Pub Date : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268438
Hoang Quoc Dong, Soon‐Geul Lee, S. Woo, T. LeB..
Spherical robots are the mobile robots with the locomoting by displacing its centre of gravity to generate torque and rotate itself. Therefore, the angle of the main body inside the robot determines the position and posture of the robot. There is only one contact point between the robot and the ground, and the inappropriate control strategy can generate the sizeable angular amplitude of the main body. As a result, the stable movement of the robot cannot be satisfied along with the appeared vibrations. This problem significantly impacts the tracking control quality and creates the clumsy gestures of the robot. In this research, an under-actuated dynamic model-based back-stepping control focusing on the rolling motion is developed and applied for a designed two-wheel spherical robot. With the provided closed-loop control law, both the precision and stability of the robot’s movement are guaranteed. The entire work’s efficiency is investigated by the experimental results.
{"title":"Back-stepping Approach for Rolling Motion Control of an Under-actuated Two-wheel Spherical Robot","authors":"Hoang Quoc Dong, Soon‐Geul Lee, S. Woo, T. LeB..","doi":"10.23919/ICCAS50221.2020.9268438","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268438","url":null,"abstract":"Spherical robots are the mobile robots with the locomoting by displacing its centre of gravity to generate torque and rotate itself. Therefore, the angle of the main body inside the robot determines the position and posture of the robot. There is only one contact point between the robot and the ground, and the inappropriate control strategy can generate the sizeable angular amplitude of the main body. As a result, the stable movement of the robot cannot be satisfied along with the appeared vibrations. This problem significantly impacts the tracking control quality and creates the clumsy gestures of the robot. In this research, an under-actuated dynamic model-based back-stepping control focusing on the rolling motion is developed and applied for a designed two-wheel spherical robot. With the provided closed-loop control law, both the precision and stability of the robot’s movement are guaranteed. The entire work’s efficiency is investigated by the experimental results.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"40 1","pages":"233-238"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79877686","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 : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268280
Woo-Yong Kim, Pyeongyeon Lee, Jonghoon Kim, Kyung-Soo Kim
This study proposes a nonlinear representation of the open circuit voltage curve for the state of charge estimation of LiFePO4 battery cell. The proposed open circuit voltage representation is devised by dividing the linear term and nonlinear term of given curve shape. The advantage of the proposed method is that by establishing nonlinear battery cell model, the state of charge can be estimated even if there exists voltage plateau in the open circuit voltage curve. The conventional linearized method cannot estimate the SOC in such area. The effectiveness of the proposed method was verified through simulation with virtual battery cell having wide voltage plateau area in open circuit voltage curve.
{"title":"A Nonlinear Open Circuit Voltage Representation Enabling State of Charge Estimation at the Voltage Plateau Region of LiFePO4 Battery","authors":"Woo-Yong Kim, Pyeongyeon Lee, Jonghoon Kim, Kyung-Soo Kim","doi":"10.23919/ICCAS50221.2020.9268280","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268280","url":null,"abstract":"This study proposes a nonlinear representation of the open circuit voltage curve for the state of charge estimation of LiFePO4 battery cell. The proposed open circuit voltage representation is devised by dividing the linear term and nonlinear term of given curve shape. The advantage of the proposed method is that by establishing nonlinear battery cell model, the state of charge can be estimated even if there exists voltage plateau in the open circuit voltage curve. The conventional linearized method cannot estimate the SOC in such area. The effectiveness of the proposed method was verified through simulation with virtual battery cell having wide voltage plateau area in open circuit voltage curve.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"16 1","pages":"356-359"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76685536","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 : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268225
A. Jalil, Jun Kobayashi
This study aims to develop a network architecture for low-cost multi-robot systems, in which robots operate with limited hardware capability and on-board computational power. Low-speed data processing and high latency time in communication are unavoidable issues in such a multi-robot system. To address those problems, this study proposes Aggregated Robot Processing – Robot Operating System (ARP-ROS) as a network architecture for low-cost multi-robot systems. This network architecture arranges a computing environment dedicated to data processing in a multi-robot system. In the proposed network architecture, most of sensor data obtained by each robot are transmitted to the computing environment via the communication network and processed there, and then control commands are sent back to the robots. For the data exchange in the network architecture, ROS2 node communication is employed because it uses Data Distribution Service (DDS) suitable for real-time distributed embedded systems. In addition, Cache-Control Algorithm (CCA) is introduced to the communication network for its performance improvement. This paper presents experimental analyses of the ARP-ROS with CCA in terms of latency time and data process failures.
本研究旨在开发一种低成本多机器人系统的网络架构，其中机器人在有限的硬件能力和板载计算能力下运行。在这种多机器人系统中，低速的数据处理和高时延的通信是不可避免的问题。为了解决这些问题，本研究提出聚合机器人处理-机器人操作系统(ARP-ROS)作为低成本多机器人系统的网络架构。这种网络架构安排了一个专用于多机器人系统中数据处理的计算环境。在提出的网络架构中，每个机器人获取的大部分传感器数据通过通信网络传输到计算环境并在计算环境中进行处理，然后将控制命令发送回机器人。网络架构中的数据交换采用ROS2节点通信，因为它使用了适合于实时分布式嵌入式系统的DDS (data Distribution Service)。此外，为了提高通信网络的性能，还将缓存控制算法(CCA)引入到通信网络中。本文从延迟时间和数据处理失败两方面对带有CCA的ARP-ROS进行了实验分析。
{"title":"Experimental Analyses of an Efficient Aggregated Robot Processing with Cache-Control for Multi-Robot System","authors":"A. Jalil, Jun Kobayashi","doi":"10.23919/ICCAS50221.2020.9268225","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268225","url":null,"abstract":"This study aims to develop a network architecture for low-cost multi-robot systems, in which robots operate with limited hardware capability and on-board computational power. Low-speed data processing and high latency time in communication are unavoidable issues in such a multi-robot system. To address those problems, this study proposes Aggregated Robot Processing – Robot Operating System (ARP-ROS) as a network architecture for low-cost multi-robot systems. This network architecture arranges a computing environment dedicated to data processing in a multi-robot system. In the proposed network architecture, most of sensor data obtained by each robot are transmitted to the computing environment via the communication network and processed there, and then control commands are sent back to the robots. For the data exchange in the network architecture, ROS2 node communication is employed because it uses Data Distribution Service (DDS) suitable for real-time distributed embedded systems. In addition, Cache-Control Algorithm (CCA) is introduced to the communication network for its performance improvement. This paper presents experimental analyses of the ARP-ROS with CCA in terms of latency time and data process failures.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"7 1","pages":"1105-1109"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82501209","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 : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268300
Tae-Jung Kim, Ji-hoon Kim, Kuk‐Hyun Ahn, Jae-Bok Song
Recently, the demand for collaborative robots is increasing in the industrial field. However, as the collaborative robots share the same workspace with human workers, there is a high possibility of collision between the robot and the worker. A possible method to ensure the safety of a human worker is to restrict the impact force that the robot exerts on the worker during a collision. That is, if the impact force can be predicted, the robot motion that causes excessive impact force can be detected and handled properly before the actual robot motion. To this end, an algorithm for predicting the impact force generated by a collision is proposed, and a method for ensuring the human safety, by modifying the trajectory of the robot when the excessive impact is predicted with current motion, is investigated. To establish the impact force prediction model, collision experiments were performed with a 6-DOF collaborative robot and a dummy. Moreover, an algorithm for minimizing the impact force, by reducing the end-effector velocity of the robot when excessive impact is predicted from the established model, is proposed to ensure the human safety. The performance of the algorithm was verified through various experiments.
{"title":"Impact Force Minimization Algorithm for Collaborative Robots Using Impact Force Prediction Model","authors":"Tae-Jung Kim, Ji-hoon Kim, Kuk‐Hyun Ahn, Jae-Bok Song","doi":"10.23919/ICCAS50221.2020.9268300","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268300","url":null,"abstract":"Recently, the demand for collaborative robots is increasing in the industrial field. However, as the collaborative robots share the same workspace with human workers, there is a high possibility of collision between the robot and the worker. A possible method to ensure the safety of a human worker is to restrict the impact force that the robot exerts on the worker during a collision. That is, if the impact force can be predicted, the robot motion that causes excessive impact force can be detected and handled properly before the actual robot motion. To this end, an algorithm for predicting the impact force generated by a collision is proposed, and a method for ensuring the human safety, by modifying the trajectory of the robot when the excessive impact is predicted with current motion, is investigated. To establish the impact force prediction model, collision experiments were performed with a 6-DOF collaborative robot and a dummy. Moreover, an algorithm for minimizing the impact force, by reducing the end-effector velocity of the robot when excessive impact is predicted from the established model, is proposed to ensure the human safety. The performance of the algorithm was verified through various experiments.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"100 1","pages":"869-872"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76223290","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}
Object detection is one of the main task for the deep learning applications. Deep learning performance has already exceeded human’s detection ability, in the case when there are lots of data for training deep neural networks. In the case of military fields, there are needs to resolve the data shortage problem to employ deep learning system efficiently with benefits. Generating the synthetic data can be a solution, but the domain gap between the synthetic and real data is still an obstacle for training the model. In this paper, we propose a method for decreasing the domain gap by applying style transfer techniques to synthetic data for military vehicle detection. Utilizing FastPhotoStyle to the synthetic data aids efficiently improving the accuracy of object detection when the real data is insufficiency for training. Specifically, we show that stylization which enables artificial data more realistic diminishes the domain gap by evaluating the visualization of their distributions using principal component analysis and Fréchet inception distance score. As a result, the performance has been improved about 8% in the AP@50 metric for stylized synthetic data.
{"title":"Applying FastPhotoStyle to Synthetic Data for Military Vehicle Detection","authors":"Hyeongkeun Lee, Kyungmin Lee, Hunmin Yang, Se-Yoon Oh","doi":"10.23919/ICCAS50221.2020.9268331","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268331","url":null,"abstract":"Object detection is one of the main task for the deep learning applications. Deep learning performance has already exceeded human’s detection ability, in the case when there are lots of data for training deep neural networks. In the case of military fields, there are needs to resolve the data shortage problem to employ deep learning system efficiently with benefits. Generating the synthetic data can be a solution, but the domain gap between the synthetic and real data is still an obstacle for training the model. In this paper, we propose a method for decreasing the domain gap by applying style transfer techniques to synthetic data for military vehicle detection. Utilizing FastPhotoStyle to the synthetic data aids efficiently improving the accuracy of object detection when the real data is insufficiency for training. Specifically, we show that stylization which enables artificial data more realistic diminishes the domain gap by evaluating the visualization of their distributions using principal component analysis and Fréchet inception distance score. As a result, the performance has been improved about 8% in the AP@50 metric for stylized synthetic data.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"12 1","pages":"137-140"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87836472","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 : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268239
Young-Hwan Han, Changhyeon Kim, Youngseok Jang, H. Kim
The Kanade-Lucas-Tomasi(KLT) tracking algorithm is a widely used feature tracking algorithm in the field of computer vision(CV). The selection of proper warping parameters for the estimation of optical flow between adjacent image frames is crucial to obtain accurate and robust tracking results. We compare the various warping parameter settings in an autonomous driving environment based on the modified KLT algorithm with some well-known techniques. The skew and rotation parameters did not show better performance, but rather made convergence more difficult. The scale-parameter-added model has the best performance among the sets of warping parameters.
{"title":"Parametric analysis of KLT algorithm in autonomous driving","authors":"Young-Hwan Han, Changhyeon Kim, Youngseok Jang, H. Kim","doi":"10.23919/ICCAS50221.2020.9268239","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268239","url":null,"abstract":"The Kanade-Lucas-Tomasi(KLT) tracking algorithm is a widely used feature tracking algorithm in the field of computer vision(CV). The selection of proper warping parameters for the estimation of optical flow between adjacent image frames is crucial to obtain accurate and robust tracking results. We compare the various warping parameter settings in an autonomous driving environment based on the modified KLT algorithm with some well-known techniques. The skew and rotation parameters did not show better performance, but rather made convergence more difficult. The scale-parameter-added model has the best performance among the sets of warping parameters.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"4 1","pages":"184-189"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88407720","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 : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268329
Youkyung Hong, Sunggoo Jung, Suseong Kim, J. Cha
This study proposes a new mission planning method to perform routing with multiple quadrotors. Unlike conventional routing missions, this study considers the specialized routing mission for quadrotors where there is a visit priority between nodes, and there is a task to be performed at the node. One of our contributions is that a multi-layered hierarchical architecture is designed for mission planning itself at the top level, and for interworking with path planning and flight control required at the lower levels. In mission planning, to determine the optimal pair between agents and visiting nodes and the optimal order of nodes, the optimization problem is designed and solved based on mixed-integer linear programming. Furthermore, we evaluate our method by performing MATLAB and Gazebo co-simulation in a ROS environment.
{"title":"Multi-UAV Routing with Priority using Mixed Integer Linear Programming","authors":"Youkyung Hong, Sunggoo Jung, Suseong Kim, J. Cha","doi":"10.23919/ICCAS50221.2020.9268329","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268329","url":null,"abstract":"This study proposes a new mission planning method to perform routing with multiple quadrotors. Unlike conventional routing missions, this study considers the specialized routing mission for quadrotors where there is a visit priority between nodes, and there is a task to be performed at the node. One of our contributions is that a multi-layered hierarchical architecture is designed for mission planning itself at the top level, and for interworking with path planning and flight control required at the lower levels. In mission planning, to determine the optimal pair between agents and visiting nodes and the optimal order of nodes, the optimization problem is designed and solved based on mixed-integer linear programming. Furthermore, we evaluate our method by performing MATLAB and Gazebo co-simulation in a ROS environment.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"22 1","pages":"699-702"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82806316","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 : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268340
Jin-Hyeng Park, W. Na, Jonghoon Kim
This paper proposes an SOC (state of charge) and SOH (state of health) estimation technique using sensor fusion method to solve the problem of battery system stability deterioration due to voltage variation in cell-to-cell. In order to reflect the cell-to-cell variance, we use the measurement fusion method based on the multi cell model. From this model, the dual extended Kalman filter is utilized for estimating the SOC and SOH.
{"title":"State of charge and State of health estimation method based on measurement fusion and dual extended Kalman filter for combining the inhomogeneity of cell characteristics","authors":"Jin-Hyeng Park, W. Na, Jonghoon Kim","doi":"10.23919/ICCAS50221.2020.9268340","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268340","url":null,"abstract":"This paper proposes an SOC (state of charge) and SOH (state of health) estimation technique using sensor fusion method to solve the problem of battery system stability deterioration due to voltage variation in cell-to-cell. In order to reflect the cell-to-cell variance, we use the measurement fusion method based on the multi cell model. From this model, the dual extended Kalman filter is utilized for estimating the SOC and SOH.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"194 1","pages":"648-651"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82952425","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 : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268201
D. Shim, H. Kim
Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression. We propose a Gaussian Deep Recurrent visual Attention Model (GDRAM) - a reinforcement learning based lightweight deep neural network for large scale image classification that outperforms the conventional CNN (Convolutional Neural Network) which uses the entire image as input. Highly inspired by the biological visual recognition process, our model mimics the stochastic location of the retina with Gaussian distribution. We evaluate the model on Large cluttered MNIST, Large CIFAR-10 and Large CIFAR-100 datasets which are resized to 128 in both width and height. The implementation of Gaussian RAM in PyTorch and its pretrained model are available at : https://github.com/dsshim0125/gaussian-ram
{"title":"Gaussian RAM: Lightweight Image Classification via Stochastic Retina-Inspired Glimpse and Reinforcement Learning","authors":"D. Shim, H. Kim","doi":"10.23919/ICCAS50221.2020.9268201","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268201","url":null,"abstract":"Previous studies on image classification have mainly focused on the performance of the networks, not on real-time operation or model compression. We propose a Gaussian Deep Recurrent visual Attention Model (GDRAM) - a reinforcement learning based lightweight deep neural network for large scale image classification that outperforms the conventional CNN (Convolutional Neural Network) which uses the entire image as input. Highly inspired by the biological visual recognition process, our model mimics the stochastic location of the retina with Gaussian distribution. We evaluate the model on Large cluttered MNIST, Large CIFAR-10 and Large CIFAR-100 datasets which are resized to 128 in both width and height. The implementation of Gaussian RAM in PyTorch and its pretrained model are available at : https://github.com/dsshim0125/gaussian-ram","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"85 1","pages":"155-160"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86622169","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 : 2020-10-13DOI: 10.23919/ICCAS50221.2020.9268291
Francisco Yumbla, Meseret Abeyabas, T. Luong, June-sup Yi, H. Moon
In this paper, we analyze and propose a recognition process of plug-in cable connectors for wiring harness assembly tasks using image processing. For manipulation and routing of wire harness, knowing the accurate pose of the cable connector is very critical in the grasping moment. The recognition process is crucial to minimize the error in the manipulation of the connectors. Nowadays, we notice that collaborative robot manipulators or small size industrial robot manipulators attain high accuracy and repeatability levels (sub-millimeter); thus, demonstrate very precise position control capabilities. Using those capacities and with the correct recognition system, we can apply to the automation of the wire harness assembly process. For that reason, we propose a connector recognition system to obtain the precise position of the connectors on a work table; which is necessary to obtain a successful grasping and manipulation of the connectors in a wire harness. The system and the recognition process are explained in detail, and validated experimentally.
{"title":"Preliminary Connector Recognition System Based on Image Processing for Wire Harness Assembly Tasks","authors":"Francisco Yumbla, Meseret Abeyabas, T. Luong, June-sup Yi, H. Moon","doi":"10.23919/ICCAS50221.2020.9268291","DOIUrl":"https://doi.org/10.23919/ICCAS50221.2020.9268291","url":null,"abstract":"In this paper, we analyze and propose a recognition process of plug-in cable connectors for wiring harness assembly tasks using image processing. For manipulation and routing of wire harness, knowing the accurate pose of the cable connector is very critical in the grasping moment. The recognition process is crucial to minimize the error in the manipulation of the connectors. Nowadays, we notice that collaborative robot manipulators or small size industrial robot manipulators attain high accuracy and repeatability levels (sub-millimeter); thus, demonstrate very precise position control capabilities. Using those capacities and with the correct recognition system, we can apply to the automation of the wire harness assembly process. For that reason, we propose a connector recognition system to obtain the precise position of the connectors on a work table; which is necessary to obtain a successful grasping and manipulation of the connectors in a wire harness. The system and the recognition process are explained in detail, and validated experimentally.","PeriodicalId":6732,"journal":{"name":"2020 20th International Conference on Control, Automation and Systems (ICCAS)","volume":"37 4 1","pages":"1146-1150"},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89114787","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：