检索结果-内蒙古大学图书馆

3rd International Conference on Autonomous Unmanned Systems, ICAUS 2023

作者： Zhang, Maohuai Yang, Meimei Qiu, Shaoxiong Xu, Hongli Gu, Haitao Northeastern University Shenyang110819 China State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China

ISBN: (纸本)9789819710829

Multiple underwater unmanned vehicles(Multi-UUVs) area coverage collaborative path planning faces the problems of low collaborative control efficiency and frequent obstacle avoidance. To address these issues, we firstly decompose the map into several sub-regions based on the Boustrophedon algorithm, in which several suitable initial points and termination points can be selected for collaborative path planning, and connects multiple sub-regions effectively to realize area coverage. Secondly, we design the Beetle Swarm Optimization(BSO) algorithm to achieve cooperative path planning from initial point to termination point, while using the Artificial Potential Field(APF) method to achieve local obstacle avoidance. Finally the simulation results show that compared with the system unoptimized, the obstacle avoidance times of the system based on BSO are reduced by 38%, and the energy consumption is reduced by 3.15%. © Beijing HIWING Scientific and Technological Information Institute 2024.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

A Multi-Class Imbalanced Learning Method Using Random Balanced Sampling for Predicting the Quality Level of Diesel Engines

A Multi-Class Imbalanced Learning Method Using Random Balanc...

引用

2024 International Conference on automation in Manufacturing, Transportation and Logistics, ICaMaL 2024

作者： Song, Yi-Tian Sun, Yan-Ning Zhu, Jia-Yang Liu, Li-Lan Gao, Zeng-Gui Zhang, Jia-Hao School of Mechatronic Engineering and Automation Shanghai University Shanghai China Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai China

ISBN: (纸本)9798350378658

Numerous process items and procedures in the assembly process of a diesel engine have a direct and significant impact on its performance, and accurate and effective assembly process control is a key technical bottleneck in improving the quality consistency of batch-produced diesel engines. Accurate prediction of assembly quality can provide support for online control of assembly quality. However, due to the significant class imbalance between qualified and unqualified products of diesel engine assembly quality, the traditional imbalance learning makes it difficult to capture the small changes between classes. Therefore, an improved random balance sampling method is proposed, combined with the LightGBM classifier to create a quality prediction model. Firstly, class balancing of the training dataset is achieved by generating random weights for each class and fusing oversampling and undersampling. Then, a LightGBM-based quality prediction model is built. Finally, the effectiveness of this approach is validated using real industrial diesel engine assembly data. The comparison results demonstrate that the proposed method outperforms traditional resampling techniques. This study provides an accurate quality prediction model, laying the groundwork for the assembly quality control model of diesel engines. © 2024 IEEE.

关键词： Diesel engines

来源：评论

学校读者我要写书评

暂无评论

Research on Networked Communication in Multi-AUV Cluster Systems 4

Research on Networked Communication in Multi-AUV Cluster Sys...

引用

4th International Conference on Electronic Information Engineering and Computer Communication, EIECC 2024

作者： Xu, Han Zheng, Rong Yang, Bo Gu, Haitao State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Shenyang China

ISBN: (纸本)9798331534622

With the continuous advancement of Autonomous underwater vehicles (AUV) technology, the capabilities of a single AUV are increasingly limited, making it difficult to meet demands of comprehensive mission execution. To address this challenge, this study adaptively modified three heavy-duty AUV to construct an autonomous underwater cluster system. A multidisciplinary optimization approach was employed to refine the design of the modified AUV platforms. By analysing the characteristics of the acoustic channel, Evologics acoustic modems were selected, and the communication system was subsequently optimized. Finally, lake trials were conducted to validate the networked communication functionality of the multi-AUV cluster system. The experimental results demonstrate that the system can effectively track the navigation trajectories of each AUV, confirming the correctness and effectiveness of the networked communication functions and protocols. © 2024 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Model-Free Feedback Control of a Hybrid-driven Soft Manipulator 30

Model-Free Feedback Control of a Hybrid-driven Soft Manipula...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Fu, Xin Zhang, Daohui Li, Kai Chu, Yaqi Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang Institute of Automation Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350391916

Soft robots offer high compliance and flexibility, enhancing their human and environmental interaction capabilities. However, complex modeling and control hinder the adoption of soft robots. This paper presents a novel model-free control approach for a hybrid-driven soft manipulator. It utilizes a model-free control method to estimate the Jacobian matrix in real time via end position feedback of the soft manipulator. To mitigate operational noise, Huber's M-estimation technique is incorporated. Furthermore, an inner and outer loop motion controller is designed to effectively govern the soft manipulator and accelerate the pneumatic drive's response within the hybrid drive system. The proposed control approach is demonstrated through experiments. The results substantiate its capability to withstand external disturbances and environmental noise, enabling efficient soft manipulator control. © 2024 IEEE.

关键词： Jacobian matrices

来源：评论

学校读者我要写书评

暂无评论

Utilizing the Entropy Weighting Method to Determine Objective Weights in Robot Trajectory Optimization 6

Utilizing the Entropy Weighting Method to Determine Objectiv...

引用

6th International Conference on Communications, Information System and Computer Engineering, CISCE 2024

作者： Shen, Nanyan You, Hua Li, Jing Qian, Hui School of Mechatronic Engineering and Automation Shanghai University Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai China SHANGHAI-FANUC Robotics CO.LTD General Manager's Office Shanghai China

ISBN: (纸本)9798350353174

Optimizing trajectories of collaborative robots is crucial to ensure the efficiency and safety of human-robot interactions in many manufacturing industries. This paper introduced an entropy weighting-based method for determining objective weights in trajectory optimization. Virtual simulations were conducted obtaining datasets of robot trajectory optimization so that, the application scope of the proposed weight determination method could be expanded. The validity of this method was affirmed through comparative simulation experiments. The results demonstrated that in maneuvers in the negative z-axis direction, optimized weights significantly outperformed baseline weights in terms of energy consumption and nominal trajectory tracking, with scores of 0.97 versus 0.68, and 0.82 versus 0.54, respectively. This indicates a better performance than subjective weight setting method in enhancing the performance of collaborative robot trajectory optimization. © 2024 IEEE.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Offline Deep Reinforcement Learning Two-stage Optimization Framework Applied to Recommendation Systems 43

Offline Deep Reinforcement Learning Two-stage Optimization F...

引用

43rd Chinese Control Conference, CCC 2024

作者： Jiang, Yihua Liu, Qi Li, Yanjie the Harbin Institute of Technology Shenzhen Guangdong Key Laboratory of Intelligent Morphing Mechanisms and Adaptive Robotics School of Mechanical Engineering and Automation 518055 China

ISBN: (纸本)9789887581581

Most traditional recommendation systems (RS) improve the model structure to obtain valid user behavior representation and make better recommendations. However, limited by the scale of the model, the model cannot accommodate an extended range of user historical data and cannot effectively extract long-term preferences. Reinforcement learning (RL) aims to maximize the cumulative return. Introducing RL can smoothly solve the long-term and short-term profit balance. However, there are specific problems with the direct combination of the two. Training RS that relies on offline user data will cause the strategy to suffer from an overestimation of action and distribution shift. Unlike the traditional RL environment, the ample space of the RS will also cause problems of insufficient exploration and sparse rewards, making the policy more difficult to learn. In response to the above issues, this work proposes an offline RL two-stage optimization framework. The framework consists of an offline RL method based on unknown behavior to alleviate the problem of action overestimation and a two-stage feature optimization training method to reduce the impact of large spaces. Experimental results prove that the method proposed in this article can effectively improve the long-term recommendation ability of the model and more effectively improve the model performance than the general offline RL algorithm. © 2024 Technical Committee on Control Theory, Chinese Association of automation.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of a Wall-Climbing Robot with Continuum Structure 6

Design and Analysis of a Wall-Climbing Robot with Continuum ...

引用

6th International Symposium on robotics and Intelligent Manufacturing Technology, ISRIMT 2024

作者： Wang, Qianyi Wang, Hongguang Liu, Aihua Jing, Fengren Yuan, Bingbing Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798331528942

Wall-climbing robots are widely used in tasks such as inspection. However, due to size constraints, conventional wall-climbing robots cannot have the ability to traverse narrow spaces while having the ability to span large distances. In this article, we presents a wall-climbing robot with continuum structure for detecting stress corrosion cracking in sealed canister within the spent fuel dry storage system. The robot employs a combination of three flexible tubes and DC motors to traverse both continuous and discontinuous walls, having the ability to traverse narrow spaces and span large distances within the spent fuel dry storage system. The forward and inverse kinematics of the robot are modelled assuming a constant curvature of the bending deformation. The simulation was carried out in Matlab and Adams, and the results showed that the top position and bending angle of the virtual backbone obtained from theory and simulation basically coincided with each other. © 2024 IEEE.

关键词： Stress corrosion cracking

来源：评论

学校读者我要写书评

暂无评论

Robotic Sensorized Gastroendoscopy with Wireless Single-Hand Control

Robotic Sensorized Gastroendoscopy with Wireless Single-Hand...

引用

作者： García, Gabriela Fischer, Nikola Marzi, Christian Mathis-Ullrich, Franziska Health Robotics and Automation Laboratory Institute for Anthropomatics and Robotics Karlsruhe Institute of Technology Karlsruhe76131 Germany

The manipulation of flexible endoscopes is a procedure that requires great dexterity since it requires the synchronization and use of both hands in parallel. Imprecise handling during gastroendoscopy could harm the digestive tract. Our solution allows the physician to use only one hand to wirelessly control the forward, backward, and tip bending motion. The proposed system provides endoscopic vision and tactile impact force sensing at the tip to detect the force applied to tissue and thus avoid damage. We experimentally evaluate the handling of the robotic system in open space and inside a medical phantom. The results revealed a training effect with less time demand for task completion and reduction of average impact force after only 5 runs. The proposed system was successfully controlled using one hand and, together with the force information, could enhance the physician's experience during endoscopy. Future work will address axial control and an intensive user study with clinical experts. © 2022 by Walter de Gruyter Berlin/Boston.

关键词： robotics

来源：评论

学校读者我要写书评

暂无评论

Research on Online Palletizing Algorithm Based on Buffer 1

引用

13th International Workshop of Advanced Manufacturing and automation, IWAMA 2023

作者： Zhou, Chuanhong Xu, Qinfeng Xu, Yang School of Automation and Mechanical Engineering Shanghai University Shanghai200072 China Shanghai Key Laboratory of Intelligent Manufacturing and Robotics Shanghai200072 China

ISBN: (数字)9789819706655

ISBN: (纸本)9789819706648

Online hybrid palletizing scene can not predict the size of the subsequent goods, easy to make the surface of the stacking type uneven, resulting in the subsequent goods can not be stacked and the stability of the stacking type is reduced, forming a collapse phenomenon. Aiming at the online scene problem in mixed cargo palletizing, this paper proposes an online palletizing algorithm based on buffer by setting buffer, combining the overall search strategy of greedy algorithm and the specific strategy of block construction heuristic algorithm. The effectiveness of the algorithm is verified by the examples of airport baggage stacking. The experimental results show that the algorithm can solve the online palletizing problem. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Flight control of a large-scale flapping-wing flying robotic bird:System development and flight experiment

引用

Chinese Journal of Aeronautics 2022年第2期35卷 235-249页

作者： Wenfu XU Erzhen PAN Juntao LIU Yihong LI Han YUAN School of Mechanical Engineering and Automation Harbin Institute of TechnologyShenzhen 518055China State Key Laboratory of Robotics and System Harbin Institute of TechnologyHarbin 150001China

Large-scale flapping-wing flying robotic birds have huge application potential in outdoor tasks,such as military reconnaissance,environment exploring,disaster rescue and so *** this paper,a multiple modes flight control method and system are proposed for a large-scale robotic bird which has 2.3 m wingspan and 650 g *** from small flapping wing aerial vehicle,the mass of its wings cannot be neglected and the flapping frequency are much ***,the influence of transient aerodynamics instead of only mean value are considered in attitude estimation and controller ***,flight attitude and trajectory are highly coupled,and the robot has only three actuators----one for wings flapping and two for tail adjustment,it is very difficult to simultaneously control the attitude and ***,a fuzzy control strategy is addressed to determine the command of each actuator by considering the priority of attitude stabilization,trajectory tracking and the flight ***,the on-board controller is designed based on *** not only satisfies the strict restrictions on mass,size,power and space but also meets the autonomous,semi-autonomous and manual flight control ***,the developed control system was integrated to the robotic prototype,*** experiments under different environment conditions such as sunny and windy weather were completed to verify the control method and system.

关键词： Autonomous flight control Flapping-wing Free RTOS HIT-Phoenix Robotic bird

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：