检索结果-内蒙古大学图书馆

4th International Conference on Mechanical Design and Simulation, MDS 2024

作者： Wang, Xintong Tian, Hao Fang, Jingzhe Zhang, Hualiang Zhang, Tao Software College Shenyang University of Technology Liaoning Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China School of Electrical Engineering Shenyang University of Technology 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)9789819778867

The need for mechanical model simulation platforms is growing as a result of the ongoing advancements in digital technology and the mechanical manufacturing sector. The application scope and efficacy of simulation platforms are severely limited by the issue of sluggish rendering performance, which frequently arises when obtaining high-quality rendering. When drawing high demand mechanical models, a lot of processing power is frequently needed, which makes real-time rendering speed unsatisfactory for practical purposes. In order to achieve real-time rendering and simulation of 3D robots, this experiment built and implemented a WebGL-based 3D simulation platform. Additionally, the simulation platform can be optimized by increasing frame rate and rendering speed without sacrificing rendering effect by building a mixed bounding box. © The Author(s) 2025.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

GLAM: Global-Local Variation Awareness in Mamba-based World Model 39

GLAM: Global-Local Variation Awareness in Mamba-based World ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： He, Qian Liang, Wenqi Hao, Chunhui Sun, Gan Tian, Jiandong State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences China University of Chinese Academy of Sciences China Shenyang University of Chemical Technology China School of Automation Science and Engineering South China University of Technology China

ISBN: (纸本)157735897X

Mimicking the real interaction trajectory in the inference of the world model has been shown to improve the sample efficiency of model-based reinforcement learning (MBRL) algorithms. Many methods directly use known state sequences for reasoning. However, this approach fails to enhance the quality of reasoning by capturing the subtle variation between states. Much like how humans infer trends in event development from this variation, in this work, we introduce Global-Local variation Awareness Mamba-based world model (GLAM) that improves reasoning quality by perceiving and predicting variation between states. GLAM comprises two Mamba-based parallel reasoning modules, GMamba and LMamba, which focus on perceiving variation from global and local perspectives, respectively, during the reasoning process. GMamba focuses on identifying patterns of variation between states in the input sequence and leverages these patterns to enhance the prediction of future state variation. LMamba emphasizes reasoning about unknown information, such as rewards, termination signals, and visual representations, by perceiving variation in adjacent states. By integrating the strengths of the two modules, GLAM accounts for higher-value variation in environmental changes, providing the agent with more efficient imagination-based training. We demonstrate that our method outperforms existing methods in normalized human scores on the Atari 100k benchmark. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Status Monitoring for Packaging Equipment Based on Digital Twin System 10th

Status Monitoring for Packaging Equipment Based on Digital T...

引用

10th International Workshop of Advanced Manufacturing and automation, IWAMA 2020

作者： Shen, Nanyan Xu, Yingjie Li, Jing Ma, Zehui He, Tianqiang Li, Guiqin Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai200444 China

ISBN: (纸本)9789813363175

Digital twin realizes the interaction between the physical world and the information world, which can present the physical devices in the virtual space comprehensively and accurately. To solve the problem of internal motion monitoring of packaging equipment, the 3D visual monitoring technology based on the digital twin is studied. Based on the digital twin system framework composed of field equipment layer, data management layer, model layer, function module layer and application layer, the data model of condition monitoring for packaging equipment, kinematic modeling of typical mechanism, and method of 3D visual presentation are discussed. The kinematics model is established to analyze the posture of the packaging equipment’s mechanism, which realizes the real-time observation of the unmeasurable motion information of the complex mechanism. In addition, the system also monitors the operating parameters of packaging equipment comprehensively, which establishes the basis of equipment health evaluation. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

A Prospective Study of Haptic Feedback Method on a Lower-Extremity Exoskeleton 7th

A Prospective Study of Haptic Feedback Method on a Lower-Ext...

引用

7th International Conference on Human Aspects of IT for the Aged Population, ITAP 2021, held as part of the 23rd International Conference, HCI International 2021

作者： Wang, Yilin Qiu, Jing Cheng, Hong Wang, Lu Center for Robotics School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China Center for Robotics School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9783030781071

Medical lower-limb exoskeleton (LLE) has been developed for rehabilitation and walking assistance. However, it lacked feedback on current status to the wearer. The patients with perception lost in lower-extremity (for example, elderly people and paraplegia patients) cannot perceive their lower extremities. Therefore, haptic feedback might be necessary for them if they wear a LLE, which might inform them of current gait state. A prospective study was conducted in this paper with a purpose of designing a vibration device for a lower-extremity exoskeleton system to feed back the current walking state of the exoskeleton to wearers. Firstly, the basic tests were conducted to collect the accuracy and reaction time of subjects based on two vibration modes (strength change and position change vibration mode). Then, the subjects wore an exoskeleton with the two vibration devices to complete walking tasks and the task completion time was recorded. The accuracy of the two vibration devices can both reach about 90%, and there was no significant difference in the reaction time. It indicated that the feedback of the two devices can be well perceived by most subjects. The results of the subjective questionnaires showed that subjects prefer the strength change mode. Although there was no significant of completion time in no-feedback and vibration-feedback modes, the questionnaires showed that exoskeleton with haptic feedback can inform the wearers current state of exoskeleton and made the subjects feel safer. In the future design, LLE with vibration devices can be considered for rehabilitation and walking assistance for the elder people and the patients with motor dysfunction in lower limbs. © 2021, Springer Nature Switzerland AG.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Force feedback soft endoscope intervention mechanism and its performance evaluation in digestive tract phantom

Force feedback soft endoscope intervention mechanism and its...

引用

2022 IEEE International Conference on robotics and Biomimetics, ROBIO 2022

作者： Liu, Meng Yu, Tao Zhang, Shenglin Liu, Yumei Yang, Zhuo Liu, Hao School of Mechanical Engineering Shenyang Ligong University Shenyang China Shenyang Institute of Automation Chinese Academy of Sciences China School of Mechanics Engineering Shenyang Ligong University China General Hospital of the Northern Theater Command of the PLA State Key Laboratory of Robotics Shenyang Institute of Automation Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China Key Laboratory of Minimally Invasive Surgical Liaoning Province Shenyang110016 China

ISBN: (纸本)9781665481090

Robot-assisted digestive endoscopy intervention can solve the problems of doctor fatigue and intraoperative radiation. When doctors operate the robot, they cannot obtain the endoscope posture through the image under the microscope and lack the tactile feedback of manual operation, so they cannot accurately know the interaction force between the endoscope and human tissues. Therefore, this paper proposes an endoscope-assisted intervention robot with two-dimensional force perception, which can accurately measure axial force and rotational torque during the endoscopic intervention. The robot can be controlled by the master and slave to realize the continuous axial and circumferential motion of the endoscope. Several experiments were carried out to evaluate the operation accuracy and force detection accuracy of the robot, and an in vitro model experiment was conducted to verify the overall function of the robot. © 2022 IEEE.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

Design of a Pipeline Inside Anti-corrosion Robot Using Axiomatic Design Method

Design of a Pipeline Inside Anti-corrosion Robot Using Axiom...

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Zhiyang Wang Qifeng Wang Liang Du Mingyuan Wang Zhengtao Hu Sheng Bao Jianjun Yuan Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai China Shanghai Robotics Institute Shanghai University Shanghai China Changshu New & Hi-Tech Industrial Development Zone

ISBN: (数字)9798350372601

ISBN: (纸本)9798350372618

With the expanding of pipeline applications and development in related technologies, there is a growing requirement for inside anti-corrosion of pipelines. Currently, there is relatively limited application of robots for large-diameter pipeline inside anti-corrosion, and the design of such robots often facing coupling issues between the locomotion capability and operation requirements. In this study, an axiomatic design method is employed to analyze the design of a pipeline inside anti-corrosion robot, and a decoupling method is proposed to separate the locomotion and the anti-corrosion mechanism. The robot design is implemented with the axiomatic method. Preliminary analysis using dynamic simulation demonstrates that the robot equipped with independently adjustable steering functions works more stably and effectively during anti-corrosion operations pipelines inside.

关键词： Design methodology Prevention and mitigation Pipelines Force Wheels Spraying Real-time systems

来源：评论

学校读者我要写书评

暂无评论

GLAM: Global-Local Variation Awareness in Mamba-based World Model

arXiv

引用

arXiv 2025年

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

CSCC: Cross-Scene Crowd Counting via Learning to Diversify for Domain Generalization

引用

IEEE Transactions on Multimedia 2025年 27卷 3320-3330页

作者： Chen, Yuehai Wang, Qingzhong Yang, Jing Chen, Badong Xiong, Haoyi Du, Shaoyi Xi'an Jiaotong University School of Automation Science and Engineering Xi'an710049 China Baidu Research Beijing100085 China Xi'an Jiaotong University Institute of Artificial Intelligence and Robotics Shanxi Xi'an710049 China

It is challenging for crowd counting models to generalize to new scenes due to domain shifts in training and test data. Although domain adaptation approaches have made notable progress in bridging the domain gap, they require target domain data. In this paper, we propose a novel framework for cross-scene crowd counting, which unifies domain generalization and adaptation. For domain generalization, we train a model only using single-domain data and the model can be generalized to any scene with satisfying performance. Regarding domain adaptation, we use both source and target domain data to further improve the performance. We first design a generation network that diversifies the generated samples to cover the unseen target domains as much as possible by minimizing mutual information. This approach simulates training data in various domains, thereby enhancing the model's generalization ability. Then we develop a pixel-wise supervised contrastive loss function that pulls the human heads in the source images and generated images closer to each other and pushes them further away from the background. This loss helps extract a domain-invariant feature representation, thus improving the model's generalization ability. Moreover, if information about the target domain is available, our generalization method can be easily applied as an adaptation method by replacing the mutual information minimization loss with the mutual information maximization loss. This can further improve cross-scene crowd counting performance. The experimental results demonstrate the strong generalizability of our method across different datasets. © 1999-2012 IEEE.

关键词： Cross-Sence crowd counting Domain adaptation Domain generalization

来源：评论

学校读者我要写书评

暂无评论

Logarithmic Sliding-Mode Control for High-Precision Rigid-Body Attitude Tracking 49

Logarithmic Sliding-Mode Control for High-Precision Rigid-Bo...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Dong, Hanlin Yang, Xuebo Chen, Zhongbo Liu, Xiyao School of Automation Northwestern Polytechnical University Xi'an China Research Institute of Intelligent Control Systems Harbin Institute of Technology Harbin China College of Control Science and Engineering Bohai University Jinzhou China Northwestern Polytechnical University Research Center for Intelligent Robotics Xi'an China

ISBN: (纸本)9798350331820

The problem of high-precision attitude tracking is studied in this paper under model uncertainty and external disturbance risk. First of all, the kinematics and dynamics model of rigid body is derived based on the quaternion theory. Then, a standard logarithmic sliding-mode function is constructed using the attitude quaternion and its derivatives of the rigid spacecraft, and the corresponding logarithmic sliding-mode controller is also derived. Finally, the stability of the controlled closed-loop system is demonstrated. Consistenting with theoretical proof, the numerical simulation results showed that the controlled rigid body can quickly track its desired attitude command, even if there are model uncertainty and external disturbance risks. © 2023 IEEE.

关键词： Disturbance rejection

来源：评论

学校读者我要写书评

暂无评论

Design and experiment of a new citrus harvesting robot

Design and experiment of a new citrus harvesting robot

引用

2021 International Conference on Control Science and Electric Power Systems, CSEPS 2021

作者： Hu, Xiaomei Yu, Hefang Lv, Shunke Wu, Jun Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai200444 China

ISBN: (纸本)9781665426183

In order to solve the problem of high labour consumption and low efficiency of artificial citrus harvesting, this paper introduces the design and experiment of a new citrus harvesting robot. The robot is mainly composed of a mechanical arm and a caterpillar mobile platform. The end of the arm is equipped with a depth camera and an end effector specially designed for citrus harvesting. Coordinated control of various institutions and systems is carried out through the upper computer. The citrus harvesting robot achieves the whole process of autonomous harvesting. The success rate of the citrus harvesting robot is more than 90% and the average period of citrus harvesting is 15s/fruit tested in laboratory environment. This design of citrus harvesting robot provides a new implementation mode for the harvesting operation of the harvesting robot in natural environment. © 2021 IEEE.

关键词： End effectors

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：