首页 > 最新文献

2019 12th International Workshop on Robot Motion and Control (RoMoCo)最新文献

英文 中文
Accuracy comparison of navigation local planners on ROS-based mobile robot 基于ros的移动机器人导航局部规划精度比较
Pub Date : 2019-07-08 DOI: 10.1109/RoMoCo.2019.8787346
B. Cybulski, Agnieszka Węgierska, G. Granosik
The aim of this work is to investigate and analyze the performance of ROS-based navigation local planners in a simulated environment and on a real research platform the TurtleBot 3 mobile robot. Three planners were subject to the study: DWA, EBand and TEB; the accuracy and repeatability were measured for position and orientation of the robot, as well as time of travel. Tests were based on continuous movements between three waypoints placed in a confined space, in both static and dynamic environments. The motion capture system based on AR tags was used in the real world. The obtained results do not indicate a specific comparison winner. All tested planners in most cases met their requirements.
本工作的目的是调查和分析基于ros的导航局部规划器在模拟环境和真实研究平台TurtleBot 3移动机器人上的性能。研究对象包括三家规划机构:市区工务局、东区工务局及东区工务局;测量了机器人的位置和方向以及行走时间的精度和重复性。测试基于放置在密闭空间中的三个路点之间的连续运动,在静态和动态环境中进行。基于AR标签的动作捕捉系统在现实世界中得到了应用。获得的结果并不表明一个特定的比较获胜者。所有经过测试的计划者在大多数情况下都满足了他们的要求。
{"title":"Accuracy comparison of navigation local planners on ROS-based mobile robot","authors":"B. Cybulski, Agnieszka Węgierska, G. Granosik","doi":"10.1109/RoMoCo.2019.8787346","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787346","url":null,"abstract":"The aim of this work is to investigate and analyze the performance of ROS-based navigation local planners in a simulated environment and on a real research platform the TurtleBot 3 mobile robot. Three planners were subject to the study: DWA, EBand and TEB; the accuracy and repeatability were measured for position and orientation of the robot, as well as time of travel. Tests were based on continuous movements between three waypoints placed in a confined space, in both static and dynamic environments. The motion capture system based on AR tags was used in the real world. The obtained results do not indicate a specific comparison winner. All tested planners in most cases met their requirements.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123004259","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: 21
Adjustability for Grasping Force of Patients with Autism by iWakka: A Pilot Study iWakka对自闭症患者抓握力可调性的初步研究
Pub Date : 2019-07-08 DOI: 10.1109/RoMoCo.2019.8787382
Masakazu Nomura, Natalia Kucharek, Igor Zubrycki, G. Granosik, Y. Morita
Herein, we present a pilot study on the adjustability for grasping force (AGF) of patients with autism. The AGF is the ability to grasp an object with an appropriate force. In our previous study, we developed a training and testing device for the AGF and a system to use it, called iWakka. Impairments in motor functioning, which until recently have been rarely a primary focus in autism spectrum disorder research, may be associated with key social communication deficits. Patients with autism are also suggested to exhibit a longer yaw displacement, indicating a larger head turning, than those without autism. A pilot study was conducted to explore the applicability of the above-mentioned device to autistic patients; eight participants with autism were involved in this study. Three participants could not use iWakka without assistance. The AGF of the four participants who could use iWakka by themselves was improved after training. Moreover, we noticed a reduction in the yaw head displacement of three participants. Because the head pose is an important indicator of the focus of attention of a person, this result suggested that their focus of attention was also improved. Therapists were interviewed for their opinions. Some activities of the participants changed after training with iWakka (e.g., they could sit and focus for longer than before). It was suggested that iWakka has the potential to improve the AGF and other abilities of patients with autism.
在此,我们提出了一项关于自闭症患者抓握力(AGF)可调节性的初步研究。AGF是用适当的力抓住物体的能力。在我们之前的研究中,我们为AGF开发了一个训练和测试设备,以及一个使用它的系统,称为iWakka。运动功能的损伤,直到最近还很少成为自闭症谱系障碍研究的主要焦点,可能与关键的社会沟通缺陷有关。与没有自闭症的人相比,自闭症患者也表现出更长的偏航位移,这表明头部转动的幅度更大。进行了一项试点研究,探讨上述装置在自闭症患者中的适用性;8名自闭症患者参与了这项研究。三名参与者在没有帮助的情况下无法使用iWakka。4名能够独立使用iWakka的参与者在训练后AGF均有提高。此外,我们注意到三个参与者的偏航头位移减少了。因为头部姿势是一个人注意力集中的重要指标,所以这个结果表明他们的注意力也得到了提高。治疗师接受了采访,征求他们的意见。在iWakka训练后,参与者的一些活动发生了变化(例如,他们可以比以前坐得更久,注意力更集中)。这表明iWakka有可能改善自闭症患者的AGF和其他能力。
{"title":"Adjustability for Grasping Force of Patients with Autism by iWakka: A Pilot Study","authors":"Masakazu Nomura, Natalia Kucharek, Igor Zubrycki, G. Granosik, Y. Morita","doi":"10.1109/RoMoCo.2019.8787382","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787382","url":null,"abstract":"Herein, we present a pilot study on the adjustability for grasping force (AGF) of patients with autism. The AGF is the ability to grasp an object with an appropriate force. In our previous study, we developed a training and testing device for the AGF and a system to use it, called iWakka. Impairments in motor functioning, which until recently have been rarely a primary focus in autism spectrum disorder research, may be associated with key social communication deficits. Patients with autism are also suggested to exhibit a longer yaw displacement, indicating a larger head turning, than those without autism. A pilot study was conducted to explore the applicability of the above-mentioned device to autistic patients; eight participants with autism were involved in this study. Three participants could not use iWakka without assistance. The AGF of the four participants who could use iWakka by themselves was improved after training. Moreover, we noticed a reduction in the yaw head displacement of three participants. Because the head pose is an important indicator of the focus of attention of a person, this result suggested that their focus of attention was also improved. Therapists were interviewed for their opinions. Some activities of the participants changed after training with iWakka (e.g., they could sit and focus for longer than before). It was suggested that iWakka has the potential to improve the AGF and other abilities of patients with autism.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121188195","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
Design and Evaluation of a Factorization-Based Grasp Myoelectric Control Founded on Synergies 基于协同效应的因子分解抓取肌电控制设计与评价
Pub Date : 2019-07-08 DOI: 10.1109/RoMoCo.2019.8787387
R. Meattini, Daniele De Gregorio, G. Palli, C. Melchiorri
In this article we present a factorization-based myoelectric proportional control that uses surface skin electromyographic (sEMG) measurements to estimate the hand closure level of a user for telemanipulation purposes. The sEMG-based proportional control design is presented and the results of an experimental session are reported. In particular, involving one healthy subject, four different factorization algorithms are tested (Factor Analysis, Fast Independent Component Analysis, Non-negative Matrix Factorization and Principal Component Analysis) and quantitative evaluated along four different daily session using four different error metrics (Root-Mean-Square Error, Normalized Root-Mean-Square Error, cross-correlation coefficient and Dynamic Time Warping measurement). The metrics are computed comparing the sEMG-based estimation of the hand closure level with a ground-truth signal obtained through a motion tracking system. The results report for better performances of the Non-negative Matrix Factorization algorithm, that can be used for controlling robotic hands in a real telemanipulation scenario. Therefore, the proposed myoelectric proportional control was finally tested in a simple validation grasping scenario using a real robotic hand, reporting for user's simplicity and intuitiveness in regulating the grasp closure in accordance with different objects.
在这篇文章中,我们提出了一种基于分解的肌电比例控制,它使用表面皮肤肌电图(sEMG)测量来估计用户的手部闭合水平,用于远程操作。提出了基于表面肌电信号的比例控制设计,并报道了实验结果。特别地,在一名健康受试者中,测试了四种不同的分解算法(因子分析、快速独立成分分析、非负矩阵分解和主成分分析),并使用四种不同的误差度量(均方根误差、归一化均方根误差、互相关系数和动态时间扭曲测量)在四个不同的日常会话中进行定量评估。将基于表面肌电信号的手部闭合水平估计与通过运动跟踪系统获得的接地真值信号进行比较,计算出度量。结果表明,非负矩阵分解算法具有较好的性能,可用于实际遥控场景下的机械手控制。因此,本文提出的肌电比例控制方法最终在一个简单的验证抓取场景中使用真实的机器人手进行了测试,报告了用户根据不同物体调节抓取闭合的简单性和直观性。
{"title":"Design and Evaluation of a Factorization-Based Grasp Myoelectric Control Founded on Synergies","authors":"R. Meattini, Daniele De Gregorio, G. Palli, C. Melchiorri","doi":"10.1109/RoMoCo.2019.8787387","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787387","url":null,"abstract":"In this article we present a factorization-based myoelectric proportional control that uses surface skin electromyographic (sEMG) measurements to estimate the hand closure level of a user for telemanipulation purposes. The sEMG-based proportional control design is presented and the results of an experimental session are reported. In particular, involving one healthy subject, four different factorization algorithms are tested (Factor Analysis, Fast Independent Component Analysis, Non-negative Matrix Factorization and Principal Component Analysis) and quantitative evaluated along four different daily session using four different error metrics (Root-Mean-Square Error, Normalized Root-Mean-Square Error, cross-correlation coefficient and Dynamic Time Warping measurement). The metrics are computed comparing the sEMG-based estimation of the hand closure level with a ground-truth signal obtained through a motion tracking system. The results report for better performances of the Non-negative Matrix Factorization algorithm, that can be used for controlling robotic hands in a real telemanipulation scenario. Therefore, the proposed myoelectric proportional control was finally tested in a simple validation grasping scenario using a real robotic hand, reporting for user's simplicity and intuitiveness in regulating the grasp closure in accordance with different objects.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"8 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131579645","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
Predicting Vehicle Control Errors in Emergency Swerving Maneuvers 紧急转向机动车辆控制误差预测
Pub Date : 2019-07-08 DOI: 10.1109/RoMoCo.2019.8787383
Michal Schmidt, Daniel Töpfer, S. Schmidt
This paper presents a method to estimate the model error of a controlled system from real experiments using nonlinear optimization. The method is employed on an automated vehicle performing emergency swerving maneuvers in real driving tests. By estimating the underlying model error directly from real-world experiments we are able to predict the vehicles lateral error for evasive maneuvers using error propagation on the linearized feedback system.
本文提出了一种利用非线性优化方法从实际实验中估计被控系统模型误差的方法。将该方法应用于某自动驾驶汽车的紧急转向试验中。通过直接从现实世界的实验中估计潜在的模型误差,我们能够利用线性化反馈系统上的误差传播来预测车辆规避机动的横向误差。
{"title":"Predicting Vehicle Control Errors in Emergency Swerving Maneuvers","authors":"Michal Schmidt, Daniel Töpfer, S. Schmidt","doi":"10.1109/RoMoCo.2019.8787383","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787383","url":null,"abstract":"This paper presents a method to estimate the model error of a controlled system from real experiments using nonlinear optimization. The method is employed on an automated vehicle performing emergency swerving maneuvers in real driving tests. By estimating the underlying model error directly from real-world experiments we are able to predict the vehicles lateral error for evasive maneuvers using error propagation on the linearized feedback system.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114484488","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
VFO controller for set-point visual servoing of unicycle-like mobile robots equipped with a camera of an uncertain depth scale factor 带不确定深度尺度因子摄像机的单轮移动机器人定点视觉伺服的VFO控制器
Pub Date : 2019-07-08 DOI: 10.1109/RoMoCo.2019.8787351
M. Michałek, Runhua Wang, Xuebo Zhang
The paper presents derivation, control performance analysis, and numerical validation of the Vector Field Orientation (VFO) control law devised for visual servoing of the input-constrained unicycle-like robot equipped with an onboard camera of an uncertain depth scale factor. It is shown that an inherent robustness of the proposed VFO controller ensures exponential convergence of the robot pose error toward zero despite even large uncertainty of the depth scale factor. This property allows simplifying applications of visual servoing with the VFO controller by avoiding a precise calibration process relating the on-board camera and the reference plane of feature points. Simulation results show the effectiveness and robustness of the proposed approach.
针对不确定深度尺度因子的带相机的输入约束类独轮车机器人的视觉伺服,给出了矢量场定向(VFO)控制律的推导、控制性能分析和数值验证。结果表明,尽管深度尺度因子存在较大的不确定性,所提出的VFO控制器的固有鲁棒性保证了机器人位姿误差向零的指数收敛。该特性通过避免与机载摄像机和特征点参考平面相关的精确校准过程,简化了视觉伺服与VFO控制器的应用。仿真结果表明了该方法的有效性和鲁棒性。
{"title":"VFO controller for set-point visual servoing of unicycle-like mobile robots equipped with a camera of an uncertain depth scale factor","authors":"M. Michałek, Runhua Wang, Xuebo Zhang","doi":"10.1109/RoMoCo.2019.8787351","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787351","url":null,"abstract":"The paper presents derivation, control performance analysis, and numerical validation of the Vector Field Orientation (VFO) control law devised for visual servoing of the input-constrained unicycle-like robot equipped with an onboard camera of an uncertain depth scale factor. It is shown that an inherent robustness of the proposed VFO controller ensures exponential convergence of the robot pose error toward zero despite even large uncertainty of the depth scale factor. This property allows simplifying applications of visual servoing with the VFO controller by avoiding a precise calibration process relating the on-board camera and the reference plane of feature points. Simulation results show the effectiveness and robustness of the proposed approach.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126734932","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
Adaptive Controller with Output Feedback for Dielectric Electro-Active Polymer Actuator 介质电活性聚合物作动器的输出反馈自适应控制器
Pub Date : 2019-07-08 DOI: 10.1109/RoMoCo.2019.8787365
Jakub Bernat, J. Kołota
In this work, an adaptive controller with output feedback was used in order to solve the position control of a nonlinear actuator built with a Dielectric Electro-Active Polymer (DEAP). The authors present the modeling process of the device taking into account the nonlinear model and its linearization. The identification process was carried out and the results were compared with experiments with good agreement. Due to the fact that it is not possible to obtain full state of DEAP actuator, the authors applied Model Reference Adaptive Controller with output feedback were voltage is an input signal and distance is an output. This approach allows to development a control method resistant to changing the parameters of DEAP device. Presented methods have been presented with illustrative examples.
为了解决由介电活性聚合物(DEAP)构成的非线性作动器的位置控制问题,提出了一种带输出反馈的自适应控制器。作者介绍了考虑非线性模型及其线性化的器件建模过程。进行了鉴定过程,并与实验结果进行了比较,结果吻合较好。由于不可能获得DEAP执行器的完整状态,作者采用输出反馈的模型参考自适应控制器,以电压为输入信号,距离为输出信号。这种方法允许开发一种抵抗改变DEAP装置参数的控制方法。所提出的方法已用实例加以说明。
{"title":"Adaptive Controller with Output Feedback for Dielectric Electro-Active Polymer Actuator","authors":"Jakub Bernat, J. Kołota","doi":"10.1109/RoMoCo.2019.8787365","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787365","url":null,"abstract":"In this work, an adaptive controller with output feedback was used in order to solve the position control of a nonlinear actuator built with a Dielectric Electro-Active Polymer (DEAP). The authors present the modeling process of the device taking into account the nonlinear model and its linearization. The identification process was carried out and the results were compared with experiments with good agreement. Due to the fact that it is not possible to obtain full state of DEAP actuator, the authors applied Model Reference Adaptive Controller with output feedback were voltage is an input signal and distance is an output. This approach allows to development a control method resistant to changing the parameters of DEAP device. Presented methods have been presented with illustrative examples.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124595562","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: 4
Kinematic Simulator of e-Knee Robo that Reproduces Human Knee-Joint Movement 模拟人体膝关节运动的e-Knee机器人运动学模拟器
Pub Date : 2019-07-08 DOI: 10.1109/RoMoCo.2019.8787349
Goro Hatano, K. Kozlowski, P. Sauer, Y. Morita
Our previously developed e-Knee Robo is a simple structure that can reproduce healthy human knee-joint movements. Since many people suffer from osteoarthritis or ligament injuries, e-Knee Robo must be able to reproduce abnormal knee movements. Reproducing them using e-Knee Robo, e.g., changing the shape of the bones and determining the positions for attaching ligaments to the bones, can be very time consuming. Therefore, it is worth developing a simulator that reproduces e-Knee Robo's movement to address this difficulty. This paper describes the development of a kinematic simulator for e-Knee Robo. To accomplish this, the knee-joint surfaces of the femur and tibia were modeled using approximate polynomial equations. For each flexion angle, 0° to 90°, the remaining five degrees-of-freedom movements were tested. The results showed that the developed simulator can reproduce adductions, lateral tibial displacements, and joint displacements.
我们之前开发的电子膝关节机器人是一个简单的结构,可以复制健康的人类膝关节运动。由于许多人患有骨关节炎或韧带损伤,e-Knee Robo必须能够重现异常的膝盖运动。使用e-Knee Robo来复制它们,例如,改变骨骼的形状并确定将韧带连接到骨骼上的位置,可能非常耗时。因此,值得开发一个模拟器来重现e-Knee Robo的运动,以解决这一难题。本文介绍了e-膝关节机器人运动模拟器的研制。为了实现这一点,股骨和胫骨的膝关节表面使用近似多项式方程建模。对于每个弯曲角度(0°到90°),测试剩余的五个自由度运动。结果表明,所开发的模拟器可以再现内收、胫骨外侧移位和关节移位。
{"title":"Kinematic Simulator of e-Knee Robo that Reproduces Human Knee-Joint Movement","authors":"Goro Hatano, K. Kozlowski, P. Sauer, Y. Morita","doi":"10.1109/RoMoCo.2019.8787349","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787349","url":null,"abstract":"Our previously developed e-Knee Robo is a simple structure that can reproduce healthy human knee-joint movements. Since many people suffer from osteoarthritis or ligament injuries, e-Knee Robo must be able to reproduce abnormal knee movements. Reproducing them using e-Knee Robo, e.g., changing the shape of the bones and determining the positions for attaching ligaments to the bones, can be very time consuming. Therefore, it is worth developing a simulator that reproduces e-Knee Robo's movement to address this difficulty. This paper describes the development of a kinematic simulator for e-Knee Robo. To accomplish this, the knee-joint surfaces of the femur and tibia were modeled using approximate polynomial equations. For each flexion angle, 0° to 90°, the remaining five degrees-of-freedom movements were tested. The results showed that the developed simulator can reproduce adductions, lateral tibial displacements, and joint displacements.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122530821","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
Step climbing method for crawler type rescue robot using reinforcement learning with Proximal Policy Optimization 基于近端策略优化强化学习的履带式救援机器人阶梯攀爬方法
Pub Date : 2019-07-08 DOI: 10.1109/RoMoCo.2019.8787360
Mifu Totani, N. Sato, Y. Morita
It is a huge burden on an operator when he/she tele-operates a rescue robot traveling on a rough terrain. Therefore, the purpose of this study is to reduce this burden by controlling the robot autonomously. As a first step, we propose a step climbing method for a crawler type rescue robot by using reinforcement learning with Proximal Policy Optimization (PPO). The input data are the image of a camera on the robot and a posture image of the robot. We verified the effectiveness of the proposed method using a dynamics simulator.
在崎岖地形上远程操作救援机器人对操作者来说是一个巨大的负担。因此,本研究的目的是通过自主控制机器人来减轻这一负担。首先,我们提出了一种基于近端策略优化(PPO)的强化学习的履带式救援机器人爬坡方法。所述输入数据为机器人上的摄像头图像和机器人的姿态图像。我们用动力学模拟器验证了所提方法的有效性。
{"title":"Step climbing method for crawler type rescue robot using reinforcement learning with Proximal Policy Optimization","authors":"Mifu Totani, N. Sato, Y. Morita","doi":"10.1109/RoMoCo.2019.8787360","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787360","url":null,"abstract":"It is a huge burden on an operator when he/she tele-operates a rescue robot traveling on a rough terrain. Therefore, the purpose of this study is to reduce this burden by controlling the robot autonomously. As a first step, we propose a step climbing method for a crawler type rescue robot by using reinforcement learning with Proximal Policy Optimization (PPO). The input data are the image of a camera on the robot and a posture image of the robot. We verified the effectiveness of the proposed method using a dynamics simulator.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122254098","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: 10
Comparative study of muscles effort during gait phases for multi-muscle humanoids 多肌肉类人机器人步态阶段肌肉力的比较研究
Pub Date : 2019-07-08 DOI: 10.1109/RoMoCo.2019.8787348
T. Zielińska, Jikun Wang, W. Ge, Linwei Lyu
The comparative study of the muscles effort is presented. The normal gait with bare foot is studied. The effort of the main groups of human leg muscles is investigated using the muscular model of the human body and the Opensim simulator. The data are processed by the classifying artificial neural networks. The classification results are matching the gait phases. In the next stage the recorded and preprocessed EMG data are applied to the classifying artificial neural network. In this case the strong coincidence between the gait phases and the obtained classes was observed as well. The joint trajectories were also analyzed. The general aim of this study is to provide the information and tool supporting the development of multi-muscle humanoids. The information about muscle effort is needed when selecting the artificial muscles for the humanoid legs. A muscle type actuators generates force depends on the activation, therefore for robotic prosthesis with EMG control the study of EMG signals is relevant. Moreover it was proved that the classifying artificial neural network makes a good tool for recognizing the gait phases.
提出了肌肉用力的对比研究。研究了赤脚的正常步态。利用人体肌肉模型和Opensim模拟器对人体腿部主要肌肉群的用力进行了研究。通过人工神经网络对数据进行分类处理。分类结果与步态相匹配。在接下来的阶段,记录和预处理的肌电数据应用于分类人工神经网络。在这种情况下,步态阶段和获得的类别之间的强烈重合也被观察到。并对关节运动轨迹进行了分析。本研究的总体目的是为多肌肉类人机器人的发展提供信息和工具。在选择仿人腿的人工肌肉时,需要肌肉用力的信息。肌肉型致动器的受力依赖于激活,因此对具有肌电信号控制的机器人假体进行肌电信号的研究具有重要意义。结果表明,分类人工神经网络是一种很好的步态阶段识别工具。
{"title":"Comparative study of muscles effort during gait phases for multi-muscle humanoids","authors":"T. Zielińska, Jikun Wang, W. Ge, Linwei Lyu","doi":"10.1109/RoMoCo.2019.8787348","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787348","url":null,"abstract":"The comparative study of the muscles effort is presented. The normal gait with bare foot is studied. The effort of the main groups of human leg muscles is investigated using the muscular model of the human body and the Opensim simulator. The data are processed by the classifying artificial neural networks. The classification results are matching the gait phases. In the next stage the recorded and preprocessed EMG data are applied to the classifying artificial neural network. In this case the strong coincidence between the gait phases and the obtained classes was observed as well. The joint trajectories were also analyzed. The general aim of this study is to provide the information and tool supporting the development of multi-muscle humanoids. The information about muscle effort is needed when selecting the artificial muscles for the humanoid legs. A muscle type actuators generates force depends on the activation, therefore for robotic prosthesis with EMG control the study of EMG signals is relevant. Moreover it was proved that the classifying artificial neural network makes a good tool for recognizing the gait phases.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121129400","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
Task harmonisation for a single-task robot controller 单任务机器人控制器的任务协调
Pub Date : 2019-07-01 DOI: 10.1109/RoMoCo.2019.8787385
W. Dudek, M. Węgierek, Jarosław Karwowski, W. Szynkiewicz, Tomasz Winiarski
The technical capabilities of robots and their increased versatility require a single robot to be able to perform a wide array of complex tasks. What more, when performing a task, it may be asked to carry out another one. Switching between different tasks is a known problem in engineering, however, robots, compared to programs operating in a virtual space, are unique as they must follow laws of physics. In this work, we introduce a method for harmonising service robot tasks being managed by finite state machines. The method allows for the handling of safe suspend and resume procedures for a complex task. Additionally, we consider a case when the robot can not switch the current task to another at any time. The method was implemented and verified by conducting multiple interruptions of one task by another one. The tasks during the verification were being performed in simulation by a TIAGo robot.
机器人的技术能力及其增加的多功能性要求单个机器人能够执行各种复杂任务。更重要的是,在执行一项任务时,它可能被要求执行另一项任务。在不同的任务之间切换是工程学上的一个众所周知的问题,然而,与在虚拟空间中运行的程序相比,机器人是独一无二的,因为它们必须遵循物理定律。在这项工作中,我们引入了一种方法来协调由有限状态机管理的服务机器人任务。该方法允许处理复杂任务的安全挂起和恢复过程。此外,我们还考虑了机器人在任何时候都不能切换当前任务到另一个任务的情况。通过一个任务对另一个任务的多次中断,对该方法进行了实现和验证。验证期间的任务由TIAGo机器人在模拟中执行。
{"title":"Task harmonisation for a single-task robot controller","authors":"W. Dudek, M. Węgierek, Jarosław Karwowski, W. Szynkiewicz, Tomasz Winiarski","doi":"10.1109/RoMoCo.2019.8787385","DOIUrl":"https://doi.org/10.1109/RoMoCo.2019.8787385","url":null,"abstract":"The technical capabilities of robots and their increased versatility require a single robot to be able to perform a wide array of complex tasks. What more, when performing a task, it may be asked to carry out another one. Switching between different tasks is a known problem in engineering, however, robots, compared to programs operating in a virtual space, are unique as they must follow laws of physics. In this work, we introduce a method for harmonising service robot tasks being managed by finite state machines. The method allows for the handling of safe suspend and resume procedures for a complex task. Additionally, we consider a case when the robot can not switch the current task to another at any time. The method was implemented and verified by conducting multiple interruptions of one task by another one. The tasks during the verification were being performed in simulation by a TIAGo robot.","PeriodicalId":415070,"journal":{"name":"2019 12th International Workshop on Robot Motion and Control (RoMoCo)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133873929","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: 10
期刊
2019 12th International Workshop on Robot Motion and Control (RoMoCo)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
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
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1