检索结果-内蒙古大学图书馆

Shape-adaptive stiffness variable soft gripper using porous structure

Journal of institute of Control, robotics and Systems 2021年第3期27卷 238-246页

作者： Lee, Jae-Young Cho, Seong J. Seo, Yong-Sin Park, Chan-Hun Park, Dong-Il Kim, Byeung-In Kim, Hwi-Su Song, Sung-Hyuk Department of Robotics & Mechatronics Korea Institute of Machinery & Materials Daejeon Korea Republic of School of Mechanical Engineering Chungnam National University Daejeon Korea Republic of

Robotic grippers are essential components used in robots to perform certain tasks. Effective gripping capabilities are important for industrial and service robots. However, the parallel-type gripper, which is one of the most widely used robotic grippers, has limitations in terms of the objects that it can handle as well as applying the correct handling force, especially when handling fragile objects. Hence, a soft gripper fabricated using soft materials is proposed as a new alternative, with the advantage of preventing injuries when human-robot interaction is required. However, the limited holding force and uncontrollable movement of a soft gripper, due to its softness, could limit its use in real-life conditions. Therefore, in this article, we propose a shape-adaptive tip using a variable stiffness mechanism. To decrease the initial stiffness of the gripper tip, the reticulated polyurethane foam structure was embedded in the tip as the soft supporting layer to support the external force. The flexible mesh structure was applied as the jamming layer to change the stiffness of the tip. The prototype of the gripping system was tested, and the gripper could transfer the grape effectively without damage using the jamming mechanism. © ICROS 2021.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Grasp Manipulation Relationship Detection based on Graph Sample and Aggregation

Grasp Manipulation Relationship Detection based on Graph Sam...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Jiayuan Luo Yaxin Liu Han Wang Mengyuan Ding Xuguang Lan National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center of Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In multi-object stacking scenarios, exploring the relationships among objects and determining the correct sequence of operations are crucial for robotic manipulation. However, previous algorithms inefficiently combine global and local information, often focusing solely on the local features of objects or the interactions of object features at a global level. This approach leads to imbalanced distribution of features and the generation of redundant or missing relationships in complex scenes, such as multi-object stacking and partial occlusion. To address this issue, we have developed a grasp manipulation relationship detection algorithm called Graph Sampling Aggregation Network for Visual Manipulation Relationship Detection (GSAGED). This algorithm assists robots in detecting targets in complex scenes and determining the appropriate grasping order. Firstly, the Positional Encoding Module in GSAGED enhances object feature information by considering global contexts. Secondly, the Graph Sampling Aggregation method effectively integrates global and local information, relieving imbalanced distribution of features. Finally, we applied the developed algorithm to a physical robot for grasping. Experimental results on the Visual Manipulation Relationship Dataset (VMRD) and the large-scale relational grasp dataset named REGRAD demonstrate that our method significantly improves the accuracy of relationship detection in complex scenes and exhibits robust generalization capabilities in real-world applications.

关键词： Visualization Accuracy Stacking Focusing Grasping Encoding Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

MEG Channel Selection Using Copula Entropy-Based Transfer Entropy for Motor Imagery BCI

MEG Channel Selection Using Copula Entropy-Based Transfer En...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Chao Tang Dongyao Jiang Badong Chen National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Multi-channel magnetoencephalography (MEG) data provides high spatiotemporal resolution for motor imagery (MI)-based brain-machine interfaces (BCIs). However, not all channels contribute to the performance of BCIs. Taking into account the importance of specific channels in measuring their causal relationships with other channels during MI tasks, a novel channel selection method using copula entropy-based transfer entropy (CTE) is proposed to select task-relevant channels. Experiments on a publicly available dataset validate the effectiveness of the proposed methods. Compared to using all channels, channel selection based on CTE can significantly (p < 0.05) improve single-session classification accuracy and greatly reduce the number of MEG channels. Cross-session classification also outperforms the competing method.

关键词： Accuracy Image resolution Magnetoencephalography Motors Entropy Brain-computer interfaces Spatiotemporal phenomena engineering in medicine and biology

来源：评论

学校读者我要写书评

暂无评论

A Target-based Calibration Method for LiDAR-Visual-Thermal Multi-Sensor System

A Target-based Calibration Method for LiDAR-Visual-Thermal M...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Yuan, Songyu Xie, Tian Zhu, Shiqiang Chen, Yeheng Li, Yuehua Zheng, Tao Gu, Jason Research Center for Intelligent Robotics Research Institute of Interdis-ciplinary Innovation Zhejiang Lab Hangzhou311100 China Zhejiang Engineering Research Center for Intelligent Robotics Hangzhou311100 China Dalhousie University Department of Electrical and Computer Engineering HalifaxNSB3H 4R2 Canada

ISBN: (纸本)9781665481090

As the basis of multi-sensor fusion, accurate extrinsic calibration among multi-sensors is vital for hetero-geneous information fusion. However, most existing methods only focus on the calibration between two specific heteroge-neous sensors, such as camera-LiDAR, LiDAR-thermal, and etc. which may cause inevitable accumulation when applied to a multi-sensor system. To address this problem, a novel calibration target and a high-accuracy method are proposed to simultaneously calibrate the intrinsic and extrinsic of a 3D LiDAR, a thermal camera and a visible camera without any user intervention. The proposed method only relies on one calibration board, to calibrate all the intrinsic and extrinsic parameters in one-step, without any strict pose requirement or long-time optimization. Furthermore, 2D-3D corresponding features can be extracted with higher precision by considering sensor model, comparing to the common feature extraction methods. Experiments with Velodyne VLP-16 LiDAR, ZED camera and D843NT thermal camera demonstrate that the proposed method can complete calibration among three of them automatically. Finally, this paper also presents a target-based method of uniformly expressing the calibration errors among multi-sensor system, with a competitive performance against most state-of-the-art methods. © 2022 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

LSTM with AhI-Model Based Kalman Filter for Lithium-ion Battery State of Charge Estimation

LSTM with AhI-Model Based Kalman Filter for Lithium-ion Batt...

引用

Chinese Automation Congress (CAC)

作者： Xiangyong Luo Lujuan Dang Meng Yang Badong Chen National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Accurate state of charge (SOC) estimation of lithium-ion battery in battery management system (BMS) is important for the safety and reliability of electronic devices and electric vehicles. This paper proposes a LSTM-extended Kalman filter based on AhI-model (LSTM-EA), which constrains SOC result from LSTM with an AhI-model based Kalman filter. AhI-model is based on Ampere-hour integration method and requires simpler structure to obtain estimated SOC with higher accuracy and robustness. In the experiments, the public datasets from the center for Advanced Life Cycle engineering (CALCE) are used to validate the SOC estimation performance. The mean absolute error (MAE) and maximum error of the proposed method are less than 2.51% and 8.82% respectively.

关键词： Lithium-ion batteries Accuracy Fluctuations Estimation Electric vehicles Robustness Safety State of charge Kalman filters Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Measuring mutual policy divergence for multi-agent sequential exploration 24

Measuring mutual policy divergence for multi-agent sequentia...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Haowen Dou Lujuan Dang Zhirong Luan Badong Chen National Key Laboratory of Human-Machine Hybrid Augmented Intelligence and National Engineering Research Center for Visual Information and Applications and Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University School of Electrical Engineering Xi'an University of Technology

ISBN: (纸本)9798331314385

Despite the success of Multi-Agent Reinforcement Learning (MARL) algorithms in cooperative tasks, previous works, unfortunately, face challenges in heterogeneous scenarios since they simply disable parameter sharing for agent specialization. Sequential updating scheme was thus proposed, naturally diversifying agents by encouraging agents to learn from preceding ones. However, the exploration strategy in sequential scheme has not been investigated. Benefiting from updating one-by-one, agents have the access to the information from preceding agents. Thus, in this work, we propose to exploit the preceding information to enhance exploration and heterogeneity sequentially. We present Multi-Agent Divergence Policy Optimization (MADPO), equipped with mutual policy divergence maximization framework. We quantify the discrepancies between episodes to enhance exploration and between agents to heterogenize agents, termed intra-agent divergence and inter-agent divergence. To address the issue that traditional divergence measurements lack stability and directionality, we propose to employ the conditional Cauchy-Schwarz divergence to provide entropy-guided exploration incentives. Extensive experiments show that the proposed method outperforms state-of-the-art sequential updating approaches in two challenging multi-agent tasks with various heterogeneous scenarios. Source code is available at https://***/hwdou6677/MADPO.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Curriculum Learning for Ultra-Wide-Angle Fundus Optic Disc Segmentation

Semi-Supervised Curriculum Learning for Ultra-Wide-Angle Fun...

引用

Chinese Automation Congress (CAC)

作者： Yingkai Wang Yiyi Chen Jiayi Wu Jingmin Xin National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Segmentation of the optic disc in ultra-wide-angle fundus images could aid in detection and diagnosis of diabetic kidney disease and diabetic retinopathy. Due to the wide field of view, large image size, and small targets of ultra-wide-angle fundus images, it's hard to annotate them. In this case, semi-supervised methods could solve this problem. However, standalone semi-supervised training does not take into account the differences between samples. We developed a new semi-supervised training method incorporating curriculum learning, where the model initially trains on easier samples and gradually progresses to more hard ones. This strategy could avoid the pos-sible negative impact of the unlabeled samples in early stages in training and strengthen model's robustness and serves as a plug-and-play approach and is adaptable to existing semi-supervised semantic segmentation methods. More concretely, we design a difficulty measurer to estimate the training difficulty of samples from the perspective of the entire dataset and a pace controller to control training time and duration of different samples according to their training difficulty. The experiment result shows the method we proposed could improves the performance.

关键词： Training Adaptation models Diabetic retinopathy Automation Semantic segmentation Optical imaging Time measurement Robustness Kidney Diseases

来源：评论

学校读者我要写书评

暂无评论

Exploring Self-supervised Skeleton-based Action Recognition in Occluded Environments

arXiv

引用

arXiv 2023年

作者： Chen, Yifei Peng, Kunyu Roitberg, Alina Schneider, David Zhang, Jiaming Zheng, Junwei Chen, Yufan Liu, Ruiping Yang, Kailun Stiefelhagen, Rainer Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Germany Institute for Artificial Intelligence University of Stuttgart Germany School of Robotics Hunan University China National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University China

To integrate action recognition into autonomous robotic systems, it is essential to address challenges such as person occlusions—a common yet often overlooked scenario in existing self-supervised skeleton-based action recognition methods. In this work, we propose IosPSTL, a simple and effective self-supervised learning framework designed to handle occlusions. IosPSTL combines a cluster-agnostic KNN imputer with an Occluded Partial Spatio-Temporal Learning (OPSTL) strategy. First, we pre-train the model on occluded skeleton sequences. Then, we introduce a cluster-agnostic KNN imputer that performs semantic grouping using k-means clustering on sequence embeddings. It imputes missing skeleton data by applying K-Nearest Neighbors in the latent space, leveraging nearby sample representations to restore occluded joints. This imputation generates more complete skeleton sequences, which significantly benefits downstream self-supervised models. To further enhance learning, the OPSTL module incorporates Adaptive Spatial Masking (ASM) to make better use of intact, high-quality skeleton sequences during training. Our method achieves state-of-the-art performance on the occluded versions of the NTU-60 and NTU-120 datasets, demonstrating its robustness and effectiveness under challenging conditions. Code is available at https://***/cyfml/OPSTL. Copyright © 2023, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Smart Railway Level Crossing System for Avoiding Accidents

Smart Railway Level Crossing System for Avoiding Accidents

引用

International Conference on robotics and Artificial Intelligence (ICRAI)

作者： Ghulam Fiza Mirza Yahya Sameen Junejo Faisal Karim Shaikh Bhawani Shankar Chowdhry Ali Akbar Shah Department of Telecommunications NED University of Engineering and Technology Karachi Pakistan Haptics Human Robotics and Condition Monitoring Lab National Center of Robotics and Automation Mehran University of Engineering and Technology Jamshoro Pakistan

In railways, one of the foremost issue is the safety of railway level crossing. Crashes related to railway level crossing lead to a great loss with respect to goods and lives. However, the existing methods used for the accidents' avoidance are manual, sensors and cameras based which possess certain drawbacks. Manual control of crossing gates is not only time-consuming but requires human labor and generate errors. Besides, camera based control systems are costly, involve experts to process the images, require human intervention, and do not provide clear images in fog/rain. On the other hand, sensors based systems have short range issues and are dependent on environmental conditions. This paper reviews the existing control systems of railway infrastructure and their classification in different countries. It then presents an automatic, novel, high range and cost-effective approach to prevent critical accidents intelligently. The novel concept avoids level crossing accidents using Internet of Things (IoT) technology. The train GPS based on-board and track controller nodes communicate to control level crossing gates and alert road users. The communication between modules (i.e., on-board train and track devices) and remote database establishes using WiFi. The review of effective communication network for critical and non-critical communication is presented with respect to mobility, capacity, coverage, availability and reliability. This research provides concept which can greatly mitigate the accidents' frequency associated with the trains, pedestrians and road vehicles on crossing using smart technologies.

关键词： Databases Roads Logic gates Cameras Rail transportation Sensor systems Reliability

来源：评论

学校读者我要写书评

暂无评论

General Planning Method for Humanoid Collaborative Robots Using Large Language Models

General Planning Method for Humanoid Collaborative Robots Us...

引用

Chinese Automation Congress (CAC)

作者： Runqin Gao Jiamin Shi Shu Tian Shitao Chen National Key Laboratory of Human-Machine Hybrid Augmented Intelligence National Engineering Research Center for Visual Information and Applications Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Humanoid robots, capable of simulating human behavior and decision-making, have garnered extensive attention due to their anthropomorphic structures and versatile functional designs. Traditionally, actions and high-level decision-making in robots have been manually achieved by developers, requiring modifications and adaptations for different task requirements, thus lacking autonomous decision-making capabilities. With the rapid advancement of deep learning technologies, large language models trained on internet data have provided new solutions for robot intelligence, demonstrating effective applications in high-level task planning for robots. Based on this, we propose a general high-level task planning method using large language models, implemented on a mobile single-arm humanoid robot as the platform. This method consists of two core components: high-level decision planning and low-level action execution, coupled through the robot's atomic action interface. The robot autonomously completes sequential action planning by receiving natural language task instructions and executes long-term, complex, general indoor collaborative tasks. By deploying on a real robot, we conducted sub-module tests and overall system performance tests, successfully achieving the process of sorting and organizing tasks in an indoor experimental environment.

关键词： Deep learning Large language models System performance Decision making Natural languages Humanoid robots Collaborative robots Planning Robots Sorting

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：