{"title":"Autonomous hoisting and assembly system","authors":"Yu Sun, Chunmeng Lu, Yao-Yu Yang, Peng-Yuan Chen, S. Kang, Chia‐Ming Chang","doi":"10.1109/ARIS.2017.8297191","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297191","url":null,"abstract":"Hoisting is an important part of a construction project, and it often falls upon workers to carry out fine tuning on the connector. However, assembling steel-structural components is not a safe process, and the method in use currently is not suitable for customized components. Automation in the construction industry is increasing as a result of developments in the field of robotics; in the light of this, we propose a system of autonomous hoisting and assembly. The proposed system contains two critical designs to carry out the hoisting process automatically: the horizontal connector design and the construction method design. In the connector part, we propose a horizontal connector to improve the hoisting process. In addition, we attach sensors to help us complete the construction process. The use of the horizontal connector obviates the need for manual adjustment during the hoisting process. This also reduces the risk of injury to workers and facilitates mass production. In the construction method part, the whole hoisting process is designed to be completed by one crane. In this study, we verified the design of the connector by mechanical testing and 3D printing. The result shows that the design of the connector can not only complete the task but also improve the security in construction.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125117248","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}
Yu-Chun Chen, Shih-Tsung Ma, Lily Hsu, Yun-Chen Lin, Pei-Chun Lin
{"title":"Design and implementation of a quadrupedal crawling-rolling robot","authors":"Yu-Chun Chen, Shih-Tsung Ma, Lily Hsu, Yun-Chen Lin, Pei-Chun Lin","doi":"10.1109/ARIS.2017.8297171","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297171","url":null,"abstract":"This paper reports on the development of a quadrupedal crawling-rolling hybrid robot that can switch motions under various circumstances. Through mechanical design, we reduced the number of motors used without sacrificing fluency of motion. The robot was empirically built and tested to performed the designate crawling and rolling behaviors.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129932754","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}
Shu-Yin Chiang, Yi-Quan Jiang, Hsin-Tieh Yang, Chia-Chin Wang, Yu-chen Lee
{"title":"The design of intelligent interactive service robot","authors":"Shu-Yin Chiang, Yi-Quan Jiang, Hsin-Tieh Yang, Chia-Chin Wang, Yu-chen Lee","doi":"10.1109/ARIS.2017.8297198","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297198","url":null,"abstract":"This study aims to develop the intelligent interactive multi-functional robot to provide companion and entertainment. To obtain the environmental information, we use Kinect depth image as the visual system platform and to perform the image processing operations. Then, the image processing results are applied to the robot behavior planning, integrated with omni-directional wheels, high power motors, FPGA and ARM-based development board as motion system. The lower body of the robot is constructed by four omni-directional wheels, and the upper body is in humanoid design. In this study, we use the information extracted from depth image stream of Kinect and integrate the robot localization system to build the real-time environment map and achieve the obstacle avoidance. In addition, we use Kinect skeleton detection and human facial expression recognition to accomplish the task of the intelligent interaction.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124085167","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}
{"title":"Mixture of trees with three layers","authors":"G. Hsu, K. Ho, Cheng-Hua Hsieh","doi":"10.1109/ARIS.2017.8297179","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297179","url":null,"abstract":"The Tree Structured Model (TSM) is proven effective for solving face detection, pose estimation and landmark localization in an unified model; however, the drawback of its processing time makes it unfavorable in practical applications, especially when dealing with cases of multiple faces. We propose the Mixture of Trees with Three Layers (3L-MoT) to improve the run-time speed. The 3L-MoT is composed of three component TSMs, the coarse TSM (c-TSM), median TSM(m-TSM) and the refined TSM (r-TSM), and a Bilateral Support Vector Regressor (BSVR). The c-TSM is built on the low-resolution octaves of samples so that it provides coarse but fast face detection. The m-TSM remove the false positive generate from c-TSM to speed up the process in r-TSM. The r-TSM is built on the high resolution octaves so that it can locate the landmarks on the face candidates given by the m-TSM and improve precision. The r-TSM based landmarks are used in the forward BSVR as references to locate the dense set of landmarks, which are then used in the backward BSVR to relocate the landmarks with large localization errors. The forward and backward regression goes on iteratively until convergence. In spite of the negative correlation between run-time speed and performance, the performance of the 3L-MoT is validated on Multi-PIE benchmark databases to be similar with TSM[10] while enhanced in processing time.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124751183","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}
{"title":"Knowledge sharing approaches for distributed agents system","authors":"Kao-Shing Hwang, Chi-Wei Hsieh, Wei-Cheng Jiang","doi":"10.1109/ARIS.2017.8297184","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297184","url":null,"abstract":"Considering situations in a multi-agent system, if there are tremendous number of agents sharing knowledge with each other, it is complicated activities hard to be solved. This thesis proposed a method that all agents just connect with a server to alleviate the complexity of the experiences exchange activities. The server collects learning knowledge loaded from all the agents, merges the knowledge, and shares the knowledge to all agents which lack akin experiences. The agents utilized the proposed Pheromone Mechanism in Ant Colony Algorithm to evaluate whether an experience is worthy to upload to the server. Meanwhile, to deal with the problem of massive data processing, this thesis used the open source software, Apache Hadoop, along with the MapReduce programming model. The agents can take shared experiences integrated with their own knowledge to achieve knowledge sharing and increase the efficiency significantly. The proposed approach in this thesis was implemented by a homemade server and personal computers.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123160844","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}
{"title":"Design and hardware realization of wheel-shaped object labeling and quality inspection system","authors":"Chi-Hin Chao, Yen‐Chen Liu","doi":"10.1109/ARIS.2017.8297192","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297192","url":null,"abstract":"The design and hardware realization of a cooperating platform that is capable of wheel-shaped objects with different sizes and thicknesses are presented in this paper. Considering the symmetric characteristics of wheel-shaped object the platform is designed to have the abilities of transferring, gripping and rotating to deal with specific missions. By using a processing unit to integrate the information of camera and sensors which are installed on the platform, also a graphical user interface (GUI) is constructed by Lab VIEW to perform human-machine interaction, a Cyber Physical System (CPS) is introduced. Taking the labeling process as example, the platform will cooperate with the labeling device to verify the design.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"45 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133078290","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}
{"title":"GPU-accelerated image alignment for object detection in industrial applications","authors":"Trung-Son Le, Chyi-Yeu Lin","doi":"10.1109/ARIS.2017.8297173","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297173","url":null,"abstract":"This research proposes a practical method for detecting featureless objects by using image alignment approach with a robust similarity measure in industrial applications. This similarity measure is robust against occlusion, illumination changes and background clutter. The performance of the proposed GPU (Graphics Processing Unit) accelerated algorithm is deemed successful in experiments of comparison between both CPU and GPU implementations.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117040699","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}
{"title":"Improving robot grasping plans with affordance","authors":"Y. Su, Alan Liu, Weihong Lu","doi":"10.1109/ARIS.2017.8297172","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297172","url":null,"abstract":"The quality of grasping is supported by leveraging the concept of affordance in this paper to improve grasping operations. When introducing flexibility in handling different objects in a dynamically changing environment, uncertainty in grasping areas and operations may cause problems. We have studied the relationship between the objects, their associated operations, and the effect of performing such operations. With such information, the robot arm may be able to limit some improper grasping operations and angles in order to introduce better plans more efficiently. We use OpenRAVE as the simulation environment to carry out the plans generated. The experiments show that better plans were generated with affordance.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129882484","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}
Chih-Tien Kuo, Wen-Yung Li, Yu-Hsun Wang, Pei-Chun Lin
{"title":"Dynamic modeling analysis of a spider monkey robot","authors":"Chih-Tien Kuo, Wen-Yung Li, Yu-Hsun Wang, Pei-Chun Lin","doi":"10.1109/ARIS.2017.8297197","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297197","url":null,"abstract":"We developed a dynamic model of a spider monkey robot that was constructed to imitate the brachiating behavior of real spider monkeys. The equations of motion were derived using a Lagrangian method. The dynamic behaviors of the model were investigated by varying the model parameters. The optimal operating conditions found from the simulation can serve as a guide to the initiation of dynamic behavior in the empirical robot.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128258681","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}
S. Chien, Feng-Chia Chang, K. Hua, I-Ying Chen, Yung-Yao Chen
{"title":"Contrast enhancement by using global and local histogram information jointly","authors":"S. Chien, Feng-Chia Chang, K. Hua, I-Ying Chen, Yung-Yao Chen","doi":"10.1109/ARIS.2017.8297188","DOIUrl":"https://doi.org/10.1109/ARIS.2017.8297188","url":null,"abstract":"Global histogram equalization (GHE) is a common technique used to enhance image contrast by utilizing the histogram information of the input image to create its transformation function. However, it usually fails to adapt with the local image brightness features. By contrast, Local histogram equalization (LHE) is suitable for handling the local feature; whereas it suffers from halo or blocking artifacts and requires high computation power. This paper presents an effective hybrid method for image contrast enhancement that jointly combines local information and global information. Therefore, it provides a regional enhanced effect without generating visual artifacts or halo in local areas. Experimental results show that our proposed method produces higher visual quality on the enhanced images than the GHE method does.","PeriodicalId":104750,"journal":{"name":"2017 International Conference on Advanced Robotics and Intelligent Systems (ARIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126662133","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}