检索结果-内蒙古大学图书馆

Object Detection and Multiple Objective Optimization Manipulation Planning for Underwater Autonomous Capture in Oceanic Natural Aquatic Farm

引用

Journal of Field robotics 2025年第0期

作者： Hai, Huang Tao, Jiang Xinyu, Bian Hao, Zhou Xu, Yang Gang, Wang Hongde, Qin Xinyue, Han National Key Laboratory of Science and Technology on Underwater Vehicle Harbin Engineering University Harbin China State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Science Bei Jing China

Underwater autonomous capture operations offer significant potential for reducing labor and health risks in sea organism industries. This study presents a comprehensive solution for cross-domain underwater object detection and autonomous capture. A novel unsupervised domain adaptive learning method is proposed, integrating multiscale domain adaptive modules and attention mechanisms into a Faster Region-Convolutional Neural Network framework. This approach enhances feature alignment across diverse aquatic domains without parameter tuning. Additionally, an efficient, parameterless constrained multiobjective optimization algorithm is introduced for underwater autonomous mobile capture, integrating parameterized trajectory planning with innovative features, such as adaptive mutation strategies and constraint violation tolerance. The proposed approaches are extensively validated through simulations, tank experiments, and real-world oceanic trials in the Natural Aquatic Farm of Zhangzidao Island. Results demonstrate the system's robustness in complex underwater environments with varying currents, with experimental outcomes validating the accuracy and reliability of detection and capture capabilities. This research significantly advances autonomous underwater systems' capabilities in object detection and capture tasks, addressing complex challenges in realistic organism capture applications across diverse aquatic environments. © 2025 Wiley Periodicals LLC.

关键词： Health risks

来源：评论

学校读者我要写书评

暂无评论

Direct bonding of AZ31B and ZrO2 induced by interfacial sono-oxidation reaction at a low temperature

引用

Journal of Magnesium and Alloys 2025年

作者： Li, Z.L. Wang, J. Yi, S.L. Song, X.G. Fu, J.H. Shi, Y. Feng, J.C. State Key Laboratory of Precision Welding & Joining of Materials and Structures Harbin Institute of Technology Harbin150001 China Shandong Provincial Key Lab of Special Welding Technology Harbin Institute of Technology at Weihai Weihai264209 China

Recently, the presentation of the metal-ceramic composite structure design provides an alternative idea for the improvement of components service performance, while conventional methods for joining metals and ceramics have to involve a high heat input. However, due to the low melting point of magnesium alloys, the magnesium alloys-ceramics joining system necessitates a low joining temperature. Ultrasonic vibrations can induce numerous defects in the solid matrix, which can effectively promote atomic diffusion and metallurgical bonding between solid-phase interfaces at low temperatures. Thus, ultrasonic-assisted bonding is a highly promising method for achieving rapid and reliable joining between metals and ceramics without the use of interlayers. In this study, the direct bonding of AZ31B alloy with ZrO2 ceramic was successfully achieved at 200 °C. A polycrystal spinel MgAl2O4 with an average thickness of 55 nm was identified at the AZ31B/ZrO2 interface. The average shear strength of joints reached 30.47 MPa. Furthermore, the dynamic recrystallization of AZ31B and the oxygen-depletion behavior of ZrO2 during the bonding process were characterized to illustrate the contribution of ultrasonic vibration to joint bonding. Consequently, the solid interfacial sono-oxidation reaction is proposed to discuss the bonding mechanism of the joint in detail. © 2024

关键词： Magnesium alloys

来源：评论

学校读者我要写书评

暂无评论

Low-gain Control Strategy for Robot Manipulators Based on Sparse Feature Learning Dynamics with an Application to Collision Detection

Low-gain Control Strategy for Robot Manipulators Based on Sp...

引用

IEEE International Workshop on Safety, Security, and Rescue robotics (SSRR)

作者： Chenglong Yu Zhiqi Li Weixin Chou Hong Liu State Key Laboratory of Robotics and System Harbin Institute of Technology China

ISBN: (纸本)9781665456814

Recently, with the robotic technique developing toward precision and intelligence, robots have been used more widely in human life and production. As a common feature in the foreseen applications, robots should be able to detect unexpected collisions while ensuring dynamic accuracy, so as to improve safety at work. In the previous model-based collision detection solution, most methods assume that the robot dynamic model is complete and accurate. Unfortunately, reliable robot dynamics is hard to obtain due to model uncertainties, assembly errors, and the lack of information provided by manufacturers. This paper proposed a novel low-gain control strategy based on sparse feature learning dynamics. Firstly, without considering the physical structure parameters, the dynamics was learned directly via the data-driven technique. Secondly, according to the learned accurate dynamics, a model-based low-gain controller was designed to ensure control performance while avoiding excessive unspecified force. Finally, using this control strategy, sensorless collision detection was realized in a 7-DOF manipulator and the performance of the proposed method was evaluated.

关键词： Representation learning Service robots Dynamics Force Robot sensing systems Safety Security

来源：评论

学校读者我要写书评

暂无评论

Dynamics Analysis of a Symmetric 3-R(SRS)RP Multi-loop Mechanism 23rd

Dynamics Analysis of a Symmetric 3-R(SRS)RP Multi-loop Mecha...

引用

23rd IFToMM China International Conference on Mechanism and Machine Science and Engineering, IFToMM CCMMS 2022

作者： Li, Chuanyang Qin, Zhongbao Hu, Changhua Liu, Rongqiang Liu, Ruiwei Song, Xiaoke PLA Rocket Force University of Engineering Xi’an710025 China State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150080 China College of Naval Architecture and Ocean Engineering Guangzhou Maritime University GuangZhou510725 China School of Mechatronics and Vehicle Engineering East China Jiaotong University Nanchang330013 China

ISBN: (纸本)9789811993978

The 3-R(SRS)RP multi-loop Mechanism is regarded as one module of a multi-stage manipulator for space manipulation operations, such as capturing free-flying objects. The mechanism has two rotational and one translational degrees of freedom, as well as includes coupled kinematic chains, which can be constructed to the modular system for space operation. The dynamics analysis of the mechanism is the basis of its structural design and actuation control. In this paper, the twist shaping matrix between the twists of links and the input rate array is derived by decoupling the mechanism and motion analysis. Based on the Newton–Euler equation, the dynamics model of the mechanism is established. the theoretical values of actuation power consumption on the certain motion modes is calculated via programming, then being compared with the simulation values obtained through ADAMS model. The results are basically consistent, which verifies the correctness of the dynamics analysis of the mechanical system. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

Reliable protocol using gradient boosting decision tree with limited experimental data to modify membrane surface for enhanced resilience and nitrogen removal in biofilm system

引用

Bioresource technology 2025年 431卷 132602页

作者： Wang, Jie Shen, Qi Zhang, Senyao Yuan, Chunyan Wang, Mingming Tu, Honghua Feng, Liang Sun, Feiyun Shenzhen518055 China State Key Laboratory of Urban Water Resource and Environment Harbin Institute of Technology Harbin150090 China

This study highlights the importance of advanced membrane modification optimization methods for Membrane biofilm reactors (MBfR). Using Response surface methodology (RSM) and Gradient Boosting Decision Tree (GBDT), a relationship between solution concentration, reaction time, and temperature versus membrane surface characteristics was established. The GBDT model accurately predicted surface roughness during training (R2 = 0.994) and testing (R2pred = 0.993), outperforming RSM (R2 = 0.981, R2pred = 0.763, RMSE = 8.302) with a low RMSE of 2.077. The optimal conditions (1 mg·L-1 concentration, 5 h reaction time, 45 ℃) were used to modify membranes, which enhanced bio-attachment greatly. The optimized membrane achieved a nitrogen removal efficiency of 98.4 % in MBfR, performs better than the control one of 35.7 %. These results demonstrate that GBDT shows promising potential in optimizing membrane modification parameters, providing an effective strategy for enhancing MBfR performance through modelling and modification methods. © 2025

关键词： Biofilm management Denitrification Machine learning Membrane biofilm reactor Membrane modification

来源：评论

学校读者我要写书评

暂无评论

Research on multi-coils wireless power transfer system Based on Insulator with Flanges 4

Research on multi-coils wireless power transfer System Based...

引用

4th IEEE China International Youth Conference on Electrical Engineering, CIYCEE 2023

作者： Liu, Yang Yang, Fuyao Han, Yu Gao, Jie Sun, Hao Wang, Cong Guan, Yueshi State Grid Smart Grid Research Institute Co. Ltd State Key Laboratory of Advanced Power Transmission Technology Bei Jing102209 China Harbin Institute of Technology School of Electrical Engineering and Automation Harbin150001 China

ISBN: (纸本)9798350305562

This article claims the properties and working characteristics of multi-relay WPT systems, and studies various factors that affect the output efficiency of the system. At the same time, this article also investigates the impact of composite insulator metal flanges on the multi-relay WPT system when it operates in 110kV composite insulators, providing some guidance for the arrangement of all the coils in the composite insulator. © 2023 IEEE.

关键词： Flanges

来源：评论

学校读者我要写书评

暂无评论

Manipulation of asymmetric steering and periodic entanglement in cavity magnetomechanics induced by chiral exceptional points

引用

Physical Review B 2025年第1期111卷 014433-014433页

作者： Zhong-Hui Yuan Yan Xia Yong-Yuan Jiang Jie Song School of Physics Harbin Institute of Technology Harbin 150001 China Department of Physics Fuzhou University Fuzhou 350002 China Key Laboratory of Micro-Nano Optoelectronic Information System Ministry of Industry and Information Technology Harbin 150001 China Key Laboratory of Micro-Optics and Photonic Technology of Heilongjiang Province Harbin Institute of Technology Harbin 150001 China Collaborative Innovation Center of Extreme Optics Shanxi University Taiyuan Shanxi 030006 China

We study the periodic entanglement and asymmetric steering at exceptional points for a non-Hermitian cavity magnetomechanics system in which exceptional points (EPs) emerge periodically by controlling the relative phase angle of the nanoparticles. First, we analyze this hybrid system and identify parametric regimes where different types of entanglement and steering are enhanced. Entanglement and steering can be significantly enhanced due to the external control method and are thus more robust to thermal noises. This provides an active method to manipulate the asymmetry of steering instead of adding asymmetric losses or noises to subsystems at the cost of reducing steering ability. Moreover, the relative phase angle (RPA) not only enhances the strength of entanglement but also increases the domain of entanglement over a wider space of detunings compared to a system in which no RPA is present. Another important consequence of the RPA is that it controls the directivity of quantum steering. Specifically, steering reaches a maximal value at EPs as well, and we can get rich properties of Einstein-Podolsky-Rosen steering; e.g., the asymmetry of the overall state is stepwise, including one-way quantum steering, no-way quantum steering, and two-way quantum steering. We believe that the presented scheme is a step forward in realizing robust quantum entanglement using current technology. Our results indicate that cavity magnetomechanics systems could provide a promising platform for the study of macroscopic quantum phenomena.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Yowov2: A Real-Time Multi-Level Detection Framework for Spatio-Temporal Action Detection

SSRN

引用

SSRN 2023年

作者： Yang, Jianhua Wang, Ke Zhao, Lijun Dai, Kun Li, Ruifeng State Key Laboratory of Robotics and System Harbin Institute of Technology Harbin150001 China Wuhu Robot Industry Technology Research Institute Harbin Institute of Technology Wuhu241000 China Zhengzhou Research Institute Harbin Institute of Technology Zhengzhou450000 China

Designing a real-time framework for the spatio-temporal action detection task is still a challenge. In this paper, we propose a novel real-time action detection framework, YOWOv2. In this new framework, YOWOv2 takes advantage of both the 3D backbone and 2D backbone for accurate action detection. A multi-level detection pipeline is designed to detect action instances of different scales. To achieve this goal, we carefully build a simple and efficient 2D backbone with a feature pyramid network to extract different levels of classification features and regression features. For the 3D backbone, we adopt the existing efficient 3D CNN to save development time. By combining 3D backbones and 2D backbones of different sizes, we design a YOWOv2 family including YOWOv2-Tiny, YOWOv2-Medium, and YOWOv2-Large. We also introduce the popular dynamic label assignment strategy and anchor-free mechanism to make the YOWOv2 consistent with the advanced model architecture design. With our improvement, YOWOv2 is significantly superior to YOWO, and can still keep real-time detection. Without any bells and whistles, YOWOv2 achieves 87.0% frame mAP and 52.8% video mAP with over 20 FPS on the UCF101-24. On the AVA, YOWOv2 achieves 21.7% frame mAP with over 20 FPS. Our code is available on https://***/yjh0410/YOWOv2. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Robotic Grasping Method for Nest Frame Based on Gen6D and AnyGrasp

Vision-Based Robotic Grasping Method for Nest Frame Based on...

引用

Computer Applications and Information technology (ISCAIT), International Symposium on

作者： Maoguo Li Zhenyu Zhang Xiaoyan Zhang Shiyu Li Ning Zhang Shengxin Sun School of Astronautics Harbin Institute of Technology Harbin China State Key Laboratory of Micro-Spacecraft Rapid Design and Intelligent Cluster Harbin Institute of Technology Harbin China

ISBN: (数字)9798331542856

ISBN: (纸本)9798331542863

Beekeeping plays a significant role in agricultural production, while the traditional farming method makes beekeepers not only have heavy physical labor, but also easy to be attacked by bees. Nest frame grasping is the core task of honey harvesting robots, for which a vision-based robotic grasping method combining Gen6D with AnyGrasp is proposed. After that, an evaluation and decision system based on the nest frame mechanics model is added to select the most suitable grasping pose. Finally, vision program tests and grasping experimental based on a mobile base 6-DOF manipulator are carried out. The method succeeds in 35 gripping experiments under 4 different working conditions, with acceptable response time, specifically, 10.632 s on average. The study contributes to the application of honey harvesting robots, saving response time and improving grasping accuracy significantly.

关键词： Location awareness Visualization Accuracy Pose estimation Grasping Production Manipulators 6-DOF Time factors Meteorology

来源：评论

学校读者我要写书评

暂无评论

A Multi-Robot Task Allocation Method Based on Graph Attention Network and Unsupervised Learning

A Multi-Robot Task Allocation Method Based on Graph Attentio...

引用

2024 IEEE International Conference on Unmanned systems, ICUS 2024

作者： Wu, Zirui Li, Zhen Zhu, Dong Liao, Qiuhan Yao, Weiran School of Astronautics Harbin Institute of Technology Harbin China Beijing Electro-Mechanical Engineering Institute Beijing China Chengdu CHG Robots & Intelligent Equipment Institute Co. Ltd. Chengdu China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China

ISBN: (纸本)9798350384185

The task allocation for multiple robots is a critical component in the coordination of unmanned *** existing heuristic algorithms are hard to achieve satisfactory results in large-scale problems, and reinforcement learning-based methods face challenges in ensuring the rationality of reward *** paper introduces a model based on multi-head attention and graph neural networks to address the schedule-dependent multi-robot task allocation problem, trained using unsupervised learning *** model can be trained with varying numbers of robots and tasks without necessitating changes to its structure or *** the experiment of this paper, the model is trained under two different conditions, and the performance is evaluated across six different problem *** the proposed model against greedy algorithms and genetic algorithms, the results demonstrate that the proposed model has significant advantages in overall performance. © 2024 IEEE.

关键词： Adversarial machine learning

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：