发布求助
文献互助 智能选刊 最新文献

2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)最新文献

筛选
英文 中文
Sim2Real Deep Reinforcement Learning of Compliance-based Robotic Assembly Operations 基于顺应性的机器人装配操作Sim2Real深度强化学习
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874304
O. Petrovic, Lukas Schäper, Simon Roggendorf, S. Storms, C. Brecher
{"title":"Sim2Real Deep Reinforcement Learning of Compliance-based Robotic Assembly Operations","authors":"O. Petrovic, Lukas Schäper, Simon Roggendorf, S. Storms, C. Brecher","doi":"10.1109/MMAR55195.2022.9874304","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874304","url":null,"abstract":"Reinforcement learning (RL) enables robots to learn goal-oriented behavior. In production processes with high variances, such as joining operations in end-of-line assembly, this is particularly interesting to save significant programming effort. Due to a large amount of required training data, simulative training is becoming increasingly important. In this paper, we present an approach to learn a contact-rich peg-in-hole assembly task utilizing deep reinforcement learning (DRL) and a compliant robot controller. The DRL-Agent learns directly in the Cartesian space (task space) and not in the joint space of the robot, to increase the robustness and efficiency of the algorithms. To further increase the robustness of the policy and to shorten training times, geometric limitations are imposed by introducing an admissible workspace using a trajectory generator. Furthermore, these limitations result in nearly identical behavior in the simulation and on the real robot, allowing the DRL training process to be purely simulative. The learned policy is experimentally investigated both in the simulation environment and on a real robot, to evaluate its transferability from simulation to reality (sim2real).","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128286026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Control of a Soft Actuator using a Long Short-Term Memory Neural Network 基于长短期记忆神经网络的软执行器控制
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874322
Victor Yanev, M. Giannaccini, S. S. Aphale
{"title":"Control of a Soft Actuator using a Long Short-Term Memory Neural Network","authors":"Victor Yanev, M. Giannaccini, S. S. Aphale","doi":"10.1109/MMAR55195.2022.9874322","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874322","url":null,"abstract":"Soft robots offer new opportunities because of their compliant physical structure and their wide range of applications. Currently the development of such robots is hampered by their low controllability. One of the main constituents of soft robots are soft actuators. The aim of this project is to improve the control of a non-linear system, the soft actuator, and its interaction with the environment, by training a long short-term memory (LSTM) neural network to accurately predict the actuator's position in space, its curvature, and the force applied by its end-effector on an external object. The increased performance of the trained network resulted in an error as low as $0.01pm 0.005 mathrm{N}$ in estimating the force applied by the end effector on the external object. The results show significantly superior performance (on the order of 10 times) in the positional and curvature predictions of the LSTM network when using one marker per air-chamber.","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127387144","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Mutual influence of PID and FOPID controllers on different axes of the 3D crane PID和FOPID控制器对三维起重机不同轴线的相互影响
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874306
Jakub Zeglen-Wlodarczyk, Klaudia Wajda
{"title":"Mutual influence of PID and FOPID controllers on different axes of the 3D crane","authors":"Jakub Zeglen-Wlodarczyk, Klaudia Wajda","doi":"10.1109/MMAR55195.2022.9874306","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874306","url":null,"abstract":"The article presents 3D crane control with PID and FOPID (which is an extension of the classic PID with fractional parts) controllers in various configurations. 5 controllers are needed to control the crane - 3 for controlling the XYZ axes and 2 for influencing the angular position $alpha$ and $beta$. 3 sets of simulations were prepared. The first version includes 5 FOPID regulators that serve as a benchmark for comparisons. In two subsequent sets, the FOPID controllers on one axis and the corresponding angle for this axis were replaced with PID controllers (X axis $+alpha$ angle and Y axis $+beta$ angle). Matlab/Simulink environment was used to prepare the simulation. Later in the article all the results were compared with each other. GWO optimization was used to prepare the best coefficients for individual controllers.","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132100258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Iterative learning control for vacuum heat treatment process 真空热处理过程的迭代学习控制
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874347
Piotr Balik, Kamil Klimkowicz, M. Patan
{"title":"Iterative learning control for vacuum heat treatment process","authors":"Piotr Balik, Kamil Klimkowicz, M. Patan","doi":"10.1109/MMAR55195.2022.9874347","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874347","url":null,"abstract":"Distributed parameter systems constitute an important class of modern industrial processes. However, in many practical applications the engineers still tend to adapt some classical control techniques developed for lumped systems totally neglecting the spatial dynamics of the investigated process. In a view of increasing demands imposed on system accuracy and performance, such conventional control algorithms simply become insufficient and there is a great necessity for novel identification and control methods taking into account both the temporal and spatial dynamics. This work reports a dedicated approach to control design for repetitive thermal processes consisting of the extension of the existing feedback control scheme with an intelligent data-driven component using the iterative learning control technique. Although this is a method which emerged in the context of time-invariant systems, it become adapted to more complex systems due to its flexibility and inherent robustness. The characterization of the resulting control scheme is discussed together with control design and implementation details. In order to compare the quality of the regulation, the approach is illustrated with simulation on the realistic model of wafer heating in an industrial vacuum furnace.","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"13 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126243659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Scheduling jobs with machine-dependent release dates on unrelated machines 在不相关的机器上调度具有与机器相关的发布日期的作业
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874277
Miroslaw Lawrynowicz, J. Józefczyk
{"title":"Scheduling jobs with machine-dependent release dates on unrelated machines","authors":"Miroslaw Lawrynowicz, J. Józefczyk","doi":"10.1109/MMAR55195.2022.9874277","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874277","url":null,"abstract":"This paper considers the job scheduling problem with varying release dates on unrelated parallel machines. Our model involves the machine-dependent release dates and the makespan criterion. The two developed and presented constructive deterministic algorithms use different decomposition strategies that result logically from exploiting the problem structure. The approximation factor of the greedy polynomial algorithm depends on the machines. An efficient adaptation of the well-known brute-force technique to solve $Rmvert r_{i,j}vert C_{max}$ is also considered in this paper. A series of numerical experiments are conducted to compare the quality of schedules.","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"08 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125862887","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Indoor Navigation System of Mobile Robot with Trajectory Optimization 基于轨迹优化的移动机器人室内导航系统
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874287
Qishuai Liu, Yu-rou Jiang, Ying Li
{"title":"Indoor Navigation System of Mobile Robot with Trajectory Optimization","authors":"Qishuai Liu, Yu-rou Jiang, Ying Li","doi":"10.1109/MMAR55195.2022.9874287","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874287","url":null,"abstract":"This paper proposes a navigation system for mobile robot working in indoor environment, which includes mapping and trajectory generation for the motion tracking problem of the real mobile robot. The mapping process comprises a Gaussian model to improve the accuracy of the environment representation. With this new mapping method, the mobile robot knows the obstacle in the environment around robot itself. For the trajectory generation process, a multimodality method is used to explore all feasible paths to reach the target point by estimating the density of distribution of the objective function. Finally, the experiments show the effectiveness of this navigation framework.","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"163 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121698108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multi-Objective Population-based Optimization Algorithms for Scheduling of Manufacturing Entities 基于多目标群体的制造实体调度优化算法
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874301
Milica Petrović, Aleksandar Jokic, Z. Miljković, Z. Kulesza
{"title":"Multi-Objective Population-based Optimization Algorithms for Scheduling of Manufacturing Entities","authors":"Milica Petrović, Aleksandar Jokic, Z. Miljković, Z. Kulesza","doi":"10.1109/MMAR55195.2022.9874301","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874301","url":null,"abstract":"The contemporary manufacturing systems face a challenging and uncertain future due to frequent customer demands for customized products. A promising direction that can enable manufacturing systems to fulfill the market requirements is the adaptation of a reconfigurable manufacturing system paradigm. Physical reconfigurability can be achieved by developing systems that can satisfy conflicting production priorities such as minimal production time and maximal profit. Having that in mind, in this paper, the authors present a comprehensive analysis of population-based multi-objective optimization algorithms utilized for scheduling manufacturing entities. The output of multi-objective optimization is a set of Pareto optimal solutions in the form of production scheduling plans with transportation constraints. Three state-of-the-art population-based algorithms i.e., Genetic Algorithm (GA), Particle Swarm Optimization (PSO), and Whale Optimization Algorithm (WOA), are employed for optimization, while the experimental results show the effectiveness and superiority of the WOA algorithm.","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125018313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Practical Implementation of Anti-Skew Fuzzy Logic Controller for Semi-Gantry Crane 半门式起重机抗斜模糊控制器的实际实现
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874266
Przemyslaw Krupiarz, K. Bartecki
{"title":"Practical Implementation of Anti-Skew Fuzzy Logic Controller for Semi-Gantry Crane","authors":"Przemyslaw Krupiarz, K. Bartecki","doi":"10.1109/MMAR55195.2022.9874266","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874266","url":null,"abstract":"This paper presents a case study of a 4 input 1 output Fuzzy Logic Controller implementing the anti-skew control for a semi-gantry crane. It was necessary due to the wear and tear caused by the skewed movement and the braking resistor overheating. The control system is designed to monitor two analog proximity sensors, measuring the carriage-to-rail distance as well as the torque feedback from the drives. The fuzzy algorithm is implemented on a Programmable Logic Controller and controls the Variable Frequency Drives through digital and analog signals. The proposed control system performed as intended, by preventing the traveling motors from the generator work and the crane from skewing.","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129972173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Hybrid VTOL UAV Autonomous Operations from Mobile Landing Pad 混合垂直起降无人机在移动着陆平台上的自主操作
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874343
L. Ambroziak, C. Kownacki, Arkadiusz Bożko
{"title":"Hybrid VTOL UAV Autonomous Operations from Mobile Landing Pad","authors":"L. Ambroziak, C. Kownacki, Arkadiusz Bożko","doi":"10.1109/MMAR55195.2022.9874343","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874343","url":null,"abstract":"Flight missions carried out from mobile landing pads are a challenge for hybrid VTOL UAVs. An approach to precise landing on a moving pad requires implementing an appropriate control system supported by accurate relative positioning. The paper presents the results of real conditions test on such a UAV system, which is a combination of hybrid VTOL UAV and dedicated landing pad navigation station that was developed to allow UAVS to take off and land on a mobile platform. Tests were carried out by employing a mobile landing platform mounted on a trailer pulled by a car. During the tests, the hybrid VTOL UAV was able to take off and land on the landing platform moving at a speed up to 25 km/h, and all flight trials ended with success. These tests improved the UAV system before the final test on maritime conditions.","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122490977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
Force-Control Capabilities for Lightweight Industrial Robots 轻型工业机器人的力控能力
2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR) Pub Date : 2022-08-22 DOI: 10.1109/MMAR55195.2022.9874326
Christian Thormann, M. Matour, Alexander W. Winkler
{"title":"Force-Control Capabilities for Lightweight Industrial Robots","authors":"Christian Thormann, M. Matour, Alexander W. Winkler","doi":"10.1109/MMAR55195.2022.9874326","DOIUrl":"https://doi.org/10.1109/MMAR55195.2022.9874326","url":null,"abstract":"This paper investigates the capabilities of lightweight industrial robots with respect to force/torque control. Two robots were chosen for this investigation. One robot was equipped with an internal force/torque sensor, while the other used motor current values to measure forces and torques. Many approaches of robot force control have been examined in the past. However, it is often difficult to implement these algorithms in commercial systems, as the robot controller lacks adequate programming features. The robotic system used in this paper included a precast functions for force control. It seems necessary to study the behavior of such robots when force control is activated. In particular, we analyzed the forces where the end-effector made contact with its environment (coming from free space). In the case of persistent contact, the desired contact force was altered, and the step responses were investigated. In addition, a more complex task involving force control was developed and presented to evaluate the quality of the precast force-control functions.","PeriodicalId":169528,"journal":{"name":"2022 26th International Conference on Methods and Models in Automation and Robotics (MMAR)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125695222","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信