检索结果-内蒙古大学图书馆

13th IEEE International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, CYBER 2023

作者： Chen, Heping Fang, Siwen Shenzhen Academy of Robotics Shenzhen China

ISBN: (纸本)9798350315196

Piping robots that work inside pipes are widely used in nuclear, oil and gas industries. These robots can perform inner pipe operations such as in-spection, cleaning and grinding inside pipes. No matter what the operation is, the ability to move smoothly inside a pipe is very important. Pipes always have joints, turns and elbows that constrain the dimensionality of piping robots. In this paper, we present an optimization method to optimize the dimensionality of piping robots. Once the pipe's parameters are known, an optimization method is formulated to maximize the volume of a piping robot to ensure enough space for powerful actuators to perform different tasks. The proposed method is validated by fabricating a piping robot based on the optimized parameters for a given pipe. Experiments were performed and the results show that the robot can move smoothly inside the pipe. © 2023 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

TrinityMag:A novel magnetically actuated miniature robot manipulating system with a human-scale workspace

引用

Science China(Technological Sciences) 2024年第11期67卷 3546-3558页

作者： LI Dong CHEN BinHan HUANG ChenYang XU Sheng WU XinYu XU TianTian Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Key Laboratory of Biomedical Imaging Science and System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China

The development of the magnetic manipulating system is essential for applications of magnetically actuated miniature robots in biomedical practice,such as targeted therapy and precise ***,the workspaces of existing magnetic manipulating systems for miniature robots are mostly insufficient to manipulate miniature robots inside human *** present study proposes an innovative electromagnets-based manipulating system,TrinityMag,which can produce dynamic three-dimensional(3D)magnetic fields in a human-scale spherical workspace with a 2.6 m *** magnetic field of a single electromagnet is simulated,and a new calibration technic is designed based on deep learning ***,the arrangement of three electromagnets is optimized to produce maximal 3D arbitrary magnetic fields with limited ***,a target-tracking algorithm is developed so that the TrinityMag can track the miniature robot in real ***,the TrinityMag is validated in experiments to manipulate a soft millirobot to move in human-scale tortuous tracks with two types of *** maximum speed of the soft millirobot reaches 11.05 body length/*** work contributes to a significant increment in the workspace of the electromagnets-based manipulating system for miniature *** further expect that the TrinityMag could push the applications of miniature robots from laboratory to clinical practice.

关键词： magnetic manipulating system human-scale workspace magnetically actuated miniature robots

来源：评论

学校读者我要写书评

暂无评论

PCE: Multi-Agent Path Finding via Priority-Aware Communication & Experience Learning

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-13页

作者： Gao, Jianqi Li, Yanjie Ye, Zhaohui Wu, Xinyu Department of Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics and School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

Multi-agent path finding (MAPF) is an essential issue for warehouse automation, where multiple agents plan collision-free paths from the start to goal positions. Reinforcement learning (RL) has been employed to develop partially observable distributed MAPF methods that can be scaled to any number of agents. However, existing RL-based MAPF methods still have some limitations in handling redundant information and avoiding deadlock, resulting in a low success rate or longer makespan. This paper proposes a Priority-aware Communication & Experience learning method (PCE), which combines RL with a novel priority-aware multi-agent communication and a new priority-aware deadlock experience replay to tackle this challenge. To be specific, our innovation encompasses two-fold. Our proposed communication mechanism aims to handle redundant information, which establishes a dynamic communication topology based on agents' priorities and proposes a two-head priority-aware graph attention network to aggregate information. In order to help the agent avoid deadlock, we prioritize the expert experience that solves the deadlock when performing experience replay. We conduct multiple simulation experiments on warehouse-like structured grid maps. Compared with the state-of-the-art RL-based MAPF methods, PCE performs significantly better with a higher success rate and lower makespan in small and large MAPF and higher average throughput in the lifelong MAPF, which can further improve the efficiency of warehouse automation. Finally, we validate PCE using three Turtlebot3-Burger robots, which shows that PCE can be applied in real warehouse automation scenarios. IEEE

关键词： Aggregates

来源：评论

学校读者我要写书评

暂无评论

Thermal and Magnetic Dual-Responsive Catheter-Assisted Shape Memory Microrobots for Multistage Vascular Embolization

引用

Research 2024年第3期2024卷 529-543页

作者： Qianbi Peng Shu Wang Jianguo Han Chenyang Huang Hengyuan Yu Dong Li Ming Qiu Si Cheng Chong Wu Mingxue Cai Shixiong Fu Binghan Chen Xinyu Wu Shiwei Du Tiantian Xu Guangdong Provincial Key Lab of Robotics and Intelligent Systems Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhenChina University of Chinese Academy of Sciences BeijingChina Department of Neurosurgery South China HospitalMedical SchoolShenzhen University.ShenzhenChina The Key Laboratory of Biomedical Imaging Science and System Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhenChina.

Catheters navigating through complex vessels,such as sharp turns or multiple U-turns,remain challenging for vascular ***,we propose a novel multistage vascular embolization strategy for hard-to-reach vessels that releases untethered swimming shape-memory magnetic microrobots(SMMs)from the prior catheter to the vessel ***,made of organo-gel with magnetic particles,ensure biocompatibility,radiopacity,thrombosis,and fast thermal and magnetic *** SMM is initially a linear shape with a 0.5-mm diameter at 20°C inserted in a *** transforms into a predetermined helix within 2 s at 38°C blood temperature after being pushed out of the catheter into the *** enable agile swimming in confined and tortuous vessels and can swim upstream using helical propulsion with rotating magnetic ***,we validated this multistage vascular embolization in living rabbits,completing 100-cm travel and renal artery embolization in 2 *** 4 weeks,the SMMs maintained the embolic position,and the kidney volume decreased by 36%.

关键词： turns maintained travel

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Navigation for Robots Based on Hippocampus Episode Cognition

引用

Journal of Bionic Engineering 2024年第1期21卷 288-302页

作者： Jinsheng Yuan Wei Guo Zhiyuan Hou Fusheng Zha Mantian Li Pengfei Wang Lining Sun State Key Laboratory of Robotics and System Harbin Institute of Technology(HIT)Harbin 150001China Shenzhen Academy of Aerospace Technology Shenzhen 518057China School of Mechanical and Electrical Engineering Lanzhou University of TechnologyLanzhou 730050China

Artificial intelligence is currently achieving impressive success in all ***,autonomous navigation remains a major challenge for *** learning is used for target navigation to simulate the interaction between the brain and the environment at the behavioral level,but the Artificial Neural Network trained by reinforcement learning cannot match the autonomous mobility of humans and *** hippocampus–striatum circuits are considered as key circuits for target navigation planning and *** paper aims to construct a bionic navigation model of reinforcement learning corresponding to the nervous system to improve the autonomous navigation performance of the *** ventral striatum is considered to be the behavioral evaluation region,and the hippocampal–striatum circuit constitutes the position–reward *** this paper,a set of episode cognition and reinforcement learning system simulating the mechanism of hippocampus and ventral striatum is constructed,which is used to provide target guidance for the robot to perform autonomous *** with traditional methods,this system reflects the high efficiency of learning and better Environmental *** research is an exploration of the intersection and fusion of artificial intelligence and neuroscience,which is conducive to the development of artificial intelligence and the understanding of the nervous system.

关键词： Episode cognition Reinforcement learning Hippocampus Robot navigation

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Control Scheme for Active Power-assist Lower-limb Exoskeletons

引用

Journal of Bionic Engineering 2024年第5期21卷 2184-2198页

作者： Jing Deng Wenzheng Jiang Haibo Gao Yapeng Shi Mantian Li State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin150001HeilongjiangChina Shenzhen Academy of Aerospace Technology Shenzhen518063China Faculty of Computing Harbin Institute of TechnologyHarbin150001HeilongjiangChina Institute of Intelligent Manufacturing Technology Shenzhen Polytechnic UniversityShenzhen518055China

Effectively controlling active power-assist lower-limb exoskeletons in a human-in-the-loop manner poses a substantial chal-lenge,demanding an approach that ensures wearer autonomy while seamlessly adapting to diverse wearer *** paper introduces a novel hierarchical control scheme comprising five integral components:intention recognition layer,dynamics feedforward layer,force distribution layer,feedback compensation layer,as well as sensors and *** intention rec-ognition layer predicts the wearer's movement and enables wearer-dominant movement through integrated force and position *** force distribution layer effectively resolves the statically indeterminate problem in the context of double-foot support,showcasing flexible control *** dynamics feedforward layer mitigates the effect of the exoskeleton itself on ***,the feedback compensation layer provides reliable closed-loop *** approach mitigates abrupt changes in joint torques during frequent transitions between swing and stance phases by decomposed *** this innovative hierarchical control scheme on a hydraulic exoskeleton platform through a series of experiments,the results demonstrate its capability to deliver assistance in various modes such as stepping,squatting,and jumping while adapting seamlessly to different terrains.

关键词： Hierarchical control Active power-assist Exoskeleton robots Dynamics feedforward Force distribution Feedback compensation

来源：评论

学校读者我要写书评

暂无评论

Towards robustness and generalization of point cloud representation:A geometry coding method and a large-scale object-level dataset

引用

Computational Visual Media 2024年第1期10卷 27-43页

作者： Mingye Xu Zhipeng Zhou Yali Wang Yu Qiao Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen518000China University of Chinese Academy of Sciences Beijing065001China Shanghai AI Laboratory Shanghai200001China SIAT Branch Shenzhen Institute of Artificial Intelligence and Robotics for SocietyShenzhen518000China Alibaba DAMO Academy Hangzhou242332China

Robustness and generalization are two challenging problems for learning point cloud *** tackle these problems,we first design a novel geometry coding model,which can effectively use an invariant eigengraph to group points with similar geometric information,even when such points are far from each *** also introduce a large-scale point cloud dataset,*** consists of 184 categories and 51,915 synthetic objects,which brings new challenges for point cloud classification,and provides a new benchmark to assess point cloud cross-domain ***,we perform extensive experiments on point cloud classification,using ModelNet40,ScanObjectNN,and our PCNet184,and segmentation,using ShapeNetPart and *** method achieves comparable performance to state-of-the-art methods on these datasets,for both supervised and unsupervised *** and our dataset are available at https://***/MingyeXu/PCNet184.

关键词： geometry coding self-supervised learning point cloud classification segmentation 3D analysis

来源：评论

学校读者我要写书评

暂无评论

Learning Agile Quadrotor Flight in Restricted Environments With Safety Guarantees

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年第9期9卷 5642-5649页

作者： Chen, Shiyu Li, Yanjie Lou, Yunjiang Lin, Ke Wu, Xinyu Harbin Institute of Technology Shenzhen Department of Control Science and Engineering Shenzhen518055 China Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics Shenzhen518055 China Chinese Academy of Sciences Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China

With the increasing requirement for agile and efficient controllers in safety-critical scenarios, controllers that exhibit both agility and safety are attracting attention, especially in the aerial robotics domain. This paper focuses on the safety issue of Reinforcement Learning (RL)-based control for agile quadrotor flight in restricted environments. To this end, we propose a unified Adaptive Safety Predictive Corrector (ASPC) to certify each output action of the RL-based controller in real-time, ensuring its safety while maintaining agility. Specifically, we develop the ASPC as a finite-horizon optimal control problem, formulated by a variant of Model Predictive Control (MPC). Given the safety constraints determined by the restricted environment, the objective of minimizing loss of agility can be optimized by reducing the difference between the actions of RL and ASPC. As the safety constraints are decoupled from the RL-based control policy, the ASPC is plug-and-play and can be incorporated into any potentially unsafe controllers. Furthermore, an online adaptive regulator is presented to adjust the safety bounds of the state constraints with respect to the environment changes, extending the proposed ASPC to different restricted environments. Finally, simulations and real-world experiments are demonstrated in various restricted environments to validate the effectiveness of the proposed ASPC. © 2016 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design and Signal Quality Assessment of a Novel Low-Cost Wireless EMG Sensor 14

Design and Signal Quality Assessment of a Novel Low-Cost Wir...

引用

14th IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems, CYBER 2024

作者： Ling, Ziqin Chen, Jiangcheng Li, Yaonan Xi, Ning University of Hong Kong Department of Industrial and Manufacturing Systems Engineering Hong Kong Shenzhen Academy of Robotics Shenzhen China

ISBN: (纸本)9798331506056

Electromyography (EMG) sensors have been widely used for assessing muscle activation state and human-robot interaction (HRI). However, available commercial EMG sensors are expensive and inconvenient for real-time applications. The aim of this study is to design and validate a novel low-cost wireless EMG sensor. Specifically, the wireless EMG sensor is equipped with an analog-front-end (AFE), radio frequency (RF) module, and controller area network (CAN) bus, which achieves wireless data transmission and provides an interface for real-time HRI. The evaluation of the designed system was done by a series of exercises performed by volunteers. Raw signal., mean absolute value (MAV), zero crossings (ZC), slope sign changes (SSC), waveform length (WL), and median frequency (MDF) are used for comparing wireless EMG sensors and commercial sensors. In addition, Spearman's correlation (SC), and intra-class cross-correlation (ICC) are used as two validation indicators. The result shows that the SC and ICC between the raw signals of the two types of sensors are 0.6156 and 0.7780, respectively. The SC of MAV, ZC, SSC, WL, and MDF are 0.9708, 0.6740, 0.8023, 0.9663, and 0.9476, respectively. The ICC of MAV, ZC, SSC, WL, and MDF are 0.9670, 0.7340, 0.7910, 0.9540., and 0.8230, respectively. The results indicate a good agreement between the two systems and confirm the reliability of the wireless EMG sensor's design. The wireless EMG sensor can be further applied to real-time HRI and muscle fatigue assessment. © 2024 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

A Novel Sample-Efficient Deep Reinforcement Learning with Episodic Policy Transfer for PID-Based Control in Robotic Catheter System

A Novel Sample-Efficient Deep Reinforcement Learning with Ep...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Omisore, Olatunji Mumini Akinyemi, Toluwanimi Oluwadara Duan, Wenke Du, Wenjing Wang, Lei Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Research Center for Medical Robotics and MIS Devices Shenzhen China

ISBN: (纸本)9781665481090

Robotic catheterization is typically used for percutaneous coronary intervention procedures nowadays and it involves steering flexible endovascular tools to open up occlusion in the coronaries. In this study, a sample-efficient deep reinforcement learning with episodic policy transfer is, for the first time, used for motion control during robotic catheterization with a fully adaptive PID tuning strategy. The reinforcement model aids the agent to continuously learn from its interactions in its environment and adaptively tune PID control gains for axial navigation of endovascular tools. The model was validated for axial motion control of a robotic system designed for intravascular catheterization. Simulation and experimental trials were done to validate the application of the model, and results obtained shows it could self-tune PID gains appropriately for motion control of a robotic catheter system. Performance comparison with conventional methods in an average of 10 trials shows the agent tunes the gain better with an error of 0.003 mm. Thus, the proposed model would offer more stable set-point motion control robotic catheterization. © 2024 IEEE.

关键词： Deep reinforcement 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：