检索结果-内蒙古大学图书馆

Prototypical Context-Aware Dynamics for Generalization in visual control With Model-Based Reinforcement Learning

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2024年第9期20卷 10717-10727页

作者： Wang, Junjie Zhang, Qichao Mu, Yao Li, Dong Zhao, Dongbin Zhuang, Yuzheng Luo, Ping Wang, Bin Hao, Jianye Chinese Acad Sci Inst Automat Key Lab Multimodal Artificial Intelligence Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100049 Peoples R China Univ Hong Kong Hong Kong 100085 Peoples R China Huawei Technol Noahs Ark Lab Beijing 100085 Peoples R China Tianjin Univ Coll Intelligence & Comp Tianjin 300350 Peoples R China

The latent world model, which efficiently represents high-dimensional observations within a latent space, has shown promise in reinforcement learning-based policies for visual control tasks. Due to a lack of clear environmental context comprehension, its applicability in a variety of contexts with unknown dynamics is constrained. We propose a prototypical context- aware dynamics (ProtoCAD) model to address this issue. This model captures local dynamics using temporally consistent latent contexts and aids generalization in visual control tasks. By grouping prototypes over historical experiences, ProtoCAD collects useful contextual information that improves model-based reinforcement learning dynamics generalization in two ways. First, to guarantee the consistency of prototype assignments for various temporal segments of the same latent trajectory, a temporally consistent prototypes regularizer is used. Then, a context representation is devised to combine the aggregated prototype with the projection embedding of latent states. According to extensive trials, ProtoCAD outperforms competing approaches in terms of dynamics generalization for visual robotic control and autonomous driving applications.

关键词： Context-aware dynamics generalization model-based reinforcement learning visual control

来源：评论

学校读者我要写书评

暂无评论

Freehand Interaction With visual control and Haptic Feedback in Electromagnetically Assisted Interventional Surgery

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第24期11卷 40845-40860页

作者： Deng, Xutian Zhao, Jianhui Yuan, Zhiyong Li, Miao Du, Bo Yang, Zhijian Wuhan Univ Sch Comp Sci Wuhan 430072 Hubei Peoples R China Wuhan Univ Sch Microelect Wuhan 430072 Hubei Peoples R China Wuhan Univ Inst Technol Sci Wuhan 430072 Hubei Peoples R China Wuhan Univ Sch Math & Stat Wuhan 430072 Hubei Peoples R China

Internet of Medical Things (IoMT) technology has significantly helped surgeons perform complex clinical procedures, including interventional and endoscopic surgeries. However, surgeons face challenges in quickly becoming proficient with some IoMT devices. This difficulty stems from the fact that IoMT devices are not commonly used or familiar in their daily work and lives. To address this issue, we propose a novel interactive framework for IoMT, named freehand interaction, which includes visual control and haptic feedback. Our idea is to allow surgeons to operate surgical instruments, such as needles, capsules, and catheters with their bare hands and regular experience. At the same time, identical instruments in the surgical environment mirror the surgeon's actions through visual control. The interactive forces encountered in the surgical environment are quantitatively communicated to the surgeon through the hand-held instruments. Our IoMT framework achieves both visual control and haptic feedback using electromagnetic mechanisms, ensuring mid-air freehand manipulation and contactless remote actuation. We perform different tasks in suspended, liquid, and in-vitro environments. The hand-held and mirroring instruments show high similarity and correlation, even within different electromagnetic systems and confined workspaces. Tracking accuracy, response time, and haptic forces quantified by a mechanical gauge are satisfactory. Our algorithm processes raw video streams and maintains efficiency even in scenarios with partial hand occlusion and various types of image noise. In summary, this work contributes to improving visual intuition and haptic immersion in IoMT applications.

关键词： Haptic interfaces Surgery Instruments visualization Motors Continuum robots Robots Electromagnetics freehand interaction haptic feedback Internet of Medical Things (IoMT) visual control

来源：评论

学校读者我要写书评

暂无评论

MODEL-BASED visual control FOR ROBOTIC MANIPULATORS USING UDWADIA KALABA FORMULATION

MODEL-BASED VISUAL CONTROL FOR ROBOTIC MANIPULATORS USING UD...

引用

ASME International Mechanical Engineering Congress and Exposition (IMECE)

作者： Morgan, Edward Ard, William Barbalata, Corina Louisiana State Univ Baton Rouge LA 70803 USA

ISBN: (纸本)9780791887639

This work presents the development of a model-based visual control strategy for robotic manipulators performing target tracking. The proposed approach leverages fiducial-based techniques for target identification with the Udwadia-Kalaba (UK) formulation for constrained robotic motion control. Using Baumgarte's approach leads to a model-based visual control strategy capable of stable behavior when discontinuities are present in the desired trajectory that the robot has to follow, as well as when there are uncertainties in the dynamic model of the system. The control strategy is tested in simulation with a 4-DOF Reach Alpha 5 manipulator using real-world visual target tracking. The qualitative and quantitative evaluation of the strategy shows its capabilities in accurately tracking the desired trajectories.

关键词： robotics manipulation control udwadia kalaba visual control

来源：评论

学校读者我要写书评

暂无评论

Study on visual control system of acoustic in situ measurement technology for survey of seafloor sediment

引用

MARINE GEORESOURCES & GEOTECHNOLOGY 2020年第3期38卷 363-373页

作者： Lv, Bin Qi, Guo-liang Li, Guan-bao Kan, Guang-ming Wang, Jing-qiang Liu, Jie Qilu Univ Technol Shandong Acad Sci Inst Oceanog Instrumentat Qingdao Shandong Peoples R China State Ocean Adm Inst Oceanog 1 Qingdao Shandong Peoples R China

A new kind of visual acoustic measurement system was developed to obtain the acoustic characteristics of seabed sediment and the working state of in situ measuring equipment in real time. The control unit of the system structure is mainly made up of the underwater control unit and the deck control unit. In comparison with similar traditional systems, the system can transmit the working video image, the measured acoustic data and the waveform synchronous from the underwater control equipment to the deck control unit through the connecting cable. Apart from self-contained in situ measurement, the working modes of it include visual online real-time control. In order to guarantee the stability and measurement precision of the video control system, the process control of in situ measurement was strictly tested in the experimental tank. In 2017, sea trials of the in situ measurement system was carried out in the South China Sea. In the process, data related to measurement, including the acoustic velocity and attenuation coefficient of the seabed sediment, were obtained as well. The results from sea trials show that the control process of the visual system is intuitive, reliable and accurate, and therefore it can be popularized and applied.

关键词： In situ measurement of the control system sound speed sound attenuation coefficient seafloor sediments visual control

来源：评论

学校读者我要写书评

暂无评论

visual control Based Musculotendon Force Estimation in the Human Upper-Limb

Visual Control Based Musculotendon Force Estimation in the H...

引用

29th International Conference on Robotics in Alpe-Adria-Danube Region (RAAD)

作者： Baklouti, Souha Jemaa, Olfa Bennour, Sami Univ Sousse Lab Mech Sousse LMS Bp 264 Erriadh Sousse 4023 Tunisia

ISBN: (纸本)9783030489915;9783030489892;9783030489885

This paper deals with an upper-limb muscle forces estimation method using Kinect camera. This latter provides 3-D information of the upper limb trajectory, which serves as an input of the kinetic model of the upper-limb. Estimation methods are used to determine the muscle force from the torque output of the inverse dynamics. An EMG-based forward dynamics model is used for validation purposes. Experimental results on a human being validate the proposed visual tracking upper-limb muscle forces estimation method.

关键词： visual control EMG Upper-limb Musculotendon force

来源：评论

学校读者我要写书评

暂无评论

Non-contact visual control of personalized hand prostheses/exoskeletons by tracking using augmented reality glasses

引用

3D PRINTING IN MEDICINE 2020年第1期6卷 1-3页

作者： Hazubski, Simon Hoppe, Harald Otte, Andreas Offenburg Univ Lab Comp Assisted Med Badstr 24 D-77652 Offenburg Germany Offenburg Univ Div Med Engn Lab NeuroSci Dept Elect Engn Med Engn & Comp Sci Badstr 24 D-77652 Offenburg Germany

A new concept for robust non-invasive optical activation of motorized hand prostheses by simple and non-contact commands is presented. In addition, a novel approach for aiding hand amputees is shown, outlining significant progress in thinking worth testing. In this, personalized 3D-printed artificial flexible hands are combined with commercially available motorized exoskeletons, as they are used e.g. in tetraplegics.

关键词： Personalized prostheses 3D-print visual control Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Independent Feeding of People Affected with Osteoarthritis Through a Didactic Robot and visual control

Independent Feeding of People Affected with Osteoarthritis T...

引用

Multidisciplinary International Conference of Research Applied to Defense and Security (MICRADS)

作者： Jimenez, Arturo Aroca, Katherine Hallo, Vicente Velasco, Nancy Mendoza, Dario Univ Fuerzas Armadas ESPE Dept Energia & Mecan Sangolqui Ecuador Univ Fuerzas Armadas ESPE Dept Ciencias Exactas Sangolqui Ecuador

ISBN: (纸本)9789811391552;9789811391545

This chapter presents a work that will help in the consumption of the food of people with osteoarthritis. In this way, the patient will avoid discomfort in the joints of their hands. The system consists of an artificial vision algorithm and independent feeding part. The vision algorithm allows the detection of the face, localization, and tracking the person's mouth. The independent feeding part consists of a didactic robotic arm. The robotic arm takes the food from the dish. The vision algorithm detects and tracks the face, then locates the position of the mouth. Finally, the robotic arm delivers the food to the user. The program was developed in Python using OpenCV and Dlib libraries. The face alignment method has an average of 94% of effectiveness.

关键词： visual control Recognition and monitoring Robot feeding people Osteoarthritis

来源：评论

学校读者我要写书评

暂无评论

A Stage-wise Stationary Monocular visual control Method for Assembly Robot

引用

RECENT ADVANCES IN ELECTRICAL & ELECTRONIC ENGINEERING 2018年第3期11卷 274-279页

作者： Hu, Xiaoping Xiao, Dongming Hunan Univ Sci & Technol Hunan Prov Key Lab Hlth Maintenance Mech Equipmen Xiangtan Peoples R China

Background: The stationary monocular visual control is a major mode of robot assembly. In this mode, the viewing field is stationary and the target is not detached. Methods: Self-calibration based on the fundamental matrix is first performed on the camera to obtain its linear interior parameters in this paper. Next, a novel stage-wise visual control method is proposed, which adopts different control strategies at different stages. Results: The location-based visual control strategy is used for the vertical plane, and the image-based visual control strategy is used for the horizontal plane. Guidance experiment is then conducted to verify the accuracy and effectiveness of the proposed control method.

关键词： Assembling robot visual control stationary monocular vision PID control stage-wise control strategy fusion controller

来源：评论

学校读者我要写书评

暂无评论

Design of a visual control Based using Optical Flow for a Ball-Riding Robot 17

Design of a Visual Control Based using Optical Flow for a Ba...

引用

17th Annual International Conference on Electronics, Information, and Communication (ICEIC)

作者： Songkrasin, Konlayut Sukvichai, Kanjanapan Wongsuwan, Kandith Chayopitak, Nattapon Koike, Yasuharu Kasetsart Univ Dept Elect Engn Bangkok Thailand Natl Elect & Comp Technol Ctr Pathum Thani Thailand Tokyo Inst Technol Tokyo Japan

ISBN: (纸本)9781538647547

Characteristic of the ball-riding robot is always fascinating humans. It can be developed for serving human in several applications. In order to operate the ball-riding robot for the intelligent tasks, an image processing and computer vision are required to be implemented into the robot system while stabilization is still needed. To prevent the cause of serious issue for implementing into a robot, the simulation is best testing tool that can evaluate robot performance before conduct a real implementation. A visual odometry estimation via homography is used to estimate the robot leaning angles, and used as a feedback data for a robot balancing controller. In this research, the simulation is implemented in Gazebo simulator, the ball-riding robot model is added into the Gazebo environment with a RGB camera, Inertial Measurement Unit (IMU) and quadrature encoder sensor. The low-level LQR+I controller and the visual odometry estimation are implemented into simulator by using Robot Operating System (ROS) node and communicating with Gazebo via publisher/subscriber protocol.

关键词： Ball-riding robot visual control visual odometry Gazebo LQR plus I ROS

来源：评论

学校读者我要写书评

暂无评论

Now you see me. An assessment of the visual recognition and control of individuals in archaeological landscapes

引用

JOURNAL OF ARCHAEOLOGICAL SCIENCE 2019年 104卷 56-74页

作者： Fabrega-Alvarez, Pastor Parcero-Oubina, Cesar CSIC Spanish Natl Res Council Inst Heritage Sci Incipit Ave Vigo S-N Santiago De Compostela 15705 Spain

Visibility analysis has become extremely popular in landscape-oriented archaeology in recent decades and has become even more widespread with the popularization of GIS tools, which have multiplied the ways in which visual perception can be analysed and digitally modelled. Visibility has been used as a proxy for different archaeological approaches, from the analysis of subjective perception to the assessment of strategic control. While interest has most often been focused on how objects, features and sites are perceived, there has also been an interest in how visual control is exerted from archaeological sites or other places in the landscape. Within the latter approaches, the distances at which visual control can be exercised have usually been determined in a more or less arbitrary manner, without a clear and empirically informed reference on how things and, especially, people can be observed and recognized differently at a distance. In this paper, we present the results of a field experiment carried out to measure the distances at which individuals can be spotted, recognized and identified with the naked eye in favourable conditions. Based on these results, we introduce the concept of Individual Distance Viewshed (IDV) as a GIS-based representation of visual control. This will serve as a reference to better qualify potential visibility in landscape analysis. Finally, we illustrate the applicability of this approach with a case study which explores the relationship between visual control and mobility during the Iron Age in the NW of the Iberian Peninsula.

关键词： Visibility Landscape visual control Perception Distance GIS Viewshed Iron Age NW Iberian Peninsula

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：