检索结果-内蒙古大学图书馆

Parallel System Based Quantitative Assessment and Self-evolution for Artificial Intelligence of Active Power Corrective control

引用

CSEE Journal of Power and Energy systems 2024年第1期10卷 13-28页

作者： Tianyun Zhang Jun Zhang Feiyue Wang Peidong Xu Tianlu Gao Haoran Zhang Ruiqi Si School of Electrical Engineering and Automation Wuhan UniversityWuhan 430072HubeiChina State Key Laboratory for Management and Control of Complex System Institute of AutomationChinese Academy of SciencesBeijing 100190China

In artificial intelligence(AI)based-complex power system management and control technology,one of the urgent tasks is to evaluate AI intelligence and invent a way of autonomous intelligence ***,there is,currently,nearly no standard technical framework for objective and quantitative intelligence *** this article,based on a parallel system framework,a method is established to objectively and quantitatively assess the intelligence level of an AI agent for active power corrective control of modern power systems,by resorting to human intelligence evaluation *** this basis,this article puts forward an AI self-evolution method based on intelligence assessment through embedding a quantitative intelligence assessment method into automated reinforcement learning(AutoRL)systems.A parallel system based quantitative assessment and self-evolution(PLASE)system for power grid corrective control AI is thereby constructed,taking Bayesian Optimization as the measure of AI evolution to fulfill autonomous evolution of AI under guidance of their intelligence assessment *** results exemplified in the power grid corrective control AI agent show the PLASE system can reliably and quantitatively assess the intelligence level of the power grid corrective control agent,and it could promote evolution of the power grid corrective control agent under guidance of intelligence assessment results,effectively,as well as intuitively improving its intelligence level through selfevolution.

关键词： AI quantitative intelligence assessment and self-evolution automated reinforcement learning Bayesian optimization corrective control parallel system

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

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

Autonomous Path Planning and Realization for Dual Robot Cooperation Based on ROS Framework 8

Autonomous Path Planning and Realization for Dual Robot Coop...

引用

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

作者： Shao, Jiawei 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

To realize dual-robot autonomous path planning and realization, the trajectory planning research of dual-robot is carried out using the open-source robot operating system ROS as the simulation platform. The motion planning-related file configuration is completed by using MoveIt! In trajectory planning, cubic spline interpolation is performed on the trajectory points generated by the RRT-Connect path planning algorithm to complete the planning of the dual-arm assembly task. The communication between ROS nodes and ROS is established in the controller, and the processed trajectory points are communicated with the controller through ROS-Industrial. The experimental results show that the trajectory of the dual robot movement process is smooth and continuous, the stability is strong, and the error is small, which can ensure the completion of basic assembly tasks. © 2023 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

Image-Based Fast Finite-Time Target Tracking control of Onboard Inertially Stabilized Camera Platform

引用

IEEE Transactions on Industrial Electronics 2024年第12期71卷 16409-16418页

作者： Sun, Xunhong Zhu, Wenwu Du, Haibo Chen, Weile Chen, Chih-Chiang Hefei University of Technology School of Electrical Engineering and Automation Hefei230009 China Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Southeast University School of Automation Nanjing210096 China National Cheng Kung University Department of Systems and Naval Mechatronic Engineering Tainan70101 Taiwan

In this article, we investigate the problem of fast finite-time target tracking control of the inertially stabilized platform (ISP) with a camera that mounted on a mobile robot. At first, the kinematics of the onboard ISP target tracking system is established by the geographic coordinate and pinhole camera model, which includes the state-dependent uncertainties and external disturbances. Then, based on the image information captured by camera, a continuous image-based fast finite-time control algorithm is designed for target tracking. Rigorous analysis proves that the target can be tracked at the center of camera's view in finite time in the absence of disturbances. In the presence of disturbances, the tracking error can converge to a region around the origin in finite time. Simulation and experimental comparisons are presented to confirm the efficiency of the proposed method. © 1982-2012 IEEE.

关键词： Mobile robots

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

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

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

PMSM System Identification by Knowledge-informed Machine Learning 22

PMSM System Identification by Knowledge-informed Machine Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Yu, Yue Tong, Jiageng Xia, Jinhui Su, Jinya Li, Shihua School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9798331527471

Because of its excellent efficiency, compact dimensions, and accurate control features, Permanent Magnet Synchronous Motor (PMSM) are experiencing widespread applications across various industries. By accurately characterizing the dynamic behavior of PMSM systems through system identification, engineers can ensure that PMSM motors reach their maximum potentials and meet the stringent requirements of modern industrial and technical systems while reducing energy consumption and maintenance costs. The traditional recursive least squares method is sensitive to noises, and unable to accurately identify parameters in complex environments. Pure data-driven models lack interpretability and require complex model architecture and computational costs. To this end, this work draws knowledge-informed neural ordinary differential equations (NODEs) for system identification, which embeds system prior knowledge into the NODEs for more efficient and accurate model learning. Comparative simulations show that this method not only obtains a higher-precision system model, but also significantly reduces the amount of training data and computation costs. © 2024 IEEE.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

PWM Wave-Based Cooperative Vector control of Multiple Stepper Motors for Unmanned Surface Vehicles 7

PWM Wave-Based Cooperative Vector Control of Multiple Steppe...

引用

7th Asian Conference on Artificial Intelligence Technology, ACAIT 2023

作者： Xu, Ruizhe Xu, Yihang Wu, Yongbao Liu, Jian Xue, Lei Southeast University Key Laboratory of Measurement And Control of Complex Systems of Engineering Ministry of Education School of Automation Nanjing China

ISBN: (纸本)9798350359145

This paper studies the control system of multiple stepper motors. Four stepper motors are selected to design the vector control system for the actual application scenario of the unmanned surface vehicles. This paper designs a PWM wave-based motor control algorithm taking into account the characteristics of stepper motors. We proposes a closed-loop control algorithm incorporating magnetic encoders. The system applies CAN bus to realize the communication among stepper motors, enabling distributed cooperative control four stepper motors of the unmanned surface vehicles. In this paper, the multiple stepper motor system is modeled and finally simulated and experimentally verified to achieve cooperative vector control of multiple stepper motors for surface vehicles. © 2023 IEEE.

关键词： Vectors

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

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

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：