检索结果-内蒙古大学图书馆

Pattern Sensitive Prediction of Traffic Flow Based on Generative Adversarial Framework

IEEE TRANSACTIONS ON intelligent TRANSPORTATION systems 2019年第6期20卷 2395-2400页

作者： Lin, Yilun Dai, Xingyuan Li, Li Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100080 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Shandong Peoples R China Tsinghua Univ Dept Automat Tsinghua Natl Lab Informat Sci & Technol Beijing 100084 Peoples R China

Traffic flow prediction is one of the most popular topics in the field of the intelligent transportation system due to its importance. Powered by advanced machine learning techniques, especially the deep learning method, prediction accuracy noticeably increases in recent years. However, most existing methods applied a data-driven paradigm and tend to ignore the outliers, which result in poor performance while handling burst phenomena in the traffic system. To overcome this problem, the prediction model needs to recognise different patterns and handle them in different ways. In this paper. we propose a new prediction model (called pattern sensitive network) that can handle different traffic patterns automatically. By using adversarial training. our model can make more accurate predictions in unusual states without compromising its performance in usual states. Experiments demonstrate that our method can work well in both usual traffic states and unusual traffic states.

关键词： Traflic flow prediction deep learning generative adversarial network

来源：评论

学校读者我要写书评

暂无评论

Target Location and Gait Planning for Humanoid Robot Climbing Stairs 4

Target Location and Gait Planning for Humanoid Robot Climbin...

引用

4th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Zhang, Huayan Zhang, Lei Yuan, Fei Bian, Gui-Bin Xin, Shan Beijing Univ Civil Engn & Architecture Beijing Adv Innovat Ctr Intelligent Robots & Syst Beijing Key Lab Robot Bion & Funct Res Beijing 10016 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

ISBN: (纸本)9781728100647

Climbing stairs is an important ability for humanoid robots. This paper proposes a target location and gait planning method for humanoid robot climbing stairs. Target location enables the humanoid robot to accurately locate the stair position, and the gait planning algorithm makes the humanoid robot to climb the stairs. In order to enable the humanoid robot to climb multiple stairs, this paper proposes control strategy of motion for humanoid robot. The effectiveness of our proposed method was confirmed by experiments. The experimental results show that this method improves the accuracy of target location, and enables the humanoid robot Nao to climb a staircase with 2.928 cm steps.

关键词： Humanoid robots Foot Robot kinematics Trajectory Legged locomotion Planning

来源：评论

学校读者我要写书评

暂无评论

Detecting Traffic Information From Social Media Texts With Deep Learning Approaches

引用

IEEE TRANSACTIONS ON intelligent TRANSPORTATION systems 2019年第8期20卷 3049-3058页

作者： Chen, Yuanyuan Lv, Yisheng Wang, Xiao Li, Lingxi Wang, Fei-Yue Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing 100190 Peoples R China Qingdao Acad Intelligent Ind Qingdao 266109 Shandong Peoples R China Indiana Univ Purdue Univ Dept Elect & Comp Engn Indianapolis IN 46202 USA

Mining traffic-relevant information from social media data has become an emerging topic due to the real-time and ubiquitous features of social media. In this paper, we focus on a specific problem in social media mining which is to extract traffic relevant microblogs from Sina Weibo, a Chinese microblogging platform. It is transformed into a machine learning problem of short text classification. First, we apply the continuous bag-ofword model to learn word embedding representations based on a data set of three billion microblogs. Compared to the traditional one-hot vector representation of words, word embedding can capture semantic similarity between words and has been proved effective in natural language processing tasks. Next, we propose using convolutional neural networks (CNNs), long short-term memory (LSTM) models and their combination LSTM-CNN to extract traffic relevant microblogs with the learned word embeddings as inputs. We compare the proposed methods with competitive approaches, including the support vector machine (SVM) model based on a bag of n-gram features, the SVM model based on word vector features, and the multi-layer perceptron model based on word vector features. Experiments show the effectiveness of the proposed deep learning approaches.

关键词： Deep learning social transportation traffic information detection social media text mining

来源：评论

学校读者我要写书评

暂无评论

Path planning method of a humanoid robot based on a home network 4

Path planning method of a humanoid robot based on a home net...

引用

4th IEEE International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Yu, Jiayuan Zhang, Lei Bian, Gui-Bin Liu, Chenxi Beijing Univ Civil Engn & Architecture Beijing Adv Innovat Ctr Intelligent Robots & Syst Beijing Key Lab Robot Bion & Funct Res Beijing 10016 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

ISBN: (纸本)9781728100647

Human machine natural cohabitation is one of the most important way for humanoid robots to serve humans. This paper aims to improve the efficiency of the path planning system of a humanoid robot in a human robot cohabitation environment. In the proposed system, an environment map is acquired by an improved method based on visual sensors, and the mathematical model is established according to the acquired environmental information. Two improvements are made to the traditional A* algorithm for the humanoid robot's path planning. The improved algorithm can achieve the system's more efficient path planning in complex indoor environments. And the effectiveness of the proposed methods has been verified by experiments designed in actual scene.

关键词： Path planning Robot sensing systems Humanoid robots Filtering Visualization Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Effect of Compliant Passive Joint on Swimming Performance for a Multi-Joint Robotic Fish

Effect of Compliant Passive Joint on Swimming Performance fo...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Di Chen Zhengxing Wu Junzhi Yu State Key Lab Management and Control for Complex Systems Institute of Automation CAS Beijing China

In this paper, a novel compliant passive joint with two torsion springs is designed for a multi-joint robotic fish to improve propulsive performance. The motion of the multi-joint robotic fish is governed by the central pattern generator (CPG) control method. Using this multi-joint robotic fish as a testbed, the effect of compliant passive joint on swimming speed with changes in spring constant and CPG parameters such as oscillation frequency and phase difference is explored. As for the multi-joint robotic fish with a compliant passive joint, the swimming speed increases directly with the increase of oscillation frequency and the swimming speed achieved at maximum oscillation frequency increases with the decrease of phase difference. In addition, the comparison of swimming performance between robotic fish with a compliant passive joint and a fixed passive joint is made. Remarkably, the maximum swimming speed after improvement increases approximately 9.43 cm/s, corresponding to 0.17 BL/s. Experimental results reveal that adding an extra compliant passive joint can not always bring an improvement in swimming performance. Appropriate stiffness of passive joint and control parameters are needed to achieve better swimming performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Motion Optimization for a Robotic Fish Based on Adversarial Structured control

Motion Optimization for a Robotic Fish Based on Adversarial ...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Shuaizheng Yan Jian Wang Zhengxing Wu Junzhi Yu Min Tan State Key Lab Management and Control for Complex Systems Institute of Automation CAS Beijing China

This paper proposes a task-based control optimization method for the robotic fish. It is essentially an adversarial structured control consisting of a global control module and a local compensation control module. In detail, the global control module emulates an optimized central pattern generator with Evolutionary Strategy, while the local control module produces targeted compensation control signals with Soft Actor-Critic. The linear summation of two control laws works for the final robotic fish control. Considering that the evolutionary computation optimization algorithms generally have the defect of falling into the local optimum, we propose a method of antagonistic training to improve the optimization performance. The effectiveness of the designed controller is validated by simulation on agents in Mujoco. Noticeably, the simulation results demonstrate that the proposed method teaches the agent fish to move to any target point with a low energy consumption, which lays a good foundation for application of reinforcement learning in real robotic fish control.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Yaw control of a Two-Motor-Actuated Biomimetic Robotic Fish

Design and Yaw Control of a Two-Motor-Actuated Biomimetic Ro...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Sheng Du Zhengxing Wu Junzhi Yu State Key Lab Management and Control for Complex Systems Institute of Automation CAS Beijing China

This paper addresses the design and control of a novel tuna-inspired robotic fish able to realize both fast swimming and high maneuverability. A two-stage transmission mechanism is proposed, aiming at reducing the volume and mass of caudal peduncle. Benefited by it, both volumes and mass of moving parts can be reduced to allow higher swing frequency. At the same time, two joints driven by two motors ensure the flexibility of steering. The robotic fish achieves a maximum speed up to 1.65 body lengths per second (BL/s) and a minimum turning radius less than 0.35 body lengths (BL), based on the open-loop control designed by Central Pattern Generator (CPG) method. Furthermore, a yaw control is proposed to maintain course angle at high swimming speed, and simulation in Automatic Dynamic Analysis of Mechanical systems (ADAMS) software reveals the effectiveness. The results show that the proposed yaw control method can regulate the fluctuation of anterior body to desired range but without compensation of sideways drift.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Path Planning System for Smart Cars Used in Education 15

Path Planning System for Smart Cars Used in Education

引用

15th IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Xiong, Guangyu Niu, Lulu Tian, Yanfu Zhou, Jiehan Mohajeri, Babak Nyberg, Timo R. Sanya Univ USY Silk Rd Business Sch Sanya Hainan Peoples R China Chinese Acad Sci Guangdong Engn Res Ctr 3D Printing & Intelligent Cloud Comp Ctr Dongguan Peoples R China Univ Chinese Acad Sci Sch Articial Intelligence Beijing Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China Univ Oulu Oulu Finland Aalto Univ Dept Ind Engn & Management Espoo Finland

ISBN: (纸本)9781728151694

In this paper, we developed a path planning system for smart cars for teaching electronic engineering or computer science, which consists of the interactive platform for smart cars development and path planning. Designed by Visual C++, the interactive platform can call Matlab.engine, allows users to choose path optimization algorithms such as genetic or A-star(A*) algorithm for different tasks and control smart ears through serial ports. The simulation and practice demonstrate that our interactive platform can help learners to plan paths and control intelligent vehicles without specially designing a user interface.

关键词： Path planning STEAM Smart cars Genetic Algoritluu A-star(A*) algorithm

来源：评论

学校读者我要写书评

暂无评论

A two-level adaptive target recognition and tracking method based on vision for multi-robot system

A two-level adaptive target recognition and tracking method ...

引用

2019 IEEE International Conference on Robotics and Biomimetics, ROBIO 2019

作者： Ren, Liang Cao, Zhiqiang Tan, Min Zhao, Peng Chen, Xuechao University of Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems CASIA Beijing China 21st Research Institute of China Electronics Technology Group Corporation Shanghai China BIT Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing China

ISBN: (纸本)9781728163215

The vision-based target recognition and tracking have received much attention in the field of robotics. Existing methods mainly focus on the vision perception of individual robot with a single view, however, the performance is susceptible to illumination and occlusion. Multi-robot collab.rative perception provides a potential solution to deal with the limitation of single-view observation, however, the challenging of environmental adaptability for multi-robot collab.rative decision still remains unsolved. To solve this problem, this paper proposes a two-level adaptive target recognition and tracking method based on vision for multi-robot system. The problem of multi-robot target recognition and tracking is solved under a two-level framework, which contains the features fusion level of individual robot and the cooperation level of multi-robot system. In the first level, the features measuring results that influence the visual perception of individual robot are fused, while the second level combines the voting of each robot together to determine the target for multi-robot system. Both the features measuring weights and robots voting weights are adaptively updated according to their evaluation, which lead to a beneficial result where the features and robots with higher accuracy play major roles in the first and second levels, respectively. Therefore, a good adaptability to the environments can be guaranteed. The experimental results show that the proposed approach can realize the coordination of multi-robot system in target recognition and tracking with an effective performance. © 2019 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

MatchMesh: Knowledge-based 3D Point Cloud Meshing Using Divide-and-conquer Deformation

MatchMesh: Knowledge-based 3D Point Cloud Meshing Using Divi...

引用

IEEE International Conference on Networking, Sensing and control

作者： Ying Tang Shengtao Sun Ben Wu Rowan University Glassboro USA State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Smart Education Qingdao Academy of Intelligent Industries Qingdao China Rowan University Glassboro NJ USA

ISBN: (数字)9781728168555

ISBN: (纸本)9781728168562

The reconstruction of surface mesh from point cloud is compute-intensive but also very important step in the remanufacturing and personalization industries. With more 3D scanners providing lower cost and higher resolution, further detailed point clouds can be gathered without so much effort as before. In manufacturing, there are databases which contain the origin 3D design models of the products. How to utilize the design model data for swift production of related products remains a problem for remanufacturing and customization. In order to develop a knowledge-based way of handling this problem, editing or deforming an existing mesh to match the target is an effective way of easing the workload. In this paper, we introduce a divide-and -conquer process which segments the depth scan data and then find the best match in the database as its source of deformation. The segmentation is performed on 3D point level using global features extracted by 3D CNN. After that we find best match to our knowledge with the same features to acquire a fast meshing of the target object by deforming the existing parts from the match. The deformation of parts are being done sequentially. For further performance improvement, we present a deformation training method employing transfer learning on segment editing process.

关键词： Training Surface reconstruction Three-dimensional displays Databases Knowledge based systems Feature extraction Strain

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：