particle measurements Frequency measurement Atmospheric measurements

来源：评论

学校读者我要写书评

暂无评论

An Improved Chimp Optimization Algorithm for Short-term Hydrothermal Scheduling

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2022年第3期49卷 666页

作者： Chen, Gonggui Wang, Shumin He, Yongsheng Shang, Wanfeng Long, Hongyu Key Laboratory of Industrial Internet of Things and Networked Control Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing University of Posts and Telecommunications Chongqing400065 China State Grid Chongqing Electric Power Company Chongqing400015 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen Shenzhen518055 China Chongqing Key Laboratory of Complex Systems and Bionic Control Chongqing University of Posts and Telecommunications Chongqing400065 China

The short-term hydrothermal scheduling (STHS) is a complex non-linear, non-convex and high-dimensional mathematical optimization problem. Due to the fact that the original chimp optimization algorithm (ChOA) is likely to fall into local optimum and has the disadvantage of low population diversity, an improved chimp optimization algorithm (IChOA) is proposed to solve the STHS problem. Firstly, Logistic-Tent chaotic mapping is employed to initialize the population and increase the population diversity. Then a new nonlinear convergence factor is introduced to make the optimization search process more applicable to STHS problems. Next, particle swarm algorithm (PSO) and gravitational search algorithm (GSA) are combined to enhance the shortcoming and balance the global search ability and local exploration ability of ChOA. Moreover, Cauchy mutation and opposition-based learning strategy are supplemented as perturbation interference when the optimal position is not updated to improve the ability to leap out of the local optimum. Finally, a graded optimization strategy is adopted for the constraint handing of dynamic reservoir balance and thermal power balance. Three standard hydrothermal power systems are utilized to verify the practicability and validity of the proposed method. Results of simulations reveal that IChOA has significant competitive advantages in addressing the STHS problem. © 2022, IAENG International Journal of Computer Science. All Rights Reserved.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

A Bottom-up Paradigm for Traffic Scene Graph Representation 2020

A Bottom-up Paradigm for Traffic Scene Graph Representation

引用

Proceedings of the 2020 9th International Conference on Computing and Pattern Recognition

作者： Zhixuan Zhang Chi Zhang Yuehu Liu Yuanqi Su Ping Li Jinzi Zheng School of Software Engineering Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China and Shaanxi Key Lab of Digital Technology and Intelligent Systems Xi'an China School of Computer Science and Technology Xi'an Jiaotong University Xi'an China China Academy of Railway Sciences Corporation Limited Beijing China

ISBN: (纸本)9781450387835

With increasing hardware computing power and model capacity, visual tasks for scene cognitive understanding have attracted more attention, such as visual relationships inference. The scene graph representation formed by a coupling of objects, attributes and relationships nodes displayed by different modalities of information, including original image, foreground things, background stuff and scene attributes, strongly promotes the progress of research area. In this paper, we address the scene graph representation of traffic scenarios for autonomous driving. It should be noted that the universal representation are the specific needs of cognitive understanding of traffic scenes: on the one hand, there is a lack of fine-grained description of key objects and attributes; on the other hand, there are redundant descriptions of objects and relationships. To tackle these problems, we take advantage of the fine-grained instance-level annotation of the traffic scene, proposing a bottom-up representation paradigm. It makes full use of the hierarchical structure of the traffic scene and the sparsity of element classes. In addition, on the basis of the existing methods, we optimize the relationship list of traffic scene graph representation. Moreover, we improve the scene graph annotation methods, proposing a "ground-vision joint location method" to better describe the spatially-distributed visual knowledge. The case analysis showed that compared with existing methods, our paradigm for scene graph can represent more abundant traffic scene information.

关键词： visual relationship description traffic knowledge representation autonomous driving Scene graph

来源：评论

学校读者我要写书评

暂无评论

Fundus-Image-Based Retinal Vascular Analysis in Myopic Eyes

Fundus-Image-Based Retinal Vascular Analysis in Myopic Eyes

引用

Chinese Control Conference (CCC)

作者： Jichen Shen Haohan Zou Yan Wang Jinchao Liu Ningbo Yu College of Artificial Intelligence Nankai University Tianjin China Clinical College of Ophthalmology Tianjin Medical University Tianjin China Tianjin Key Lab of Ophthalmology and Visual Science Tianjin Eye Institute Tianjin Eye Hospital Nankai University Affiliated Eye Hospital Tianjin China Nankai University Eye Institute Nankai University Tianjin China Tianjin Key Laboratory of Intelligent Robotics Nankai University Tianjin China Engineering Research Center of Trusted Behavior Intelligence Ministry of Education Nankai University Tianjin China Institute of Intelligence Technology and Robotic Systems Shenzhen Research Institute of Nankai University Shenzhen China

Myopia is prevalent worldwide and it is of great significance to prevent, control and intervene myopia in an early stage. The etiopathogenesis of myopia remains unclear and needs further research. Fundus photographs can show biomarkers and lesions of the retina in a non-invasive way directly. To discover some potential changes in myopic eyes, we extracted the retinal vascular features from vessel segmented results, and calculated the Spearman correlation coefficients between the retinal vascular features and the spherical refractive errors. The Kruskal-Wallis test was applied to explore the difference exists in the characteristics of retinal vessels among the mild, moderate and high myopia groups. The statistical analysis results indicated that the higher the degrees of myopia, the smaller the retinal vessels. This study found vascular changes in myopic eyes through fundus images, which could help to explain the mechanism of myopia and the damage caused by myopia.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Peer-to-Peer Localization via On-board Sensing for Aerial Flocking

Peer-to-Peer Localization via On-board Sensing for Aerial Fl...

引用

International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

作者： Fat-Hy Omar Rajab Samet Güler Jeff S. Shamma Robotics Intelligent Systems and Control (RISC) Lab Computer Electrical and Mathematical Science and Engineering Division (CEMSE) KAUST Thuwal Saudi Arabia Abdullah Gül University Kayseri Turkey

ISBN: (数字)9781728157153

ISBN: (纸本)9781728157160

The performance of mobile multi-robot systems dramatically depends on the mutual awareness of individual robots, particularly the positions of other robots. GPS and motion capture cameras are commonly used to acquire and ultimately communicate positions of robots. Such sensing schemes depend on infrastructure and restrict the capabilities of a multi-robot system, e.g., the robots cannot operate in both indoor and outdoor environments. Conversely, peer-to-peer localization algorithms can be used to free the robots from such infrastructures. In such systems, robots use on-board sensing to infer the positions of nearby robots. In this approach, it is essential to have a model of the motion of other robots. We introduce a flocking localization scheme that takes into account motion behavior exhibited by the other robots. The proposed scheme depends only on the robots' on-board sensors and computational capabilities and yields a more accurate localization solution than the peer-to-peer localization algorithms that do not take into account the flocking behavior. We verify the performance of our scheme in simulations and demonstrate experiments on two unmanned aerial vehicles.

关键词： Robot sensing systems Robot kinematics Mathematical model Drones Distance measurement

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：