检索结果-内蒙古大学图书馆

Transformer-Based Macroscopic Regulation for High-Speed Railway Timetable Rescheduling

IEEE/CAA Journal of Automatica Sinica 2023年第9期10卷 1822-1833页

作者： Wei Xu Chen Zhao Jie Cheng Yin Wang Yiqing Tang Tao Zhang Zhiming Yuan Yisheng Lv Fei-Yue Wang Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Signal&Communication Research Institute China Academy Railway SciencesBeijing 100081China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049 State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China IEEE State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190 Macao Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

Unexpected delays in train operations can cause a cascade of negative consequences in a high-speed railway *** such cases,train timetables need to be ***,timely and efficient train timetable rescheduling is still a challenging problem due to its modeling difficulties and low optimization *** paper presents a Transformer-based macroscopic regulation approach which consists of two stages including Transformer-based modeling and policy-based ***,the relationship between various train schedules and operations is described by creating a macroscopic model with the Transformer,providing the better understanding of overall operation in the high-speed railway ***,a policy-based approach is used to solve a continuous decision problem after macro-modeling for fast *** experiments on various delay scenarios are *** results demonstrate the effectiveness of the proposed method in comparison to other popular methods.

关键词： High-speed railway reinforcement learning train timetable rescheduling Transformer

来源：评论

学校读者我要写书评

暂无评论

Multi-functional motion control and simulation of a large unmanned mobile manipulator for autonomous grasping scenes 41

Multi-functional motion control and simulation of a large un...

引用

第41届中国控制会议

作者： Wei Ma Yirong Liu Rongsheng Wang Fang Fang Bo Zhou Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSoutheast University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Mobile manipulator can perform complex operation tasks in a larger workspace,and has great application potential in practical *** at a large unmanned mobile manipulator for autonomous grasping scenes,this paper realizes its multi-functional motion control and ***,this paper analyzes the kinematics models of the manipulator and mobile base,and describes them with D-H parameters;The whole-body kinematics model of the mobile manipulator is obtained by integrating the mobile base and the ***,in order to meet the requirements of path planning and motion simulation of mobile manipulator in different scenarios,this paper designs three different simulation modes and realizes the simulation in virtual environment,the simulation combining actual controller and virtual robot and the simulation of digital twin ***,different experiments are designed to verify the feasibility and effectiveness of the three simulation methods.

关键词： mobile manipulation whole-body model path planning motion simulation digital twin system

来源：评论

学校读者我要写书评

暂无评论

Foundation Vehicles: From Foundation Intelligence to Foundation Transportation for Future Mobility

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2023年 1-5页

作者： Wang, Fei-Yue Lv, Chen The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Mechanical and Aerospace Engineering Nanyang Technological University Singapore

来源：评论

学校读者我要写书评

暂无评论

Can ChatGPT Boost Artistic Creation:The Need of Imaginative Intelligence for Parallel Art

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 835-838页

作者： Chao Guo Yue Lu Yong Dou Fei-Yue Wang The State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Institute of Systems Engineering Macao University of Science and TechnologyMacao 999078China

CHATGPT,one of the leading Large Language Models(LLMs),has acquired linguistic capabilities such as text comprehension and logical reasoning,enabling it to engage in natural conversations with humans.

关键词： such has reasoning

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

引用

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 231-239页

作者： Yahui Liu Bin Tian Yisheng Lv Lingxi Li Fei-Yue Wang the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190 the School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190 IEEE the Transportation and Autonomous Systems Institute(TASI)and the Department of Electrical and Computer Engineering Purdue School of Engineering and TechnologyIndiana University-Purdue University Indianapolis(IUPUI)Indianapolis 46202 USA

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://***/yahuiliu99/PointC onT.

关键词： Content-based Transformer deep learning feature aggregator local attention point cloud classification

来源：评论

学校读者我要写书评

暂无评论

End-point Steady control for Whole-Body control Mobile Manipulators by Null Space Tunation 8

End-point Steady Control for Whole-Body Control Mobile Manip...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Zhang, Enjin Gan, Yahui Dai, Xianzhong School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education NanJing China

ISBN: (纸本)9798350300178

This paper deal with the end-point steady control problem of a mobile manipulators(MM) at the velocity level. Mobile manipulators are usually kinematically redundant when performing tasks, so multiple subtasks can be performed simultaneously, such as tracking the trajectory of the end effector(EE), optimizing manipulability, etc. First, the mobile manipulators system is modeled as an ordinary jointed manipulator. The velocity of the EE has a higher priority, scheduling low-priority tasks in the null space of high-priority tasks leaves high-priority tasks unaffected. The damped least square method is used to generate a kinematic inverse solution with singular robustness, and the gradient projection method is used to optimize the manipulability measure. By analyzing the structure of the Jacobian matrix, the complexity of gradient calculation is reduced. Finally, the effectiveness of the proposed algorithm is verified by simulation experiments. © 2023 IEEE.

关键词： Jacobian matrices

来源：评论

学校读者我要写书评

暂无评论

Bézier-UKF Enhanced Incremental MPC Planner for Quadrotor Based Target Following 25

Bézier-UKF Enhanced Incremental MPC Planner for Quadrotor B...

引用

25th IEEE International Conference on Industrial Technology, ICIT 2024

作者： Zhang, Haodi Su, Jinya Li, Shihua School Of Automation Southeast University Nanjing China Southeast University Key Laboratory Of Measurement And Control Of Complex Systems Of Engineering Ministry Of Education Nanjing China

ISBN: (纸本)9798350340266

This paper presents a vision-based tracking control for a quadrotor to follow a moving target without assuming any quadrotor-target communication. Constant turn rate & acceleration model (CTRA) is first drawn to describe the target's motion, allowing to infer unmeasurable target motion variables while mitigating the adverse effects of vision sensor noises through an unscented Kalman filter (UKF). Then the target's future trajectory is firstly predicted by using a Bézier curve, which is further treated as virtual observation of the CTRA model within the prediction horizon so that a better target trajectory prediction is derived by using the proposed Bézier- UKF fusion predictor method. The outputs of Bézier- UKF predictor are input into an incremental model predictive control (IMPC) planner as the target reference, enabling the derivation of the desired position, velocity and acceleration signal for the quadrotor. These signals are implemented by the low-level SE(3) geometric controller. Finally, we conduct a comparative study of the proposed method against baseline planners such as MPC and IMPC planners in high-fidelity AirSim simulation environment, demonstrating better target following performance. © 2024 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-AI Trust by Describing AI Decision-Making Behavior

Enhancing Human-AI Trust by Describing AI Decision-Making Be...

引用

2023 IEEE International Conference on Unmanned systems, ICUS 2023

作者： Lou, Zhouwei Wei, Haikun School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9798350316308

Air combat game is a highly complex and dynamic decision-making problem that is crucial for ensuring national security and improving combat efficiency. In recent years, artificial intelligence (AI) technologies such as deep reinforcement learning have made significant progress in the air combat game field, surpassing human experts' capabilities. However, the decision-making process of AI algorithms often lacks transparency and interpretability, resulting in low trust in them, which limits their promotion and application in practical scenarios. To enhance human-AI trust, this paper proposes a decision explanation method based on natural language generation. As the most direct means of information transmission, natural language can help people quickly understand the behavior and intent of AI algorithms. Taking a one-on-one air combat game as an experimental scenario, this paper constructs a combat dataset mapping temporal states to behavioral explanations and designs an attention-based Encoder-decoder architecture (AED) capable of generating natural language descriptions of current AI decision-making behavior based on a period of combat data. Experimental results show that AED can accurately describe the decision-making behavior of AI algorithms and help improve the level of human-AI trust. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

YOLO-MSP: Effective Cigarette Detection YOLO Network for Surveillance Scenario 10

YOLO-MSP: Effective Cigarette Detection YOLO Network for Sur...

引用

10th International Conference on systems and Informatics, ICSAI 2024

作者： Zhang, Zhiwei Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Ministry of Education Key Laboratory of Measurement and Control of Complex Systems of Engineering Nanjing210096 China

ISBN: (纸本)9798331510138

This paper presents an new approach to enhance the detection of smoking behavior using object detection neural networks, focusing on the challenge of small object detection, namely cigarettes in video frames. We introduce a Multi-Spatial Pooling (MSP) bottleneck mechanism integrated into a YOLOv8 backbone, which significantly improves the network's ability to discern smaller objects without compromising real-time inference capabilities. This enhancement facilitates the extraction of relevant features across various scales and efficiently handles the computational overhead, thereby boosting the detection accuracy and operational efficiency. Our results demonstrate a substantial improvement in performance metrics over traditional and existing neural network approaches, making this method highly suitable for real-time applications in diverse scenarios. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Time-Optimal and Smooth Trajectory Planning Based on Continuous Pseudo-Acceleration 8

Time-Optimal and Smooth Trajectory Planning Based on Continu...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Wang, Xin Gan, Yahui Dai, Xianzhong School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9798350300178

The current time-optimal trajectory planning based on dynamics does not take into account the continuity of joint torque. Although the time obtained by the solution of the original time-optimal path parameterization (TOPP) algorithm is optimal, the joint torque obtained by the solution is not continuous, and the discontinuous joint torque will cause the manipulator to resonate, which will reduce the accuracy of the trajectory, making the obtained trajectory in practical engineering applications cannot be effectively applied. Therefore, this paper improves the problem of discontinuous torque on the basis of the TOPP algorithm, and proposes to use a quadratic polynomial curve to deal with the discontinuous part of the pseudo-acceleration in the phase plane composed of position and pseudo-acceleration, which not only ensures the integrity of the path, but also makes the joint torque continuous and smoothes the joint torque trajectory to some extent. This method is verified by the simulation experiment of the two-link manipulator. © 2023 IEEE.

关键词： Trajectories

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：