检索结果-内蒙古大学图书馆

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

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

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

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

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

AST: Annulus Swin Transformer For Pedestrians Detection Under Top-view Fisheye Image 12

AST: Annulus Swin Transformer For Pedestrians Detection Unde...

引用

12th International Conference on Computing and Pattern Recognition, ICCPR 2023

作者： Lu, Cheng Wei, Xuan Lu, Xiaobo School of Software Engineering Southeast University Suzhou China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Suzhou China School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9798400707988

Fisheye images have a larger field of view than ordinary perspective cameras and can obtain more scene information. Therefore, object detection based on top-view fisheye images has wide applications in security monitoring, passenger flow perception, and industrial detection fields. However, due to the radial distortion symmetry of fisheye images, most current networks still need to adapt to this radial distortion symmetry. Therefore, we proposed the Annulus Swin Transformer(AST) for top-view fisheye images, which includes Annulus Window (AW) and Annulus Position Coding (APC). Traditional rectangular windows can break the radial distortion symmetry in top-view fisheye images, instead of taking advantage of it to improve the network's perception of distortion. Annulus-Window transforms it into an inner-to-outer annulus window to calculate self-attention, thereby maintaining the distortion symmetry of the fisheye image within each window, allowing the network to perceive better the degree of distortion in the fisheye image and get better detection performance. Due to the varying degree of distortion of images within each annulus, APC introduces an annulus position to work with Annulus window based on the original position encoding, enabling it to contain annulus position information. The experimental results on the dataset SEU-fisheye show that our method improves the neural network's performance markedly. © 2023 ACM.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Energy-based Swing-up control of the Soft Inverted Pendulum with Affine Curvature

引用

Nonlinear Dynamics 2025年 1-20页

作者： Wang, Yongjia Xin, Xin School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Institute of Intelligent Unmanned Systems Southeast University Nanjing210096 China

This paper studies the energy-based swing-up control of an underactuated soft inverted pendulum, a template model of soft robots with its base attached to the ground and its curvature described by an affine function. First, this paper presents a necessary and sufficient condition for the linear controllability of the robot around its upright equilibrium point (UEP). Next, without any constraint on its stiffness, this paper derives an energy-based controller to swing up the robot to its UEP, where the pendulum is in its upright position, and provides a necessary and sufficient condition such that the controller is free of singular points. Then, this paper characterizes the patterns of closed-loop equilibrium points with respect to the physical parameters of the pendulum and the gains of the derived controller, and analyzes the closed-loop motion corresponding to the special case in which desired convergence of the total mechanical energy is achieved. In such case, this paper reveals that the UEP is generically the unique closed-loop equilibrium point, and provides clarification regarding its stability. These results serve as guidelines of the design of soft robots and the tuning of control gains to achieve the desired performance of the swing-up control. Finally, this paper conducts numerical simulations to validate the theoretical results and to demonstrate the effectiveness and performance of the derived controller in swinging up the robot to its UEP from initial states far from the UEP, even under the challenging condition of very low stiffness. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.

关键词： Affine transforms

来源：评论

学校读者我要写书评

暂无评论

Self-supervised Depth Completion with Adaptive Online Adaptation 23

Self-supervised Depth Completion with Adaptive Online Adapta...

引用

7th International Conference on Machine Learning and Soft Computing, ICMLSC 2023

作者： Chen, Yang Tan, Yang Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

ISBN: (纸本)9781450398633

Although depth completion has achieved remarkable performance relying on deep learning in recent years, these models tend to suffer a performance degradation when exposed to new environments. Online adaptation, where the model is trained in a self-supervised manner during testing, seems a promising technique to alleviate the drop. However, continuous online adaptation may cause the model to over-adapt and miss the optimal parameters, resulting in oscillation or even degradation of the model performance, in addition to wasting computational resources. Therefore, this paper proposes an adaptive online adaptation framework to make model adaptively trigger online adaptation when encountering novel environments and stop adaptation when model has adapted to the current environment. In detail, we design a trigger to detect the familiarity of model to the current scenario based on image similarity and then launch online adaptation when the scenario is novel. Besides, we elaborate a stopper to monitor the error between prediction and depth input and convert online adaptation to inference when online adaptation does not bring improvement for model. Experimental results demonstrate that our method improves the accuracy of model prediction and increases average running speed of the model on each frame in online adaptation. © 2023 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Multi-Dimensional Taylor Network Tracking control for Stochastic Nonlinear Systems with Full-State Constraints and Input Saturation 8

Adaptive Multi-Dimensional Taylor Network Tracking Control f...

引用

8th International Conference on Robotics and Automation Engineering, ICRAE 2023

作者： Zheng, Xiao-Yi Yan, Hong-Sen Ministry of Education School of Automation Southeast University Key Laboratory of Measurement Control of Complex Systems of Engineering Nanjing210096 China

ISBN: (纸本)9798350327656

In this study, an adaptive tracking controller using multi-dimensional Taylor network (MTN) is presented for state-constrained nonlinear stochastic systems with saturated input, in which MTN is implemented to model the unknown nonlinear functions. Firstly, the barrier Lyapunov function (BLF) and backstepping technique are combined under a unified framework to eliminate the impact of full-state constraints. Then, the effect raised by saturated input is solved by introducing an appropriate auxiliary system. Furthermore, by employing the Lyapunov stability theorem, the designed adaptive controller could ensure that all closed-loop signals are bounded in probability, the output signal can track the desired signal successfully, the tracking error is bounded by the expected bound, and the system state constraints are never violated. Finally, the efficiency of the suggested control methodology is confirmed by providing an example. © 2023 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Event-Triggered Secondary Regulation Strategy for Microgrids with Loss of Effectiveness Actuator Faults 49

An Adaptive Event-Triggered Secondary Regulation Strategy fo...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Qiu, Xuechao Wang, Xiangyu Niu, Dan Wang, Xiangyu School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China

ISBN: (纸本)9798350331820

In this paper, an adaptive event-triggered secondary regulation strategy is investigated for microgrids with loss of effectiveness actuator faults. In order to deal with unknown loss of effectiveness actuator faults, a distributed secondary regulation strategy is proposed, which achieves voltage and frequency regulations, as well as power sharing. Meanwhile, to save system resources and relieve the communication burden, an adaptive event-triggered mechanism is designed. Finally, some simulation results are given to validate the proposed strategy, which indicates that the proposed strategy reduces the controller updates and increases the reliability of system. © 2023 IEEE.

关键词： Actuators

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：