检索结果-内蒙古大学图书馆

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

Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Zhu, Yuanyang Wang, Zhi Zhu, Yuanheng Chen, Chunlin Zhao, Dongbin The Department of Control Science and Intelligent Engineering School of Management and Engineering Nanjing University Nanjing210093 China The Research Center for Novel Technology of Intelligent Equipment Nanjing University Nanjing210093 China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China

For on-policy reinforcement learning, discretizing action space for continuous control can easily express multiple modes and is straightforward to optimize. However, without considering the inherent ordering between the discrete atomic actions, the explosion in the number of discrete actions can possess undesired properties and induce a higher variance for the policy gradient estimator. In this paper, we introduce a straightforward architecture that addresses this issue by constraining the discrete policy to be unimodal using Poisson probability distributions. This unimodal architecture can better leverage the continuity in the underlying continuous action space using explicit unimodal probability distributions. We conduct extensive experiments to show that the discrete policy with the unimodal probability distribution provides significantly faster convergence and higher performance for on-policy reinforcement learning algorithms in challenging control tasks, especially in highly complex tasks such as Humanoid. We provide theoretical analysis on the variance of the policy gradient estimator, which suggests that our attentively designed unimodal discrete policy can retain a lower variance and yield a stable learning process. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Improved Active Disturbance Rejection control Method for Crane System

An Improved Active Disturbance Rejection Control Method for ...

引用

Chinese control and Decision Conference, CCDC

作者： Yubo Sun Xiyuan Shan Zhicheng Zong School of Automation Beijing Institute of Technology Beijing China State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing China

ISBN: (纸本)9781665478977

In order to improve the dynamic performance of the underdriven crane system, an improved linear active disturbance rejection controller (LADRC) based on the new error was proposed. The improved LADRC takes the error value between the disturbance and its observed value multiplied by a coefficient as the basis for adjusting the linear extended state observer (LESO). The improved method has two advantages. Firstly, the new error can prevent the traditional LESO from choosing larger parameter adjustment disturbances, which will limit the performance of the observer. Secondly, the pole can be configured by adjusting the coefficient to obtain better dynamic characteristics. Finally, the effectiveness of the proposed method is verified by simulation and experiment. The proposed method can effectively restrain the swing of the payload and it is robust to system parameters perturbation as well.

关键词： Robust control Couplings Adaptation models Cranes Uncertainty Perturbation methods Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Optimal Carbon Capture, Utilization and Storage Planning for Multi-Energy System 42

Optimal Carbon Capture, Utilization and Storage Planning for...

引用

42nd Chinese control Conference, CCC 2023

作者： Hu, Aoyu Xu, Da Gao, Menglu School of Automation China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan430074 China Dc Company of State Grid Hubei Electric Power Co. Ltd. Yichang443000 China

ISBN: (纸本)9789887581543

In response to the national dual carbon policy, carbon capture, utilization and storage (CCUS) are currently attracting much attention. This paper proposes optimal CCUS planning for multi-energy system. In this multi-energy system, transmission network and natural gas network are coupled via conversion and storage devices in the energy hubs. The CCUS planning is formulated based on a source-sink matching method to analyze the CO2 capture points, CO2 storage points and CO2 transportation routes. Furthermore, the original CCUS planning problem is reformulated as a mixed integer second order cone programming (MISOCP) and subsequently solved to guarantee a satisfactory convergence performance. Numerical studies on an urban multi-energy system are implemented to verify the effectiveness and superiority of the proposed methodology over conventional scheme. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Carbon capture

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

Cascade Network with Boundary-Adaptive Filter for Surgical Gesture Recognition

Cascade Network with Boundary-Adaptive Filter for Surgical G...

引用

2021 International Joint Conference on Neural Networks, IJCNN 2021

作者： Chen H.-B. Ni Z.-L. Li Z. Bian G.-B. Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

ISBN: (纸本)9780738133669

Automatically recognizing surgical gestures plays a key role in computer-assisted surgery and automatic skill assessment. Solutions to this task that only rely on video without additional sensor hardware have attracted great attention since they are economical and feasible. However, it is still a challenging problem due to the variable gesture durations and the oversegmentation problem that occurred in a long gesture duration. To address the above problems, we propose a cascade network with boundary-adaptive filter to dynamically capture the long-range temporal dependencies and reduce the over-segmentation errors obviously. A cascade module is designed to enhance the temporal modeling abilities in different timescales, in which multiple similar temporal convolution networks are divided into cascade stages and a fusion stage. Every cascade stage with different temporal receptive fields has a frame-specific weight to adjust the distribution of each stage and they will be aggregated into the fusion stage to refine the predictions. The frame-specific model architecture may incur a more serious over-segmentation problem. A boundary-adaptive filter is designed to leverage gesture boundary information to smooth the prediction results adaptively, which maintains consistency within a gesture duration while keeping the gesture-crossing discrepancy. We evaluate our model on the JHU-ISI Gesture and Skill Assessment Working Set (JIGSAWS). The proposed method reaches the state-of-the-art frame-wise accuracy (83.79%) and comparable segment-level performance (83.35% F1@50). © 2021 IEEE.

关键词： action segmentation surgical gesture recognition temporal convolutional network video understanding

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

Asynchronous L1-gain Filtering of Nonlinear Positive Semi-Markov Jump systems with Time-varying Delays

Asynchronous L1-gain Filtering of Nonlinear Positive Semi-Ma...

引用

第41届中国控制会议

作者： Chao Ma Hang Fu Yidao Ji Wei Wu School of Mechanical Engineering University of Science and Technology State Key Lab of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

In this paper,the L-gain based filtering problem for nonlinear positive semi-Markov jump systems is investigated by proposing a novel asynchronous design *** precisely,the mode-dependent filters are designed in terms of practical observed modes instead of true system modes,such that less conservatism can be *** addition,the effect of time-varying delays is taken into account for more robustness and *** selecting suitable stochastic Lyapunov-Krasovskii functions and applying the linear programming method,sufficient conditions are established to fulfill the desired L-gain ***,the illustrative simulation is performed to verify the effectiveness of our developed control scheme.

关键词： Positive semi-Markov jump systems nonlinear semi-Markov jump systems asynchronous filtering L1-gain

来源：评论

学校读者我要写书评

暂无评论

Zero-Sum Differential Game-Based Fault-Tolerant Tracking control for Nonlinear systems With Multiplicative Failures

Zero-Sum Differential Game-Based Fault-Tolerant Tracking Con...

引用

Chinese Automation Congress (CAC)

作者： Cong Tan Mingduo Lin Hongbing Xia Bo Zhao Yancai Xu School of Systems Science Beijing Normal University Beijing China Key Laboratory of Industrial Internet of Things & Networked Control Ministry of Education Chongqing University of Posts and Telecommunications Chongqing China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

A novel fault-tolerant tracking control (FTTC) approach for affine nonlinear systems is developed from the perspective of zero-sum differential games (ZSDG) to deal with unknown multiplicative actuator failures in this paper. By regarding the control input and the multiplicative actuator failure as two players of a zero-sum game, a performance index function reflecting the trajectory tracking error, the control policy and the unknown failure is established. To handle the tracking Hamilton-Jacobi-Isaacs (HJI) equation associated with the established performance index function, a critic neural network is utilized. Then, the Nash equilibrium solution can be obtained, and the FTTC is achieved. The stability of the faulty nonlinear system is examined through Lyapunov-based approach. Finally, simulation results of a spring system is provided to ensure the utility and the realizability of the ZSDG-based FTTC approach.

关键词： Actuators Fault tolerance Trajectory tracking Simulation Fault tolerant systems Stability criteria Mathematical models

来源：评论

学校读者我要写书评

暂无评论

An IMU Error Correction Method Based on Multithreshold ZV Detection and SRCKF

An IMU Error Correction Method Based on Multithreshold ZV De...

引用

Cyber-Physical Social Intelligence (ICCSI), International Conference on

作者： Jialiang Luo Shichao Chen Yisheng Lv Wenqiao Sun Fan Yang Ruijie Xu The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences School of Information Engineering China University of Geosciences Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences The Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited Beijing China The State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Transportation and Economics Research Institute and the Center of National Railway Intelligent Transportation System Engineering and Technology China Academy of Railway Sciences Corporation Limited China The State Key Laboratory for Management and Control of Complex System State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences College of Rail Transit Shan Dong JiaoTong University Jinan China Department of Aeronautical and Aviation Engineering The Hong Kong Polytechnic University Hong Kong China

With the rapid development and widespread application of Inertial Measurement Units (IMUs), IMU-based human localization has become critically important in environments lacking Global Navigation Satellite systems (GNSS) signals. Methods such as UWB/WIFI and other anchor-based localization have been employed to enhance the positioning accuracy. However, these methods are susceptible to the environmental interference and increased costs. In contrast, SINS-based localization methods eliminate reliance on the external data. However, this method can suffer from drift errors due to cumulative integration errors. Inertial navigation error correction techniques like Zero Detection Update Technology (ZUPT) provide potential solutions to address drift errors. This paper proposes an error correction method based on the multithreshold zero-velocity detection and Square Root Cubature Kalman Filter (SRCKF) updates. Compared to the single fixed threshold detection, the multi-threshold zero-velocity detection reduces the likelihood of missed zero velocity detection and false alarms, providing accurate time intervals for error correction. Experimental results demonstrate that the SRCKF-based algorithm reduces position deviation to approximately 0.3146 meters, corresponding to an error ratio of1.14%. The proposed method enables cost-effective and accurate pedestrian localization, driving advancements in the field.

关键词：

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：