Shenyang Institute of Automation,Chinese Academy Of Sciences
Not a member yet
23582 research outputs found
Sort by
基于工业边缘计算系统的多维异构资源量化方法及装置
No full text本发明属于工业互联网领域，具体说是一种基于工业边缘计算系统的多维异构资源量化方法及装置。包括：获取多维异构资源信息与混合任务流信息；根据多维异构资源，分析多维资源与边缘计算设备实时算力的关系；根据任务流信息，分析不同种类任务执行所需算力；判断任务算力需求与异构边缘计算设备实时算力供给契合程度，实时算力供给是否满足任务算力需求，对多维资源与边缘计算设备实时算力的关系进行增量学习，不断提高量化准确度。本发明提高了工业边缘计算系统中零散异构资源的整体利用率，降低了网络通信负载及私密数据交互，对工业互联网个性化柔性生产起到支撑作用
Multi-agent deep reinforcement learning for end-edge orchestrated resource allocation in industrial wireless networks
No full textEdge artificial intelligence will empower the ever simple industrial wireless networks (IWNs) supporting complex and dynamic tasks by collaboratively exploiting the computation and communication resources of both machine-type devices (MTDs) and edge servers. In this paper, we propose a multi-agent deep reinforcement learning based resource allocation (MADRL-RA) algorithm for end-edge orchestrated IWNs to support computation-intensive and delay-sensitive applications. First, we present the system model of IWNs, wherein each MTD is regarded as a self-learning agent. Then, we apply the Markov decision process to formulate a minimum system overhead problem with joint optimization of delay and energy consumption. Next, we employ MADRL to defeat the explosive state space and learn an effective resource allocation policy with respect to computing decision, computation capacity, and transmission power. To break the time correlation of training data while accelerating the learning process of MADRL-RA, we design a weighted experience replay to store and sample experiences categorically. Furthermore, we propose a step-by-step epsilon-greedy method to balance exploitation and exploration. Finally, we verify the effectiveness of MADRL-RA by comparing it with some benchmark algorithms in many experiments, showing that MADRL-RA converges quickly and learns an effective resource allocation policy achieving the minimum system overhead
Multi-objective Optimization Design of Structural Parameters for a Crawler Type Snake-like Rescue Robot with Active Joint
No full text针对机器人化救援装备研制的难点，对具备肌肉注射功能的蛇形机器人结构参数进行了优化，进而解决了废墟非结构环境对机器人执行任务的约束问题。首先，在分析机器人废墟环境运动机理基础上，建立机器人运动性能与结构参数的函数模型。然后，利用基于非支配排序的NSGA-II和基于分解的MOEA-D多目标遗传算法2种方式对模型分别进行求解。通过对比2种方式，证明了NSGA-II算法在求解上更有效，最终确定机器人样机的最优结构设计参数。最后，根据优化结果研制了实验用的蛇形机器人样机。实验结果显示机器人的最大台阶翻越高度为0.18 m，相对误差为0%；最大沟壑跨越宽度为0.4 m，相对误差2.3%；直线构形最小转向阻力矩为14.320 N·m，相对误差11.2%。验证了基于NSGA-II算法的结构参数多目标优化设计方法的有效性。</p
Soft Exoskeleton With Fully Actuated Thumb Movements for Grasping Assistance
No full textIt has been clinically proven that exoskeletons are effective self-training rehabilitation or daily living assistance devices for patients with hand dysfunctions. However, exoskeleton-assisted hand exercises with high degrees-of-freedom are considered as challenging tasks because the digit space, especially the thumb, cannot accommodate enough actuators. In this article, we report a tendon-driven soft hand exoskeleton with a hybrid configuration for thumb actuation. The soft hand exoskeleton system uses the least number of actuators to realize full degrees-of-freedom actuation for all digits. It is tested on a stroke patient with hemiplegia and a healthy subject. The experimental results show that the hand exoskeleton could assist the stroke patient to accomplish various training tasks, such as thumb encircling, grasping, pinching, releasing, and writing. It was found that digit trajectories and joint angle changes of the stroke patient were close to those of the healthy subject. Especially, the range of motion of the stroke patient shows significant improvement with the hand exoskeleton assistance compared to that without the hand exoskeleton assistance. The research in this article paves the way to develop fully actuated soft hand exoskeleton that can be eventually integrated with an electroencephalogram or electromyography for self-training rehabilitation or daily living assistance.</p
Correlative AFM and Scanning Microlens Microscopy for Time-Efficient Multiscale Imaging
No full textWith the rapid evolution of microelectronics and nanofabrication technologies, the feature sizes of large-scale integrated circuits continue to move toward the nanoscale. There is a strong need to improve the quality and efficiency of integrated circuit inspection, but it remains a great challenge to provide both rapid imaging and circuit node-level high-resolution images simultaneously using a conventional microscope. This paper proposes a nondestructive, high-throughput, multiscale correlation imaging method that combines atomic force microscopy (AFM) with microlens-based scanning optical microscopy. In this method, a microlens is coupled to the end of the AFM cantilever and the sample-facing side of the microlens contains a focused ion beam deposited tip which serves as the AFM scanning probe. The introduction of a microlens improves the imaging resolution of the AFM optical system, providing a 3-4x increase in optical imaging magnification while the scanning imaging throughput is improved approximate to 8x. The proposed method bridges the resolution gap between traditional optical imaging and AFM, achieves cross-scale rapid imaging with micrometer to nanometer resolution, and improves the efficiency of AFM-based large-scale imaging and detection. Simultaneously, nanoscale-level correlation between the acquired optical image and structure information is enabled by the method, providing a powerful tool for semiconductor device inspection
一种水下腿履复合爬行底盘及应用其的水下机器人
No full text本发明公开了一种水下腿履复合爬行底盘及应用其的水下机器人，涉及水下移动设备技术领域，解决了现有的水下机器人遇到障碍物时一般需要转向后绕开，由于其无法快速地跨过该障碍物，因此其缺乏在水中快速躲避障碍并保持快速行驶能力的问题，其技术方案要点是，包括：主架体、行驶机构、具有折叠状态和展开状态的折叠机构，其中折叠机构包括：第一转动装置、第一连杆、第二转动装置、第二连杆；第一连杆与第一转动装置传动连接；第二连杆与第二转动装置传动连接，第一连杆与第二连杆转动连接，本发明提供了一种新的水下快速移动的具体实施方式，其带可折叠式收纳功能、具有良好躲避障碍物能力、良好通过性、自由度高、结构简单、便于生产制造的优点
一种基于云边协同的配电台区分级线损分析系统
No full text本发明提出的是一种基于云边协同的配电台区分级线损分析系统。包括云端线损分析平台、边端智能融合终端和电能数据采集终端。电能数据采集终端负责采集台区各个关键节点处的用电信息，并把采集的信息传送给边缘侧的智能融合终端，智能融合终端负责在边缘侧计算台区拓扑，并依据拓扑信息分级计算线损，云端的线损分析平台用于对边缘侧的拓扑信息进行校核以及依据边缘侧分级线损计算值，进行区域线损计算、异常线损点定位和窃电分析等线损精益化管理。本发明能够实现“变压器‑低压出线”、“低压出线与分支箱”、“分支箱与表箱”、“表箱与户表”的多级线损核算与分析方法，充分利用现有设备，成本低，易实现，从而实现配电台区的区域“自治”
一种基于脑电和视觉的水下机械手控制系统及方法
No full text本发明涉及水下机器人人机交互技术领域，尤其涉及一种基于脑电和视觉的水下机械手控制系统及方法。包括：脑电采集装置、视觉采集装置、刺激诱发模块、脑电处理模块、视觉处理模块、脑电视觉融合模块、机械手驱动模块以及多个液压机械手；脑电采集装置，用于采集脑电信号；视觉采集装置，用于实时捕捉瞳孔图像；脑电处理模块，用于处理脑电数据，判断出当前操作人员注视的色块图像；视觉处理模块，用于判断出当前操作人员视线焦点对应的色块图像；脑电视觉融合模块，用于将脑电处理模块与视觉处理模块的判断结果对比，得到机械手操作指令；本发明使用脑电和视觉信息完成命令选择及命令确认和撤销，提高了控制结果的正确率，保证可靠性
A Unified Framework for Large-Scale Occupancy Mapping and Terrain Modeling Using RMM
No full textBuilding suitable representations for diversified environments to enable robot autonomous navigation is a complicated task, especially for large-scale environments, where the captured vast amount of data will give rise to computation and storage bottlenecks. In this letter, we first propose the random mapping method (RMM), which can efficiently project the irregular points in the low-dimensional data set into the high-dimensional one, where the points are approximately linearly separable or distributed. In the mapped space, we then propose a unified environment modeling framework in the form of linear parametric model, which can represent the occupancy maps and terrain models consistently. Adopting the idea of parallel computing, we then apply our method to the large-scale environment modeling to reduce the wall-clock time of calculation without losing much accuracy. Experiments were fully conducted to evaluate the proposed random mapping method and the proposed environmental modeling method, show ing their better comprehensive performance compared to the typical methods and state-of-the-art methods
A low-cost single-motor-driven climbing robot based on overrunning spring clutch mechanisms
No full textForestry monitoring and high-voltage cable inspection demand on low-cost climbing robots. The proposed climbing robot has simple control and low cost, enabling loaded, which drives by a single motor. Based on the overrunning spring clutch mechanisms, two motions of holding and climbing are realized by one motor. A rope-driven gripper is for adaptive enveloping holding effectively and a thron wheel is used to attach the climbing surface and stable climbing. The design parameters of the overrunning spring clutch mechanism and the rope-driven gripper are determined. The prototype and experiment setup are built. The enveloping holding experiment is carried out to verify the holding stability and shape adaptability of the rope-driven gripper. The trunk and pipe climbing experiments verify the climbing performance of the climbing robot and its application prospects with a certain load. In the future, as a low-cost climbing robot, a camera or operating mechanism can be equipped for tasks