检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Yu, Yingying Cao, Zhiqiang Liang, Shuang Liu, Zhicheng Yu, Junzhi Chen, Xuechao Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Intelligent Robotics Institute BIT Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing100081 China

ISBN: (纸本)9781728163215

This paper presents a grasping convolutional neural network with image segmentation for mobile manipulating robot. The proposed method is cascaded by a feature pyramid network FPN and a grasping network DrGNet. The FPN network combined with point cloud clustering is used to obtain the mask of the target object. Then, the grayscale map and the depth map corresponding to the target object are combined and sent to the DrGNet network for providing multi-scale images. On this basis, depthwise separable convolution is used for encoding. The results of encoders are refined according to the light-weight RefineNet as well as sSE, which can achieve a better grasp detection. The proposed method is verified by the experiments on mobile manipulating robot. © 2019 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Fault-Tolerant control of a CPG-Governed Robotic Fish

引用

Engineering 2018年第6期4卷 861-868页

作者： Yueqi Yang Jian Wang Zhengxing Wu Junzhi Yu State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100049China University of the Chinese Academy of Sciences Beijing 100049China

Fault tolerance is essential for the maneuverability of self-propelled biomimetic robotic fish in real-world aquatic *** paper explores the fault-tolerance control problem of a free-swimming robotic fish with multiple moving joints and a stuck tail *** created control system is composed of two main components:a feedback controller and a feedforward ***,the bio-inspired central pattern generator-based feedback controller is designed to make the robotic fish robust to external disturbances,while the feedforward compensator speeds up the convergence of the overall control *** are performed for control system analysis and performance validation of the faulty robotic *** experimental results demonstrate that the proposed fault-tolerant control method is able to effectively regulate the faulty robotic fish,allowing it to complete the desired motion in the presence of damage and thereby improving both the stability and the lifetime of the real robotic system.

关键词： Fault-tolerant control Robotic fish Motion control Feedback controller Feedforward compensator

来源：评论

学校读者我要写书评

暂无评论

Motion control and Motion Coordination of Bionic Robotic Fish： A Review

引用

Journal of Bionic Engineering 2018年第4期15卷 579-598页

作者： Junzhi Yu Ming Wang Huifang Dong Yanlu Zhang Zhengxing Wu State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Information and Electrical Engineering Shandong Jianzhu University Jinan 250101 China

Fish＇s outstanding motion and coordination performance make it an excellent source of inspiration for scientists and engineers aiming to design and control next-generation autonomous underwater vehicles within the framework of bionics. This paper offers a general review of the current status of bionic robotic fish, with particular emphasis on the hydrodynamic modeling and testing, kinematic modeling and control, learning and optimization, as well as motion coordination control. Among these aspects, representative studies based on ideas and concepts inspired from fish motion and coordination are discussed. At last, the major challenges and the future research directions are addressed in the context of integration of various research streams from ichthyologic, hydrodynamic, mechanical, electronic, control, and artificial intelligence. Further development of bionic robotic fish can be utilized to execute some specific missions in complex underwater environments, where operations are unsafe or impractical for divers or conventional underwater vehicles.

关键词： bionic robotic fish motion control coordination control fish swimming learning and optimization

来源：评论

学校读者我要写书评

暂无评论

Short Term Traffic Flow Forecast Based on CM-GRU Networks

Short Term Traffic Flow Forecast Based on CM-GRU Networks

引用

IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI

作者： Zhongzheng Guo Weifeng Zhong Fenghua Zhu Xiaoshuang Li Fei-Yue Wang Gang Xiong the State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Automation Harbin University of Science And Technology Harbin China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Intelligent transportation systems (ITS) have developed for a long time. The rise of deep learning has brought new vitality of the ITS. However, traffic flow data is usually time-correlated and highly randomized. The data distribution will also change dynamically. To actualize the forecasting of traffic flow accurately, we use the historical traffic information to predict the messages of the traffic flow at any time interval. This paper proposes an efficient traffic flow forecast architecture based on deep learning. The method combines the gated recurrent unit (GRU, a type of recurrent neural network) layers and one-dimension convolution layers. Since the performance of these models has a strong dependence on hyper-parameters, this paper conducts a large-scale search of the hyper-parameter space. At the same time, experiments on flow data show that the method proposed in this paper can achieve a better prediction accuracy. Experiments also show lower test errors compared with the existing approaches.

关键词： Feature extraction Predictive models automation Logic gates Convolution Training complex systems

来源：评论

学校读者我要写书评

暂无评论

Reveal of domain effect: How visual restoration contributes to object detection in aquatic scenes

arXiv

引用

arXiv 2020年

作者： Chen, Xingyu Lu, Yue Wu, Zhengxing Yu, Junzhi Wen, Li State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science BIC-ESAT College of Engineering Peking University Beijing100871 China School of Mechanical Engineering and Automation Beihang University Beijing100191 China

Underwater robotic perception usually requires visual restoration and object detection, both of which have been studied for many years. Meanwhile, data domain has a huge impact on modern data-driven leaning process. However, exactly indicating domain effect, the relation between restoration and detection remains unclear. In this paper, we generally investigate the relation of quality-diverse data domain to detection performance. In the meantime, we unveil how visual restoration contributes to object detection in real-world underwater scenes. According to our analysis, five key discoveries are reported: 1) Domain quality has an ignorable effect on within-domain convolutional representation and detection accuracy;2) low-quality domain leads to higher generalization ability in cross-domain detection;3) low-quality domain can hardly be well learned in a domain-mixed learning process;4) degrading recall efficiency, restoration cannot improve within-domain detection accuracy;5) visual restoration is beneficial to detection in the wild by reducing the domain shift between training data and real-world scenes. Finally, as an illustrative example, we successfully perform underwater object detection with an aquatic robot. Copyright © 2020, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Research on Trajectory Planning and Motion control of 7-DoF Sawyer Manipulator

Research on Trajectory Planning and Motion Control of 7-DoF ...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Kun Luo Gang Xiong Yuxiao Wang Bin Hu Sheng Liu Shichao Chen The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijng China School of Artificial Intelligence University of Chinese Academy of Sciences Beijng China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Beijng China Qingdao Academy of Intelligent Industries Chinese Academy of Sciences Beijng China

Regarding human-machine collaborative task, generated trajectories of a robot manipulator should be able to avoid joint limits and singularities, but the 6 Degrees of Freedom(DoF) or lower DoF manipulators encounter difficulties in many schemes. In this paper, research is implemented on the methods of trajectory planning and motion control on the newly human-machine collaborative 7-DoF Sawyer manipulator. We try to pay more attention to these approaches and find a better combination between trajectory planners and motion controllers for Sawyer manipulator. First of all, comparison is proposed between the methods about trajectory planning in task space and joint space, drawing a conclusion that the latter has the advantage of quickness and smoothness on trajectories in real time. Next, we choose to plan trajectory in the joint space by interpolating positions and orientations. Three approaches, i.e., trapezoidal velocity trajectory, cubic polynomial trajectory and basic spline trajectory, are applied to interpolate positions. Experimental results show that it results in the smoothest trajectory using basic spline trajectory planning. We also compare linear and nonlinear orientation interpolations to address the angle wrapping issue, which leads to difficulties in smooth orientation interpolation between several waypoints. Combining polynomial trajectory planning methods with the proportional-derivative (PD) motion controller and the computed-torque motion controller, we focus on the performance of the two different combinations. It is found that trajectories with computed-torque controller have shorter path with a congruous convergence on joint position, and more accurate trajectories with less overshoots in position than others.

关键词： Interpolation Trajectory planning Collaboration Aerospace electronics Manipulators Trajectory Task analysis

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning based Lane Change Decision-Making with Imaginary Sampling

Reinforcement Learning based Lane Change Decision-Making wit...

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： Dong Li Dongbin Zhao Qichao Zhang The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728124858

ISBN: (纸本)9781728124865

This paper investigates the autonomous driving lane change problem with reinforcement learning methods. A two-stage control method is proposed which includes a decision-making module computing the high-level lane change action and a lateral control module outputting the low-level steering angle. Due to the decoupling system framework, the proposed controller can flexibly cancel the previous improper lane change command. To improve the data efficiency in the lateral control module, the Gaussian process is employed to modeling the local time-interval system models. These models are used to generate imaginary samples and facilitate the reinforcement learning training process. The lateral control experiments show that the imaginary samples can improve the data efficiency and speed up the training process. Finally, the two-lane scene and three-lane scene experiments validate the effectiveness of the proposed two-stage lane change method.

关键词： Decision making Learning (artificial intelligence) Gaussian processes Uncertainty Estimation Autonomous vehicles Roads

来源：评论

学校读者我要写书评

暂无评论

Double Deep Q-learning for Anti-saturation Attack Problem of Warship Group

Double Deep Q-learning for Anti-saturation Attack Problem of...

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Wei Li Gang Xiong Hao Tao Yunjun Han Fang Wang Xisong Dong Zhen Shen State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences China China Ship Development and Design Center Wuhan China School of Control Science and Engineering (CSE) Shandong University Jinan China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

Anti-saturation attack (ASA) strategy is vital for the survival of a warship group, and attracts the focus of many researchers. In this paper, the dynamics of ASA is formulated as a Markov Decision Process (MDP) with an enhanced states space since those characters are involved, such as the formation and detection and interception areas of warship group. A reinforcement learning method (Double Deep Q-leaning, DDQN) is developed to solve the problem and deal with the curse of dimensionality whereby the cost-to-go value is calculated by a marine engagement simulation system. A heuristic defense algorithm guided by field expert knowledge is designed for comparison. The experimental results show that the DDQN method performs better in anti-saturation attack scenarios.

关键词： Industries Heuristic algorithms Digital twin Conferences Knowledge based systems Reinforcement learning Markov processes

来源：评论

学校读者我要写书评

暂无评论

3D Printer Optical Detection System Based On DLP Projection Technology

3D Printer Optical Detection System Based On DLP Projection ...

引用

Chinese automation Congress (CAC)

作者： Guoliang Wu Zhen Shen Xiuqin Shang Huaiyu Wu Gang Xiong Jing Yang The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

In order to solve the printing failure caused by the projection part of the light source in the 3D printing process, this paper proposes a system adjustment scheme. By analyzing the polymerization state of the photosensitive resin, detecting the intensity of ultraviolet light, extracting the outline of the picture, and comparing the similarity of the picture, the optical detection system can find out the cause of the printing failure and provide us with advice on how to adjust the system to ensure that the system can continue to be normal. In the following, the authors proposed the detection process of the system, and simulated the experiment to confirm whether the ultraviolet light irradiated on the photosensitive resin is the same as the image in the slice file.

关键词： Resins Lenses Light sources Three-dimensional printing Printers Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Spread-gram: A spreading-Activation schema of network structural learning

arXiv

引用

arXiv 2019年

作者： Bai, Jie Li, Linjing Zeng, Daniel State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Network representation learning has exploded recently. However, existing studies usually reconstruct networks as sequences or matrices, which may cause information bias or sparsity problem during model training. Inspired by a cognitive model of human memory, we propose a network representation learning scheme. In this scheme, we learn node embeddings by adjusting the proximity of nodes traversing the spreading structure of the network. Our proposed method shows a significant improvement in multiple analysis tasks based on various real-world networks, ranging from semantic networks to protein interaction networks, international trade networks, human behavior networks, etc. In particular, our model can effectively discover the hierarchical structures in networks. The well-organized model training speeds up the convergence to only a small number of iterations, and the training time is linear with respect to the edge numbers. Copyright © 2019, The Authors. All rights reserved.

关键词： Embeddings

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：