In order to convert the leg interaction force between the exoskeleton and human body into the expected angle of the movement of the human hip and knee at the next moment, and realize the recognition of human motion intention, the mapping relationship between the joint angular velocity and the active joint torque generated by the leg interaction force was studied. Firstly, by collecting joint angle data from the gait experiment, the movement characteristics of lower limb swing phase and support phase in normal daily gait were analyzed, and the joint angle prediction strategies for different phases of human body were determined. Then, by establishing the dynamic model of exoskeleton under human-machine coupling, the formula of human body gravity compensation was obtained. Then, regarding the leg swing phase, the nonlinear mapping relationship between the joint angular velocity of human body and the joint torque generated by the interaction force of the leg after gravity compensation was established through the admittance control model. The desired Angle was obtained by multiplying the angular velocity of the control period plus the current joint angle. Finally, for the prediction of the expected joint Angle of the leg support phase, the hip joint should be controlled by position to keep the back of the exoskeleton upright, and the knee joint should adopt the same algorithm as the swing to obtain the desired joint angle.
{"title":"Prediction of expected Angle of knee joint of human lower limbs based on leg interaction","authors":"Xinyu Wu, Aibin Zhu, Yao Tu, Guangzhong Cao, Xiaodong Zhang, Zhifu Guo","doi":"10.1109/UR49135.2020.9144783","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144783","url":null,"abstract":"In order to convert the leg interaction force between the exoskeleton and human body into the expected angle of the movement of the human hip and knee at the next moment, and realize the recognition of human motion intention, the mapping relationship between the joint angular velocity and the active joint torque generated by the leg interaction force was studied. Firstly, by collecting joint angle data from the gait experiment, the movement characteristics of lower limb swing phase and support phase in normal daily gait were analyzed, and the joint angle prediction strategies for different phases of human body were determined. Then, by establishing the dynamic model of exoskeleton under human-machine coupling, the formula of human body gravity compensation was obtained. Then, regarding the leg swing phase, the nonlinear mapping relationship between the joint angular velocity of human body and the joint torque generated by the interaction force of the leg after gravity compensation was established through the admittance control model. The desired Angle was obtained by multiplying the angular velocity of the control period plus the current joint angle. Finally, for the prediction of the expected joint Angle of the leg support phase, the hip joint should be controlled by position to keep the back of the exoskeleton upright, and the knee joint should adopt the same algorithm as the swing to obtain the desired joint angle.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115662083","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}
Pub Date : 2020-06-01DOI: 10.1109/UR49135.2020.9144985
Nguyen Tan Viet Tuyen, A. Elibol, N. Chong
Non-verbal behaviors play an essential role in human-human interaction, allowing people to convey their intention and attitudes, and affecting social outcomes. Of particular importance in the context of human-robot interaction is that the communicative gestures are expected to endow social robots with the capability of emphasizing its speech, describing something, or showing its intention. In this paper, we propose an approach to learn the relation between human behaviors and natural language based on a Conditional Generative Adversarial Network (CGAN). We demonstrated the validity of our model through a public dataset. The experimental results indicated that the generated human-like gestures correctly convey the meaning of input sentences. The generated gestures were transformed into the target robot’s motion, being the robot’s personalized communicative gestures, which showed significant improvements over the baselines and could be widely accepted and understood by the general public.
{"title":"Learning from Humans to Generate Communicative Gestures for Social Robots","authors":"Nguyen Tan Viet Tuyen, A. Elibol, N. Chong","doi":"10.1109/UR49135.2020.9144985","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144985","url":null,"abstract":"Non-verbal behaviors play an essential role in human-human interaction, allowing people to convey their intention and attitudes, and affecting social outcomes. Of particular importance in the context of human-robot interaction is that the communicative gestures are expected to endow social robots with the capability of emphasizing its speech, describing something, or showing its intention. In this paper, we propose an approach to learn the relation between human behaviors and natural language based on a Conditional Generative Adversarial Network (CGAN). We demonstrated the validity of our model through a public dataset. The experimental results indicated that the generated human-like gestures correctly convey the meaning of input sentences. The generated gestures were transformed into the target robot’s motion, being the robot’s personalized communicative gestures, which showed significant improvements over the baselines and could be widely accepted and understood by the general public.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123302691","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}
Pub Date : 2020-06-01DOI: 10.1109/UR49135.2020.9144873
Jiayi Ling, Tomoyuu Sakuda, H. Iida, Yonghoon Ji, K. Umeda, Akira Ohashi, Daisuke Fukuda, Shuzo Kaneko, J. Murayama
This paper proposes a novel method that significantly improves the accuracy of the fisheye stereo camera using multiple disparity offset maps that contain disparity error information. The disparity offset map is constructed based on disparity errors that are calculated from the feature points extracted from an object with a known distance. Modified stereo matching process based on the maps is carried out to greatly reduce the disparity errors that cannot be completely removed by general calibration scheme. Furthermore, the our method is possible to achieve high accuracy in both short and long range by combining the multiple maps. The proposed method is verified by experiments.
{"title":"Accuracy Improvement of Fisheye Stereo Camera by Combining Multiple Disparity Offset Maps","authors":"Jiayi Ling, Tomoyuu Sakuda, H. Iida, Yonghoon Ji, K. Umeda, Akira Ohashi, Daisuke Fukuda, Shuzo Kaneko, J. Murayama","doi":"10.1109/UR49135.2020.9144873","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144873","url":null,"abstract":"This paper proposes a novel method that significantly improves the accuracy of the fisheye stereo camera using multiple disparity offset maps that contain disparity error information. The disparity offset map is constructed based on disparity errors that are calculated from the feature points extracted from an object with a known distance. Modified stereo matching process based on the maps is carried out to greatly reduce the disparity errors that cannot be completely removed by general calibration scheme. Furthermore, the our method is possible to achieve high accuracy in both short and long range by combining the multiple maps. The proposed method is verified by experiments.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":"223 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114156161","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}
Pub Date : 2020-06-01DOI: 10.1109/UR49135.2020.9144895
Cheoleon Park, Hojoon Kim, Youngsu Cha
In this study, we investigated the characteristics of piezoelectric sensors woven with a flexible fiber-based substrate. Eight polyvinylidene fluoride film-based piezoelectric sensors were placed in parallel on a flexible fabric, passing above and below the intersection of the yarns. To study the electrical properties of the sensors, sinusoidal flexural loadings with different bending angles and operating frequencies were applied to the fabric substrate. The experimental results indicated that different flexural loadings can be differentiated by analyzing the output voltages from the sensors. Also, the results confirmed that the output voltage remains constant with varying operating frequencies at a fixed bending angle. Also, the voltage amplitudes of the sensors were proportional to the bending angle.
{"title":"Fiber-based Piezoelectric Sensors in Woven Structure","authors":"Cheoleon Park, Hojoon Kim, Youngsu Cha","doi":"10.1109/UR49135.2020.9144895","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144895","url":null,"abstract":"In this study, we investigated the characteristics of piezoelectric sensors woven with a flexible fiber-based substrate. Eight polyvinylidene fluoride film-based piezoelectric sensors were placed in parallel on a flexible fabric, passing above and below the intersection of the yarns. To study the electrical properties of the sensors, sinusoidal flexural loadings with different bending angles and operating frequencies were applied to the fabric substrate. The experimental results indicated that different flexural loadings can be differentiated by analyzing the output voltages from the sensors. Also, the results confirmed that the output voltage remains constant with varying operating frequencies at a fixed bending angle. Also, the voltage amplitudes of the sensors were proportional to the bending angle.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129506608","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}
Pub Date : 2020-06-01DOI: 10.1109/UR49135.2020.9144761
L. Roveda, Marco Forgione, D. Piga
Autonomy is increasingly demanded by industrial manipulators. Robots have to be capable to regulate their behavior to different operational conditions, without requiring high time/resource-consuming human intervention. Achieving an automated tuning of the control parameters of a manipulator is still a challenging task. This paper addresses the problem of automated tuning of the manipulator controller for trajectory tracking. A Bayesian optimization algorithm is proposed to tune both the low-level controller parameters (i.e., robot dynamics compensation) and the high-level controller parameters (i.e., the joint PID gains). The algorithm adapts the control parameters through a data-driven procedure, optimizing a userdefined trajectory-tracking cost. Safety constraints ensuring, e.g., closed-loop stability and bounds on the maximum joint position errors, are also included. The performance of the proposed approach is demonstrated on a torque-controlled 7degree-of-freedom FRANKA Emika robot manipulator. The 25 robot control parameters (i.e., 4 link-mass parameters and 21 PID gains) are tuned in 125 iterations, and comparable results with respect to the FRANKA Emika embedded position controller are achieved.
{"title":"One-Stage Auto-Tuning Procedure of Robot Dynamics and Control Parameters for Trajectory Tracking Applications","authors":"L. Roveda, Marco Forgione, D. Piga","doi":"10.1109/UR49135.2020.9144761","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144761","url":null,"abstract":"Autonomy is increasingly demanded by industrial manipulators. Robots have to be capable to regulate their behavior to different operational conditions, without requiring high time/resource-consuming human intervention. Achieving an automated tuning of the control parameters of a manipulator is still a challenging task. This paper addresses the problem of automated tuning of the manipulator controller for trajectory tracking. A Bayesian optimization algorithm is proposed to tune both the low-level controller parameters (i.e., robot dynamics compensation) and the high-level controller parameters (i.e., the joint PID gains). The algorithm adapts the control parameters through a data-driven procedure, optimizing a userdefined trajectory-tracking cost. Safety constraints ensuring, e.g., closed-loop stability and bounds on the maximum joint position errors, are also included. The performance of the proposed approach is demonstrated on a torque-controlled 7degree-of-freedom FRANKA Emika robot manipulator. The 25 robot control parameters (i.e., 4 link-mass parameters and 21 PID gains) are tuned in 125 iterations, and comparable results with respect to the FRANKA Emika embedded position controller are achieved.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":"618 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129948000","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}
Pub Date : 2020-06-01DOI: 10.1109/UR49135.2020.9144989
Ye Yuan, Guangzhong Cao, Aibin Zhu, Xing Lyu, Yulong Wang
In this paper, a communication scheme of cloud platform for the lower limb exoskeleton robot is proposed. Firstly the wireless communication protocol Zigbee is used to build a sensor network to collect and summarize sensors' data of users' physiological information and robot movement. Secondly, Message Queuing Telemetry Transport (MQTT) is used to transmit the data into the cloud platform for data preservation and processing. Finally, the cloud platform is accessed remotely to obtain the physiological information of the user and robot movement based on the HyperText Transfer Protocol (HTTP). Experiments indicate its effectiveness and practicability of the proposed communication scheme to present sensors data to users or doctors in Web pages.
提出了一种面向下肢外骨骼机器人的云平台通信方案。首先利用无线通信协议Zigbee构建传感器网络，收集和汇总用户生理信息和机器人运动的传感器数据;其次，使用消息队列遥测传输(MQTT)将数据传输到云平台进行数据保存和处理。最后，基于超文本传输协议(HyperText Transfer Protocol, HTTP)远程访问云平台，获取用户和机器人运动的生理信息。实验证明了该通信方案的有效性和实用性，可以将传感器数据以网页形式呈现给用户或医生。
{"title":"Communication Scheme of Cloud Platform for the Lower Limb Exoskeleton Rehabilitation Robot","authors":"Ye Yuan, Guangzhong Cao, Aibin Zhu, Xing Lyu, Yulong Wang","doi":"10.1109/UR49135.2020.9144989","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144989","url":null,"abstract":"In this paper, a communication scheme of cloud platform for the lower limb exoskeleton robot is proposed. Firstly the wireless communication protocol Zigbee is used to build a sensor network to collect and summarize sensors' data of users' physiological information and robot movement. Secondly, Message Queuing Telemetry Transport (MQTT) is used to transmit the data into the cloud platform for data preservation and processing. Finally, the cloud platform is accessed remotely to obtain the physiological information of the user and robot movement based on the HyperText Transfer Protocol (HTTP). Experiments indicate its effectiveness and practicability of the proposed communication scheme to present sensors data to users or doctors in Web pages.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128503015","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}
Pub Date : 2020-06-01DOI: 10.1109/UR49135.2020.9144838
Sivapong Nilwong, G. Capi
This paper presents a deep reinforcement learning based robot outdoor navigation method using visual information. The deep q network (DQN) maps the visual data to robot action in a goal location reaching task. An advantage of the proposed method is that the implemented DQN is trained in the first-person shooter (FPS) game-based simulated environment provided by ViZDoom. The FPS simulated environment reduces the differences between the training and the real environments resulting in a good performance of trained DQNs. In our implementation a marker-based augmented reality algorithm with a simple object detection method is used to train the DQN. The proposed outdoor navigation system is tested in the simulation and real robot implementation, with no additional training. Experimental results showed that the navigation system trained inside the game-based simulation can guide the real robot in outdoor goal directed navigation tasks.
{"title":"Outdoor Robot Navigation System using Game-Based DQN and Augmented Reality","authors":"Sivapong Nilwong, G. Capi","doi":"10.1109/UR49135.2020.9144838","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144838","url":null,"abstract":"This paper presents a deep reinforcement learning based robot outdoor navigation method using visual information. The deep q network (DQN) maps the visual data to robot action in a goal location reaching task. An advantage of the proposed method is that the implemented DQN is trained in the first-person shooter (FPS) game-based simulated environment provided by ViZDoom. The FPS simulated environment reduces the differences between the training and the real environments resulting in a good performance of trained DQNs. In our implementation a marker-based augmented reality algorithm with a simple object detection method is used to train the DQN. The proposed outdoor navigation system is tested in the simulation and real robot implementation, with no additional training. Experimental results showed that the navigation system trained inside the game-based simulation can guide the real robot in outdoor goal directed navigation tasks.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124676174","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}
Pub Date : 2020-06-01DOI: 10.1109/UR49135.2020.9144849
Donghyung Ko, Mingyo Seo, Woosub Lee
To prevent the situation where the motors do not working appropriately by the teleoperation of unstructured environments or the system malfunctions, Dual-Motor-Driving (DMD) mechanism is applied to the mobile robots. While the conventional robot system where one actuator is assigned to each Degree of Freedom (DoF), it is essential to control two motors synchronously due to the complex mechanical system of the DMD. To maximize the load torque, each motor must rotate as the same angular velocity. In this paper, we represent a DMD mechanism with the synchronized angular velocities of the motors with an experiment as a fundamental DMD research.
{"title":"Synchronizing motors uisng PID with Dual-Motor-Driving","authors":"Donghyung Ko, Mingyo Seo, Woosub Lee","doi":"10.1109/UR49135.2020.9144849","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144849","url":null,"abstract":"To prevent the situation where the motors do not working appropriately by the teleoperation of unstructured environments or the system malfunctions, Dual-Motor-Driving (DMD) mechanism is applied to the mobile robots. While the conventional robot system where one actuator is assigned to each Degree of Freedom (DoF), it is essential to control two motors synchronously due to the complex mechanical system of the DMD. To maximize the load torque, each motor must rotate as the same angular velocity. In this paper, we represent a DMD mechanism with the synchronized angular velocities of the motors with an experiment as a fundamental DMD research.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128107248","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}
Pub Date : 2020-06-01DOI: 10.1109/UR49135.2020.9144853
Shugen Ma, Liang Du, Erina Tsuchiya, Mana Fuchimi
Soft food grasping in the food processing field is challenging for traditional robot hands because of the large demand, special hygiene cleanness and damage-free requirements. The paper-made grippers are low-cost and disposable to solve the crucial cleanness problem and they have soft structures which can adapt to the object shapes to avoid possible grasping damages. In this paper, we propose two paper-made grippers for the increasing soft object grasping requirements in the food processing field. One gripper uses a biomimetic mechanism of human hand to provide a force-closure grasping capability, and the other one uses a scoop mode to achieve a shape- closure grasping capability. Both grippers are low-cost, easy- fabrication and with simple actuation mechanism to enable a mass production. Experiments with different gripper designs were carried out to compare the two grippers performance, and preliminary results proved the possibility of applying these paper grippers for the food processing field.
{"title":"Paper-Made Grippers for Soft Food Grasping","authors":"Shugen Ma, Liang Du, Erina Tsuchiya, Mana Fuchimi","doi":"10.1109/UR49135.2020.9144853","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144853","url":null,"abstract":"Soft food grasping in the food processing field is challenging for traditional robot hands because of the large demand, special hygiene cleanness and damage-free requirements. The paper-made grippers are low-cost and disposable to solve the crucial cleanness problem and they have soft structures which can adapt to the object shapes to avoid possible grasping damages. In this paper, we propose two paper-made grippers for the increasing soft object grasping requirements in the food processing field. One gripper uses a biomimetic mechanism of human hand to provide a force-closure grasping capability, and the other one uses a scoop mode to achieve a shape- closure grasping capability. Both grippers are low-cost, easy- fabrication and with simple actuation mechanism to enable a mass production. Experiments with different gripper designs were carried out to compare the two grippers performance, and preliminary results proved the possibility of applying these paper grippers for the food processing field.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":" 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132041306","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}
Pub Date : 2020-06-01DOI: 10.1109/UR49135.2020.9144839
S. Mann, René Glebke, Ike Kunze, D. Scheurenberg, Rahul Sharma, U. Reisgen, Klaus Wehrle, D. Abel
In this study, a robot welding application for the control of the weld seam geometry by means of in situ image acquisition and robot trajectory correction has been investigated. For this approach, the arc centroid position of the process images was correlated with the weld seam flank ratio of the examined fillet weld seam application. The correction was performed along a selected trajectory plane without violating the welding process stability. In addition, the system as a sum of its partial competences with their different synchronization requirements and corresponding bottlenecks was illuminated. Optimization suggestions arose especially in advanced control engineering as well as in-kernel processing and in-network computing. In summary, it can be stated that, on the one hand, the examined relationship between arc centroid and flank ratio is subject to interference and that image processing in particular has potential for optimization.
{"title":"Study on weld seam geometry control for connected gas metal arc welding systems*","authors":"S. Mann, René Glebke, Ike Kunze, D. Scheurenberg, Rahul Sharma, U. Reisgen, Klaus Wehrle, D. Abel","doi":"10.1109/UR49135.2020.9144839","DOIUrl":"https://doi.org/10.1109/UR49135.2020.9144839","url":null,"abstract":"In this study, a robot welding application for the control of the weld seam geometry by means of in situ image acquisition and robot trajectory correction has been investigated. For this approach, the arc centroid position of the process images was correlated with the weld seam flank ratio of the examined fillet weld seam application. The correction was performed along a selected trajectory plane without violating the welding process stability. In addition, the system as a sum of its partial competences with their different synchronization requirements and corresponding bottlenecks was illuminated. Optimization suggestions arose especially in advanced control engineering as well as in-kernel processing and in-network computing. In summary, it can be stated that, on the one hand, the examined relationship between arc centroid and flank ratio is subject to interference and that image processing in particular has potential for optimization.","PeriodicalId":360208,"journal":{"name":"2020 17th International Conference on Ubiquitous Robots (UR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130245663","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：