检索结果-内蒙古大学图书馆

2024 International Conference on Machine Learning, Pattern Recognition and automation engineering, MLPRAE 2024

作者： Rao, Jinjun Wang, Cong Liu, Mei Lei, Jingtao Giernacki, Wojciech Department of Precision Mechanical Engineering School of Mechatronic Engineering and Automation Shanghai University China Institute of Robotics and Machine Intelligence Faculty of Automatic Control Robotics and Electrical Engineering Poznan University of Technology Poland

ISBN: (纸本)9798400709876

Aiming at the problem that the combination of self-play (SP) and deep reinforcement learning (DRL) only involves two-party games and the policy learning of each party is limited, a multi-party asymmetric self-play algorithm (MASP) is proposed. Firstly, by improving the ELO scoring system, the ELO scoring takes into account each party of the unmanned surface vehicle (USV) clusters, and the imbalance of the number of USV clusters, so that the frequency of exchanging strategies of all USV clusters in the confrontation process is equal. Secondly, it ensures that USV clusters have a balanced combat ability, and at the same time ensures that the combat ability of all parties is strong and weak and the gap is not too wide. In addition, the parameters are dynamically set to reduce the update frequency of the policy of the stronger party. The experimental results show that the MASP can make the USV clusters learn more effective policies, have a shorter game time, and obtain higher rewards and ELO scores in the simple 2v2 adversarial game scenario and the three-party game scenario of a warship escort mission. © 2024 ACM.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Potential Field Incorporated Deep-Q-Network Algorithm for Mobile Robot Path Prediction

引用

Intelligent automation & Soft Computing 2023年第1期35卷 1135-1150页

作者： A.Sivaranjani B.Vinod Department of Robotics and Automation Engineering PSG College of TechnologyCoimbatore641004India Department of Electrical and Electronics Engineering PSG College of TechnologyCoimbatore641004India

Autonomous navigation of mobile robots is a challenging task that requires them to travel from their initial position to their destination without collision in an *** Learning methods enable a state action function in mobile robots suited to their *** trial-and-error interaction with its surroundings,it helps a robot tofind an ideal behavior on its *** Deep Q Network(DQN)algorithm is used in TurtleBot 3(TB3)to achieve the goal by successfully avoiding the *** it requires a large number of training *** research mainly focuses on a mobility robot’s best path prediction utilizing DQN and the Artificial Potential Field(APF)***,a TB3 Waffle Pi DQN is built and trained to reach the *** the APF shortest path algorithm is incorporated into the DQN *** proposed planning approach is compared with the standard DQN method in a virtual environment based on the Robot Operation System(ROS).The results from the simulation show that the combination is effective for DQN and APF gives a better optimal path and takes less time when compared to the conventional DQN *** performance improvement rate of the proposed DQN+APF in comparison with DQN in terms of the number of successful targets is attained by 88%.The performance of the proposed DQN+APF in comparison with DQN in terms of average time is achieved by 0.331 *** performance of the proposed DQN+APF in comparison with DQN average rewards in which the positive goal is attained by 85%and the negative goal is attained by-90%.

关键词： Artificial potentialfield deep reinforcement learning mobile robot turtle bot deep Q network path prediction

来源：评论

学校读者我要写书评

暂无评论

Expansion of Self-assembled Structures of Heteroarray NdFeB Semicircular Arc Magnetic Minirobots

引用

Journal of Bionic engineering 2024年第5期21卷 2258-2270页

作者： Wenguang Yang Huibin Liu Qinghao Guo Wenhao Wang Haibo Yu Anqin Liu School of Electromechanical and Automotive Engineering Yantai UniversityYantai264005China State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of SciencesShenyang110016China School of Mechanical and Electrical Engineering Yantai Institute of TechnologyYantai264005China

Researching the cooperative operation and functional expansion of multiple minirobot assemblies has the potential to bring about significant advancements in the practical applications of *** this study,we present a novel assembly sys-tem comprised of arc-shaped NdFeB magnetic *** minirobots can be individually utilized as assembly units,allowing for function expansion and comprehensive capability *** fabricate four Semicircular Arc Magnetic Minirobots(SAMM)arranged in different configurations and analyze their force and motion ***,by using this unit as a base,various expansion structures such as latches,petals,and rings can be assembled through reason-able *** define the comprehensive reinforcement interval by comparatively analyzing changes in the unit's motion characteristics and operational *** motion manipulation is employed to verify the rationality of the basic unit structure and the feasibility of the assembly *** proposed self-assembly scheme for magnetic minirobots exhibits great potential and may be used as a paradigm for future research on expanding the functionality of minirobots.

关键词： NdFeB Semicircular arc Cutoff frequency Assembly Cooperative work Magnetic minirobots

来源：评论

学校读者我要写书评

暂无评论

Instructing Hierarchical Tasks to Robots by Verbal Commands

Instructing Hierarchical Tasks to Robots by Verbal Commands

引用

2024 IEEE/SICE International Symposium on System Integration, SII 2024

作者： Telkes, Peter Angleraud, Alexandre Pieters, Roel Tampere University Cognitive Robotics Group Unit of Automation Technology and Mechanical Engineering Tampere33720 Finland

ISBN: (纸本)9798350312072

Natural language is an effective tool for communication, as information can be expressed in different ways and at different levels of complexity. Verbal commands, utilized for instructing robot tasks, can therefor replace traditional robot programming techniques, and provide a more expressive means to assign actions and enable collaboration. However, the challenge of utilizing speech for robot programming is how actions and targets can be grounded to physical entities in the world. In addition, to be time-efficient, a balance needs to be found between fine- and course-grained commands and natural language phrases. In this work we provide a framework for instructing tasks to robots by verbal commands. The framework includes functionalities for single commands to actions and targets, as well as longer-term sequences of actions, thereby providing a hierarchical structure to the robot tasks. Experimental evaluation demonstrates the functionalities of the framework by human collaboration with a robot in different tasks, with different levels of complexity. The tools are provided open-source at https://***/voice-jogger/ © 2024 IEEE.

关键词： Robot programming

来源：评论

学校读者我要写书评

暂无评论

Design of a Versatile Soft Pneumatic Gripper 5

Design of a Versatile Soft Pneumatic Gripper

引用

5th International Conference on Control, Communication and Computing, ICCC 2023

作者： Sanjay Krishna, J. Lal Priya, P.S. College of Engineering Robotics and Automation Trivandrum India College of Engineering Department of Electrical Engineering Trivandrum India

ISBN: (纸本)9798350334128

Conventional robotic grippers are rigid mechanisms that use suction for grasping objects and are often not used in areas like the food/agriculture industries due to the highly varying sizes, shapes, and weights of the objects which should be handled by them. Since they are designed for specific use cases which are often well-known in advance they are not designed to handle requirements like fragility, deformity, etc. Soft robotic grippers are a solution to this. With the increase in human-robot interactions and increased usage of co-bots, the need for soft robotic grippers is also growing. but often they too are designed for specific needs only. This paper discusses the design of a soft pneumatic gripper with a variable fixture, which can change the grasping workspace area accordingly to make the gripper more versatile. This will enable the gripper to be used in various situations where a traditional gripper requires manual/automated end-effector swap. The finite element analysis of the soft pneumatic actuator and the structure is performed and the parts are fabricated. The bending action of the soft pneumatic actuator is evaluated. © 2023 IEEE.

关键词： Grippers

来源：评论

学校读者我要写书评

暂无评论

Workspace and Cutting Force Requirements for an Automated Grapevine Pruner

Workspace and Cutting Force Requirements for an Automated Gr...

引用

2024 Australasian Conference on robotics and automation, ACRA 2024

作者： McGuinness, Benjamin Tattersall, Andrew Bernhard, Michael Au, Chikit Williams, Henry Lim, Hin Duke, Mike School of Engineering University of Waikato Hamilton New Zealand Centre for Automation and Robotics Engineering Science The University of Auckland New Zealand

Understanding task requirements is critical to producing efficient hardware which is optimised for the specific task. Robotic manipulators are often selected based on intuition, without a thorough analysis of the task and required workspace beforehand. This paper investigates key design requirements for a grapevine cane pruning robot. It presents a method for quantifying the workspace and degrees of freedom required, and investigates the cutting force required for the end effector. A UR5 robot arm was manually moved into cut positions, and used to capture the key cut locations and orientations for 15 vines, for a total of 792 data points. The dimensions of the required cuboid for pruning where determined to be 778 wide, 294 deep and 441 high, with a centre 888 mm above the ground. 6 DOF of freedom was required to access all the cut points, or 90.2 % could be accessed with five DOF, removing the need for variable pitch. Cutting force increased linearly with increasing diameter of canes, with a maximum force requirement of approximately 1200 N. These values can be used to inform the design of a grapevine pruning robot to optimise hardware and software systems for weight, cost, and efficiency. © 2024 Australasian robotics and automation Association. All rights reserved.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Multiple Robotic End Effectors for Apple Fruitlet Thinning

Comparative Evaluation of Multiple Robotic End Effectors for...

引用

2024 Australasian Conference on robotics and automation, ACRA 2024

作者： Jangali, Rahul Lim, Hin McGuinness, Ben Au, Chi Kit Williams, Henry MacDonald, Bruce Duke, Mike School of Engineering University of Waikato Hamilton New Zealand Centre for Automation and Robotics Engineering Science University of Auckland New Zealand

This paper presents a new method to evaluate multiple end effectors for a given task, which was applied to four custom-designed robotic end effectors for apple fruitlet thinning in a controlled laboratory environment. These end effectors’ specific mechanisms are stem cutting (cutting), grasp and roll (paraboloid), suction and twist (suction), and piercing and retract (piercing). An artificial fruitlet structure that replicates real apple fruitlets critical characteristics and suitable for different mechanisms of tested end effectors was used to ensure a consistent test platform across all end effectors. Each end effector was tested on single fruitlet at approach angles varying from 90 to 30 ° and five different positions of targeted fruitlet within the cluster at approach angles varying from 90 to 60 ° (cluster). A vision system and path planning system were integrated to facilitate the evaluation. The results showed that all effectors except piercing are capable to remove fruitlets from 45 to 90 ° for single fruitlet, and suction performed best in cluster evaluation. Cutting, paraboloid and suction end effectors were deemed feasible for further development and real field evaluation. © 2024 Australasian robotics and automation Association. All rights reserved.

关键词： Piercing

来源：评论

学校读者我要写书评

暂无评论

Sound Database of Industrial Machine for Audio Anomaly Detection 12th

Sound Database of Industrial Machine for Audio Anomaly Det...

引用

12th International Conference on Soft Computing for Problem Solving, SocProS 2023

作者： Shaikh, Kader B. T. Jawarkar, Naresh P. Ahmed, Vasif Dept. of Automation and Robotics Engineering VESIT Mumbai India Dept. of Electronics and Telecommunication Engineering BNCoE Pusad India

ISBN: (纸本)9789819732913

Audio anomaly detection (AAD) can seamlessly determine faults in industrial machines and improve the efficiency of predictive maintenance systems. However, the unavailability of audio sound recordings of real industrial machines operating in their actual industrial setup has limited the efficacy of detection systems. Many different audio databases exist having collections of sounds from dummy (or real) systems operating in controlled environments but a collection of audio sounds from actual industrial machines is missing. Therefore, audio sound recordings of an Air compressor machine working in its natural industrial environment are presented. Only real sounds of an actual machine are captured. Synthetic mixing of sounds is avoided. Damaging the machine to create an anomalous state is avoided. Yet fourteen different unhealthy states are identified and their audio recordings are presented. Dataset with varied values of SNRs is also presented. Spectrograms are plotted and spectral shape parameter values of the developed corpus are calculated. The findings demonstrate the divergence in the developed database and its usefulness in building an effective AAD system for a real industrial machine. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Regression Model for State of Charge Estimation of Lithium Ion Batteries in Electric Vehicle 2

Regression Model for State of Charge Estimation of Lithium I...

引用

2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and automation, ICAECA 2023

作者： Aishwarya, Shree J. Richie, Soshan E. Hari, Ram Karthik M. Vigneswar, N. Sudhakar, R. Murugarajan, A. Sri Ramakrishna Engineering College Robotics and Automation Engg. Coimbatore India

ISBN: (纸本)9798350306811

Electric vehicle (EV) batteries are essential to increasing the effectiveness and affordability of EVs. To optimize battery usage and improve performance and longevity, it is essential to establish the relationship between the chemical behavior and physical factors that affect battery performance. In this study, statistical techniques are employed to identify the dynamic parameters, namely current, voltage, state of charge, temperature, ambient temperature, etc.,that influences the target variable, state of chargeThe battery's performance and efficiency are greatly influenced by the target variable, so improving it is essential to lengthening the battery's useful life. The results of this paper dive into the factors affecting EV battery usage, which can inform the development of strategies for optimizing battery performance and increasing the longevity of EV batteries. © 2023 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

Color Transfer Algorithm for Interior Design Based on Deep Learning 2

Color Transfer Algorithm for Interior Design Based on Deep L...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Rajadurai, Kayalvizhi Mohankumar, Madhan Joseph, Arun Vaidyanathan, Elango Kumaresan, Nandini Sivaraj, Santhosh Department of Robotics and Automation Easwari Engineering College Bharathi Salai Ramapuram India

ISBN: (纸本)9798350305418

It is suggested that a topologically informed colour transfer method for interior design be used to match areas that have significant colour variability and colours that are just moderately rich. First, the image of the interior design is segmented, then the topology complete information of each region is calculated, and last, the region-matching relationship is determined based on the topology in order to improve the accuracy of the colour transfer;Second, colour is transferred between matched zones, and colour correction is applied to areas that do not get colour input in order to enhance the color's integrity as it is transferred;In conclusion, the algorithm for colour harmony works to improve colour harmony after the colour transfer by lowering the amount of noise. According to the findings of the experiments, the algorithm is able to keep the image's rich colour throughout while also improving the matching relationship and making colour adjustments locally, which leads to better colour transfer results. Targets can be captured and tracked with TOP technology. The use of neural networks and deep learning allows ambient perception to train and self-play the network, allowing it to continually update and locate the optimal grid path. The method of vertical falling grabbing is utilised in order to obtain and determine the quickest path to return to the grid in order to complete the procedure. © 2023 IEEE.

关键词： Color transfer Deep learning, Topology Interior design

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：