检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Li, Siyu Cao, Yihong Shi, Hao Zang, Yongsheng He, Xuan Yang, Kailun Li, Zhiyong School of Robotics the National Engineering Research Center of Robot Visual Perception and Control Technology Hunan University Changsha410082 China State Key Laboratory of Extreme Photonics and Instrumentation Zhejiang University Hangzhou310027 China College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Hunan Vanguard Group Corporation Limited Changsha410100 China

The exploration of Bird’s-Eye View (BEV) mapping technology has driven significant innovation in visual perception technology for autonomous driving. BEV mapping models need to be applied to the unlabeled real world, making the study of unsupervised domain adaptation models an essential path. However, research on unsupervised domain adaptation for BEV mapping remains limited and cannot perfectly accommodate all BEV mapping tasks. To address this gap, this paper proposes HierDAMap, a universal and holistic BEV domain adaptation framework with hierarchical perspective priors. Unlike existing research that solely focuses on image-level learning using prior knowledge, this paper explores the guiding role of perspective prior knowledge across three distinct levels: global, sparse, and instance levels. With these priors, HierDA consists of three essential components, including Semantic-Guided Pseudo Supervision (SGPS), Dynamic-Aware Coherence Learning (DACL), and Cross-Domain Frustum Mixing (CDFM). SGPS constrains the cross-domain consistency of perspective feature distribution through pseudo labels generated by vision foundation models in 2D space. To mitigate feature distribution discrepancies caused by spatial variations, DACL employs uncertainty-aware predicted depth as an intermediary to derive dynamic BEV labels from perspective pseudo-labels, thereby constraining the coarse BEV features derived from corresponding perspective features. CDFM, on the other hand, leverages perspective masks of view frustum to mix multi-view perspective images from both domains, which guides cross-domain view transformation and encoding learning through mixed BEV labels. Furthermore, this paper introduces intra-domain feature exchange data augmentation to enhance the efficiency of domain adaptation learning. The proposed method is verified on multiple BEV mapping tasks, such as BEV semantic segmentation, high-definition semantic, and vectorized mapping. It demonstrates competitive perfo

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Learning to Manipulate Tools Using Deep Reinforcement Learning and Anchor Information

Learning to Manipulate Tools Using Deep Reinforcement Learni...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Wei, Junhang Cui, Shaowei Hao, Peng Wang, Shuo The School of Future Technology University of Chinese Academy of Sciences Beijing100049 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The University of Chinese Academy of Sciences Beijing100049 China The Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China

ISBN: (纸本)9781665481090

Endowing robots with tool manipulation skills helps them accomplish challenging tasks. While robots manipulate tools to achieve goals, the alignment of tools and targets is a noise-sensitive and contact-rich task. However, it is difficult to access the accurate pose of the tool and the target. When there is unknown noise in the observations, reinforcement learning can't be sure to perform well. In this paper, we define the easier-to-obtain accurate task-related information as anchor information and introduce a tool manipulation method based on reinforcement learning and anchor information, which can perform well when the observations include unknown noise. To evaluate the method, we build a simulated environment ToolGym, which includes four different kinds of tools and different noise sampling functions for each tool. Finally, we compare our method with baseline methods to show the effectiveness of the proposed method. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Visual Grasping with Spectral Clustering and Heuristic Searching for Robot in Cluttered Environments

Visual Grasping with Spectral Clustering and Heuristic Searc...

引用

IEEE International Conference on robotics and Biomimetics

作者： Wenjie Geng Zhiqiang Cao Yingbo Tang Shuo Wang Fengshui Jing The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665481106

Grasping the target object is an essential requirement for the robot to provide better services. It becomes complicated especially in cluttered environments, which still remains challenging. This paper proposes a grasping chain generation solution that enables the robot to grasp the target after other obstruction objects are moved in a good order. SSD is firstly adopted to acquire the information of detectable objects and then Euclidean clustering is employed to obtain the untrained objects. After that, the minimum bounding box of each object is obtained, which is then projected on the plane and represented by a smooth differentiable minimum ellipse. On this basis, an information density kernel function is designed to express the interaction between objects. By abstracting each ellipse as a node of the graph whose edge weight is calculated by this kernel function, the whole scene is described in a form of graph. To simplify the complexity of the scene graph, we use spectral clustering algorithm to classify the objects, and the task-oriented objects graph is constructed according to the objects closely related to the target one. As a result, the searching space is reduced. With space division of task-oriented objects graph, each candidate grasping chain is iteratively extended by using the heuristic searching and the best chain with the shortest length is determined. The proposed method can deal with secondary obstruction and its effectiveness is testified by experiments.

关键词： Visualization Clustering algorithms Grasping Search problems Complexity theory Classification algorithms Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Microsphere Superlenses-Based Optical Super-Resolution Imaging of Ovarian Tissue Sections

Microsphere Superlenses-Based Optical Super-Resolution Imagi...

引用

IEEE International Conference on Cyber Technology in Automation, control, and Intelligent systems

作者： Shuai Yuan Chaodi Jiang Hao Luo Shendi Li Xiaoduo Wang School of Electrical & Control Engineering Shenyang Jianzhu University Shenyang Liaoning Province China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China School of Shenyang Ligong University Shenyang China Institutes for Robotics and Intelligent Manufacturing Shenyang China

Tissue sections can reveal tumour-specific changes, and a tumour diagnosis can be made by analyzing the arrangement and distribution of cells on the surface. Although histopathological diagnosis based on tissue section observation has been the gold standard for tumour diagnosis, there is still much room for improvement in terms of scale due to the limited spatial resolution of conventional optical microscopy. Microsphere super-resolution microscopy offers a potential solution to these problems. Super-resolution imaging of the surface of tissue sections was achieved with the aid of microspheres fixed to the surface of the tissue section and a removable piezoelectric ceramic displacement stage. A single microsphere of barium titanate, measuring $50\mu\mathrm{m}$ in diameter, is capable of achieving super-resolution and is particularly suitable for observing the surface nanostructure of tissue sections. In our experiment, we successfully combined the microsphere super-resolution microscope with scanning stitching techniques to obtain tissue section structure images with a resolution lower than 200nm. Our research results will help improve the accuracy of tissue section observations and promote advancements in this field.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visuotactile Feedback Parallel Gripper for Robotic Adaptive Grasping

Visuotactile Feedback Parallel Gripper for Robotic Adaptive ...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Zhang, Boyue Cui, Shaowei Zhang, Chaofan Hu, Jingyi Wang, Shuo School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Institute of Automation Chinese Academy of Sciences Beijing100190 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Shanghai200031 China

ISBN: (纸本)9781665481090

In robot grasp and dexterous manipulation tasks, tactile sensing is important for the control adjustment of the manipulator. In this paper, we present a novel low-cost parallel gripper with high-resolution tactile sensing, named the GelStereo Gripper. Furthermore, an adaptive grasp strategy is proposed to endow the gripper with tactile-feedback grasp stability-maintaining ability. We install the gripper on our robot platform and conduct various grasp experiments by utilizing proposed control methods. Experimental results verify the reliability of the GelStereo gripper and also prove the effectiveness of the proposed strategy for experimental objects with different features. © 2022 IEEE.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Position Sensorless control of Permanent Magnet Synchronous Motor Based on Adaptive Filtering Sliding Mode Observer

Position Sensorless Control of Permanent Magnet Synchronous ...

引用

Chinese control and Decision Conference, CCDC

作者： Anna Wang Yingjie Xiong Tao Zhang College Of Information Science and Engineering Northeastern University Shenyang China School of Electrical Engineering Dalian University of Technology Dalian China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9781665478977

In the position sensorless control strategy of permanent magnet synchronous motor (PMSM), the back-EMF method based on sliding mode observer (SMO) is favored because of its robustness. In this paper, a SMO based on the piecewise sigmoid function is designed. Based on the back-EMF observation error, the gain adaptation of the SMO is realized, which effectively reduces the high-frequency chattering problem of the conventional SMO. The low-pass filter of the conventional SMO is improved, and an adaptive filter based on the back-EMF low-pass filter is proposed. According to the back-EMF observation error, the cut-off frequency of the low-pass filter is changed in real-time, and the estimation of rotor position is improved. After Matlab/Simulink simulation verification, the control strategy is feasible and achieves a better control effect.

关键词： Adaptation models Low-pass filters Adaptive filters Rotors Sensorless control Observers Permanent magnet motors

来源：评论

学校读者我要写书评

暂无评论

Self Recovery of Localization Loss for Indoor Mobile Robot

引用

Journal of Harbin Institute of Technology(New Series) 2020年第2期27卷 46-57页

作者： Lin Jiang Han Wang Bin Lei Jianyang Zhu Huaiguang Liu Hui Zhao Key Laboratory of Metallurgical Equipment and Control Technology Wuhan University of Science and TechnologyWuhan 430081China Institute of Robotics and Intelligent Systems Wuhan University of Science and TechnologyWuhan 430081China

In order to solve the problem of localization loss that an autonomous mobile robot may encounter in indoor environment,an improved Monte Carlo localization algorithm is proposed in this *** algorithm can identify the state of the robot by real time monitoring of the mean weight changes of the particles and introduce more high weight particles through the divergent sampling function when the robot is in the state of localization *** observation model will make the particle set slowly approach to the real position of the robot and the new particles are then sampled to reach the *** loss self recovery experiments of different algorithms under different experimental scenarios are presented in this paper.

关键词： indoor mobile robot self recovery localization loss improved Monte Carlo localization algorithm

来源：评论

学校读者我要写书评

暂无评论

Design and Experiments of a Portable Robotic Ultrasound Scanning and Diagnosis System of Carotid Artery

Design and Experiments of a Portable Robotic Ultrasound Scan...

引用

International Conference on Advanced robotics and Mechatronics (ICARM)

作者： Longyue Tan Zhaokun Deng Mingrui Hao Pengcheng Zhang Xilong Hou Xiaolin Gu Chen Chen Shuangyi Wang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Center for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong Lingshu Medical Company Suzhou China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Ultrasound (US) imaging is an important, non-invasive method for evaluating the carotid artery (CA), which plays a critical role in early screening cardiovascular and cerebrovascular conditions. However, it requires specialized training for sonographers, which is a challenge in primary healthcare. Robotic devices now enable semi-automatic or fully automatic US scans, reducing the need for skilled operators. This paper presents an innovative, economically viable robotic system specifically engineered for conducting US examinations of the human CA. This system is distinguished by its advanced human-machine interaction capabilities with artificial intelligence assistance, which facilitate semi-automatic scanning processes in primary healthcare settings. Building upon this, the study introduces a semi-automatic scanning approach designed to control the device’s operations, aiming at capturing highquality images of the key structures of CA. Employing the images obtained through this method, the research proposes a segmentation strategy, leveraging fine-tuning adjustments on the LiteMedSAM model to achieve semantic segmentation of the CA in the images. The outcome is a nuanced diagnostic tool capable of identifying and evaluating carotid stenosis. The mentioned device and methods are tested on human subjects and the results indicate success on detecting critical vascular structures and positive feedback on human-machine interaction from operators and patients.

关键词： Human computer interaction Training Ultrasonic imaging Mechatronics Semantic segmentation Buildings Imaging Medical services Robots Carotid arteries

来源：评论

学校读者我要写书评

暂无评论

Catch Planner: Catching High-Speed Targets in the Flight

arXiv

引用

arXiv 2023年

作者： Yu, Huan Wang, Pengqin Wang, Jin Ji, Jialin Zheng, Zhi Tu, Jie Lu, Guodong Meng, Jun Zhu, Meixin Shen, Shaojie Gao, Fei The State Key Laboratory of Fluid Power and Mechatronic Systems School of Mechanical Engineering Zhejiang University Hangzhou310027 China The Engineering Research Center for Design Engineering and Digital Twin of Zhejiang Province School of Mechanical Engineering Zhejiang University Hangzhou310027 China Robotics Institute of Zhejiang University Hangzhou310027 China Hong Kong The State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China Huzhou Institute of Zhejiang University Huzhou313000 China School of Electrical Engineering Zhejiang University Hangzhou310027 China The Hong Kong University of Science and Technology Guangzhou China

Catching high-speed targets in the flight is a complex and typical highly dynamic task. However, existing methods require manual setting of catching height or time, resulting in lacks of adaptability and flexibility and cannot deal with multiple targets. To bridge this gap, we propose a planning-with-decision scheme called Catch Planner. For sequential decision making, a lightweight policy search method based on deep reinforcement learning is proposed. It is jointly trained with the motion planning and decoupled from physics to speed up training. For motion planning, we propose a trajectory optimization method that jointly optimizes the highly coupled catching time and terminal state. The core is the flexible-terminal constraint transcription. It converts the three unique constraints of catching into differentiable metrics, including equality constraints for terminal position and time, and inequality constraints that enable reasonable terminal position offset and attitude relaxation. In addition, sparse parameterization based on MINCO class considers both dynamic feasibility and collision avoidance constraints. As a result, a generally constrained quadrotor planning problem is transformed into an unconstrained optimization that can be solved reliably and efficiently. We also propose an online iterative optimization method for predicting differentiable trajectories of targets. Catch Planner provides a new paradigm for the combination of learning and planning, where all algorithms can be run in real time onboard at 100hz. Extensive experiments are carried out in real-world and simulated scenes to verify the robustness and expansibility when facing a variety of high-speed flying targets. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Human-in-the-loop Optimization for Adaptive Assist-as-Needed Rehabilitation 12

Human-in-the-loop Optimization for Adaptive Assist-as-Needed...

引用

12th International Conference on CYBER Technology in Automation, control, and Intelligent systems, CYBER 2022

作者： Li, Ning Yang, Yang Yang, Tie Chen, Wenyuan Wang, Yihan Yu, Peng Wang, Wenxue Xi, Ning Liu, Lianqing Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China University of the Chinese Academy of Sciences Beijing100049 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang10016 China School of Electrical and Electronics Engineering Nanyang Technological University 50 Nanyang Avenue 639798 Singapore Emerging Technologies Institute Department of Industrial and Manufacturing Systems Engineering University of Hong Kong Pokfulam999077 Hong Kong

ISBN: (数字)9781665472678

ISBN: (纸本)9781665472678

Active voluntary participation in robot-assisted rehabilitation promote the recovery of stroke hemiplegia. However, different patients have personalized recovery states, which needs the adaptive control strategy to improve the patient's participation. Therefore, in this study, a Mirror Adaptive Assist-As-Needed (MAAN) scheme is proposed to encourage subjects to participate actively and avoid the slack of the subjects including two modules: Functional Capability Estimation (FCE) and Mirror Adaptation (MAD). Specifically, the first MSFE module can obtain joint functional capability based on fused biological and motional signals. The second MAD module acquires the needed assistance via the estimated torques of FCE based on healthy limb. Through the iteration and collaboration of these two modules, a human-in-the-loop adaptive training is achieved to promote the patient participation. The results demonstrate that the MAAN strategy can generate suitable assistance for the patients to correct abnormal muscle activation patterns and promote active voluntary participation. Compared with other methods, the proposed strategy improves motion stability and consistency with the natural physiological state of healthy limbs. This research can be expected to greatly enhance the rehabilitation and power assistance outcome of exoskeleton robot in more practical applications. © 2022 IEEE.

关键词： Mirrors

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：