{"title":"The Design and Research of Intelligent Assembly Instructions in Virtual-Real Fusion Environment","authors":"Quan Yu, X. Bai, Sili Wei, Yuxiang Yan, X. Zhang, Qiang Zhang, Yongqiang Cao, Jiaxu Huang","doi":"10.1109/IARCE57187.2022.00028","DOIUrl":"https://doi.org/10.1109/IARCE57187.2022.00028","url":null,"abstract":"Virtual assembly instruction refers to the assembly guidance instruction that superimposes virtual assembly guidance information on the real environment, making the product assembly guidance procedure more intuitive and convenient. Presently, virtual assembly instructions lack the capacity for adaptive adjustment; as a result, this research was conducted. First, the concept of intelligent assembly instruction with adaptive capability is proposed, and then the overall design framework for intelligent assembly instruction is constructed based on its definition. Then, the key components of intelligent assembly instructions, namely the dynamic decision-making of assembly guidance content and the intelligent selection of visual display mode, are designed. Finally, we construct a prototype system to demonstrate the adaptability of intelligent assembly instructions during the assembly guidance process. The experimental results demonstrate that the intelligent assembly instructions presented in this study are capable of providing dynamic assembly guidance for assembly tasks and can intelligently determine visual display mode. Intelligent assembly instructions decrease the difficulty of assembly, enhance the user’s comprehension of assembly guidance information, and provide a positive assembly experience.","PeriodicalId":329178,"journal":{"name":"2022 International Conference on Industrial Automation, Robotics and Control Engineering (IARCE)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122652840","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":"Interpretable sentiment analysis based on sentiment words’ syntax information","authors":"Qing Zhao, Huaping Zhang, Jianyun Shang","doi":"10.1109/iarce57187.2022.00025","DOIUrl":"https://doi.org/10.1109/iarce57187.2022.00025","url":null,"abstract":"In recent years, with the vigorous development of deep learning, the pre-trained models such as Bert and GPT have been brilliant, and the sentiment analysis task has made increasingly outstanding achievements. The sentimental accuracy of model recognition is getting higher and higher, and the related application fields are also getting wider and wider. However, because deep learning is a black box model, its internal decision-making mechanism is not transparent to users, and it can’t reasonably explain the output of the model, which brings great limitations to the application of sentiment analysis. In this paper, we integrate the syntax tree based on sentiment words into the embedding module and the attention module of the interpretable sentiment model, and filter the evidence tokens output by the model to achieve the interpretability of sentiment analysis. The model is validated on the DuTrust dataset, and the experiment proves the validity of sentiment words' syntax in interpretable sentiment analysis.","PeriodicalId":329178,"journal":{"name":"2022 International Conference on Industrial Automation, Robotics and Control Engineering (IARCE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125374746","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":"Angle and Heuristic Guided Probabilistic Foam for Local Path Replanning","authors":"Onur Yildirim, Aykut Özdemir, S. Bogosyan","doi":"10.1109/IARCE57187.2022.00022","DOIUrl":"https://doi.org/10.1109/IARCE57187.2022.00022","url":null,"abstract":"Online planning and replanning methods are commonly used in unknown or dynamic environments to ensure path safety. In this paper, we proposed a novel local path replanning algorithm. We adapted Probabilistic Foam (PF) idea for reactive planning tasks. Probabilistic Foam infrastructure is selected for several reasons. Firstly, these types of planners are lightweight, and secondly, they ensure collision-free path generation. But they don’t guarantee path optimality. In this work, the latest achievement on the PF idea was further improved and adapted to local planning tasks. We proved that our algorithm produces shorter paths and more lightweight than alternatives by conducting qualitative and quantitative tests. We also test our algorithm as a local planner on coverage path tracking and 2d obstacle avoidance tasks designed for a quadrotor in a realistic simulation environment.","PeriodicalId":329178,"journal":{"name":"2022 International Conference on Industrial Automation, Robotics and Control Engineering (IARCE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133215414","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}
Jian Qian, Miao Sun, Ashley Lee, Jie Li, Shenglong Zhuo, Patrick Chiang
{"title":"SDformer: Efficient End-to-End Transformer for Depth Completion","authors":"Jian Qian, Miao Sun, Ashley Lee, Jie Li, Shenglong Zhuo, Patrick Chiang","doi":"10.1109/IARCE57187.2022.00021","DOIUrl":"https://doi.org/10.1109/IARCE57187.2022.00021","url":null,"abstract":"Depth completion aims to predict dense depth maps with sparse depth measurements from a depth sensor. Currently, Convolutional Neural Network (CNN) based models are the most popular methods applied to depth completion tasks. However, despite the excellent high-end performance, they suffer from a limited representation area. To overcome the drawbacks of CNNs, a more effective and powerful method has been presented: the Transformer, which is an adaptive self-attention setting sequence-to-sequence model. While the standard Transformer quadratically increases the computational cost from the key-query dot-product of input resolution which improperly employs depth completion tasks. In this work, we propose a different window-based Transformer architecture for depth completion tasks named Sparse-to-Dense Transformer (SDformer). The network consists of an input module for the depth map and RGB image features extraction and concatenation, a U-shaped encoder-decoder Transformer for extracting deep features, and a refinement module. Specifically, we first concatenate the depth map features with the RGB image features through the input model. Then, instead of calculating self-attention with the whole feature maps, we apply different window sizes to extract the long-range depth dependencies. Finally, we refine the predicted features from the input module and the U-shaped encoder-decoder Transformer module to get the enriching depth features and employ a convolution layer to obtain the dense depth map. In practice, the SDformer obtains state-of-the-art results against the CNN-based depth completion models with lower computing loads and parameters on the NYU Depth V2 and KITTI DC datasets.","PeriodicalId":329178,"journal":{"name":"2022 International Conference on Industrial Automation, Robotics and Control Engineering (IARCE)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134636655","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":"An Improved Snake Optimization Algorithm with Opposition-Based Population Initialization","authors":"Yuancheng Xu, Mengji Shi, Long You, Weihao Li, Boxian Lin, Kaiyu Qin","doi":"10.1109/IARCE57187.2022.00017","DOIUrl":"https://doi.org/10.1109/IARCE57187.2022.00017","url":null,"abstract":"Snake Optimization (SO) is a newly developed swarm-intelligence-based optimization algorithm inspired by the behavior of snakes seeking better food sources, which potentially applies to multi-vehicle task assignments and trajectory optimization. The paper comes up with an improved SO that integrated with Opposition-based Learning (OBL) which helps to filter the snake population, reserving only the individuals closer to food. In contrast, the original SO with randomly generated population performs extra iteration steps for unfit snakes to survive, and spends more computational time. Simulations are conducted to illustrate a comparison between the proposed algorithm and the conventional one, where the former exhibits faster convergence to the optimal solutions and guarantees higher accuracy without population expansion, and these features gives rise to its applications in real-time embedded computing systems for automated vehicles.","PeriodicalId":329178,"journal":{"name":"2022 International Conference on Industrial Automation, Robotics and Control Engineering (IARCE)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115068735","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":"Research on Scenario based Test for auto-landing system","authors":"Tang Ru, Yao Zhichao","doi":"10.1109/iarce57187.2022.00013","DOIUrl":"https://doi.org/10.1109/iarce57187.2022.00013","url":null,"abstract":"The current commercial aircraft is adopted the large scale integration design method, it is a big challenge to high integration and complex system. The traditional test method is based on specification or requirement, it is mainly focus on internal and external logic and function interface, but it is not test for severe scenario influence to the aircraft system, such as pilot maneuver, limit condition, complex environment, control mode transition.etc, so some issues which should be found on laboratory are found on flight test or operational test later. This article proposes a scenario based test method on auto-landing system. Firstly, capturing the test scenario based on auto-landing system function analysis, build the traceability between scenario and requirements. Secondly, developing the operational scenario model and flight scenario model, build the test environment. Finally, validating the related requirements based on auto scenario test.","PeriodicalId":329178,"journal":{"name":"2022 International Conference on Industrial Automation, Robotics and Control Engineering (IARCE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124953289","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":"Analysis of Facial Expressions in Class Based on Lightweight Convolutional Neural Network","authors":"Zhiyuan He, Xue Qin","doi":"10.1109/iarce57187.2022.00023","DOIUrl":"https://doi.org/10.1109/iarce57187.2022.00023","url":null,"abstract":"Researches show that analyzing student’s facial expressions in class is contribute to improving the accuracy of learning behavior diagnosis which can effectively improve the quality of teaching. In order to improve the accuracy and real-time of facial expression recognition in class, we design a lightweight convolutional neural network(GEGNet) based on VGG16 framework with novel feature fusion and attention mechanism. At first, channel pruning and layer pruning are used to reduce redundant features, and Ghost convolution is adopted to replace the traditional convolution which can reduce the number of parameters. Secondly, efficient channel attention(ECA) is integrated into the feature extraction process which enhance feature extraction capability. Furthermore, a fusion of deep and shallow features is performed before regression module to improve the recognition accuracy of the model. The experiment accuracy of GEGNet on the homemade dataset reached 94.25% which is better than VGG16 model. In addition, the calculation volume of GEGnet is 8.5% as much as VGG16, and the parameters is 9.9% of VGG16. Our model also achieves the same performance in the comparative experiments on CK+ and FER2013, which furtherly proves the effectiveness of our model.","PeriodicalId":329178,"journal":{"name":"2022 International Conference on Industrial Automation, Robotics and Control Engineering (IARCE)","volume":"26 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120999097","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":"Research on target system selection of correlated data based on Bayesian network","authors":"Min Zhang, Xinxin Xu, Qi Ji","doi":"10.1109/IARCE57187.2022.00027","DOIUrl":"https://doi.org/10.1109/IARCE57187.2022.00027","url":null,"abstract":"Many related data are involved in the production process of the cigarette industry. These related data exist in multiple production systems, and there is also a requirement to select relevant systems to extract data. It is our goal to select high reliability systems to extract related data. This paper constructs a selection prediction model, selects the key influencing factors of the target system, carries out Bayesian network reasoning, calculates the selection probability of the given associated data from the Bayesian network algorithm, and constructs the model according to the actual joint probability to realize the algorithm, a new discrimination method is realized for the deployment and retrieval of the production decision-making system of tobacco automation system. Compared with the selection of real data, it is concluded that the Bayesian network based acquisition of related data target system is highly effective, and further points out that higher dimensions can be used for deeper research and application.","PeriodicalId":329178,"journal":{"name":"2022 International Conference on Industrial Automation, Robotics and Control Engineering (IARCE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127303545","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}
G. Wen, Yifan Yang, Zeyuan Yang, Jin Yue, Sijie Yan
{"title":"A High-accuracy Camera Calibration Method Based on Special Circular Target","authors":"G. Wen, Yifan Yang, Zeyuan Yang, Jin Yue, Sijie Yan","doi":"10.1109/IARCE57187.2022.00015","DOIUrl":"https://doi.org/10.1109/IARCE57187.2022.00015","url":null,"abstract":"Targets with circular markers are commonly used in camera calibration and vision measurement. This paper proposes a special circular target with complete and incomplete concentric circles and accordingly introduces a high-accuracy camera calibration method. This method first calculates the initial camera parameters by utilizing the improved ellipse fitting method to determine the centers of the complete concentric circles. But the fitted centers do not coincide with the real projected centers due to the perspective transformation and lens distortion. The coordinates of the real projected centers can be obtained by detecting the corners of the incomplete concentric circles and using the properties of projective geometry. Then, based on the determination of the real projected centers, the iterative compensation algorithm is proposed to eliminate the influence of the eccentricity errors and refine the camera parameters. Corresponding experiments were conducted to show the high accuracy and robustness of the proposed camera calibration method.","PeriodicalId":329178,"journal":{"name":"2022 International Conference on Industrial Automation, Robotics and Control Engineering (IARCE)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127788915","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}