Tool condition monitoring technology, as an important part of intelligent manufacturing field, plays a great role in promoting automation and intellectualization in the production and processing process. In this paper, audio and temperature signal parameters are used to monitor tool wear state during cutting. Then the characteristic parameters of audio and temperature signals obtained from experiments under different wear states are fitted and analyzed, and the acoustic signals are analyzed by wavelet transform. The application results show that this monitoring method effectively solves the limitation and stability of single factor monitoring tool status, and is of great significance to improve the processing efficiency and accuracy.
{"title":"Research on Tool Wear State Based on Cutting Audio and Temperature Parameter Fitting","authors":"Ning Ding, Minliang Zhang","doi":"10.1145/3366194.3366214","DOIUrl":"https://doi.org/10.1145/3366194.3366214","url":null,"abstract":"Tool condition monitoring technology, as an important part of intelligent manufacturing field, plays a great role in promoting automation and intellectualization in the production and processing process. In this paper, audio and temperature signal parameters are used to monitor tool wear state during cutting. Then the characteristic parameters of audio and temperature signals obtained from experiments under different wear states are fitted and analyzed, and the acoustic signals are analyzed by wavelet transform. The application results show that this monitoring method effectively solves the limitation and stability of single factor monitoring tool status, and is of great significance to improve the processing efficiency and accuracy.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127502095","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}
Jianhao Tan, S. Tan, Liming Liu, Siyuan Zhang, Yaonan Wang
Visual object tracking has been a concern topic these years, and many trackers have achieved good results in various fields. These research and breakthroughs have made many improvements to solve problems such as drift, lighting, deformation and occlusion. In this paper, we use convolutional network to characterize the feature, and color features. Specifically, it contains region proposal network which including the classification branch and regression branch.
{"title":"Proposal color-histogram aware network","authors":"Jianhao Tan, S. Tan, Liming Liu, Siyuan Zhang, Yaonan Wang","doi":"10.1145/3366194.3366324","DOIUrl":"https://doi.org/10.1145/3366194.3366324","url":null,"abstract":"Visual object tracking has been a concern topic these years, and many trackers have achieved good results in various fields. These research and breakthroughs have made many improvements to solve problems such as drift, lighting, deformation and occlusion. In this paper, we use convolutional network to characterize the feature, and color features. Specifically, it contains region proposal network which including the classification branch and regression branch.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121742782","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}
Most of the existing license plate recognition technologies mostly consider the frontal angle of view of the license plate images, and it is difficult to effectively solve the license plate recognition problem in complex application scenarios such as the distortion of the license plate area. Aiming at this problem, this paper does some studies based on the ALPR system in unconstrained scenarios. The vehicle detection network of the system is changed to YOLOv3 network due to its fast execution and high precision. The loss function in the original system is improved from the single function to the compound loss function. Part of the complex scene pictures which contain license plates from BDD100K dataset are selected as the test set, the initial ALPR system and the improved system's recognition effect on the test set are tested separately. The results showed that the accuracy of the original system in the selected test set for license plate recognition is 92.27%; After YOLOv3 is applied to the vehicle detection network and the loss function is improved, the recognition accuracy is 95.26%, which enhances the detection ability of small target vehicles while improving the recognition accuracy.
{"title":"License Plate Recognition in Unconstrained Scenarios Based on ALPR System","authors":"Zhiquan Jiao, Hongri Fan","doi":"10.1145/3366194.3366290","DOIUrl":"https://doi.org/10.1145/3366194.3366290","url":null,"abstract":"Most of the existing license plate recognition technologies mostly consider the frontal angle of view of the license plate images, and it is difficult to effectively solve the license plate recognition problem in complex application scenarios such as the distortion of the license plate area. Aiming at this problem, this paper does some studies based on the ALPR system in unconstrained scenarios. The vehicle detection network of the system is changed to YOLOv3 network due to its fast execution and high precision. The loss function in the original system is improved from the single function to the compound loss function. Part of the complex scene pictures which contain license plates from BDD100K dataset are selected as the test set, the initial ALPR system and the improved system's recognition effect on the test set are tested separately. The results showed that the accuracy of the original system in the selected test set for license plate recognition is 92.27%; After YOLOv3 is applied to the vehicle detection network and the loss function is improved, the recognition accuracy is 95.26%, which enhances the detection ability of small target vehicles while improving the recognition accuracy.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124859908","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}
The dynamic parameter prediction model (DPPnet) established a mapping between the original space and the compression space by HashedNet for Visual Question Answering (VQA). HashedNet is a single-seeded random hash function, so the collision rate is linear to the compression ratio. In order to relieve the interference of the conflict rate to VQA and improve the stability and accuracy of the model, we introduce a multi-seed random hashing compression named functional hashing to be used as the fusion mechanism in this paper. Multiple pairs of independent random hash function are active and the variable parameters among them are trained by a lightweight reconfigurable neural network, making the compression mechanism more flexible. In addition, we use Bi-GRU to extract the historical and future context information from question sentences. At the same time, we propose gated convolution to selectively learn the feature from images questioned dynamically. Experimental results show that our proposed method achieves higher accuracy compared with existing models.
{"title":"Visual Question Answering with Dynamic Parameter Prediction using Functional Hashing","authors":"Chunye Li, Zhiping Zhou","doi":"10.1145/3366194.3366252","DOIUrl":"https://doi.org/10.1145/3366194.3366252","url":null,"abstract":"The dynamic parameter prediction model (DPPnet) established a mapping between the original space and the compression space by HashedNet for Visual Question Answering (VQA). HashedNet is a single-seeded random hash function, so the collision rate is linear to the compression ratio. In order to relieve the interference of the conflict rate to VQA and improve the stability and accuracy of the model, we introduce a multi-seed random hashing compression named functional hashing to be used as the fusion mechanism in this paper. Multiple pairs of independent random hash function are active and the variable parameters among them are trained by a lightweight reconfigurable neural network, making the compression mechanism more flexible. In addition, we use Bi-GRU to extract the historical and future context information from question sentences. At the same time, we propose gated convolution to selectively learn the feature from images questioned dynamically. Experimental results show that our proposed method achieves higher accuracy compared with existing models.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124919678","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}
At present, most cleaning work of skyscrapers' glass wall is performed by cleaners. It is hard work under horrible environment with low efficiency, moreover it is dangerous. The glass curtain wall cleaning robot studied in this paper is a service robot that can move on the vertical wall and complete the cleaning operation. The robot can automate the cleaning of the high-rise exterior wall, greatly improving the working environment and improving the cleaning efficiency. On the basis of summarizing and drawing on various adsorption models and moving mechanisms, this paper introduces the detail constitution of the cleaning robotic system and analysis on operation principle of each component. The key technology in control system of this robot is expounded and the PLC control system is also presented.
{"title":"Research on Design and Control of Curtain Wall Cleaning Robot","authors":"Pei Zhang, Ming-hui Wu","doi":"10.1145/3366194.3366277","DOIUrl":"https://doi.org/10.1145/3366194.3366277","url":null,"abstract":"At present, most cleaning work of skyscrapers' glass wall is performed by cleaners. It is hard work under horrible environment with low efficiency, moreover it is dangerous. The glass curtain wall cleaning robot studied in this paper is a service robot that can move on the vertical wall and complete the cleaning operation. The robot can automate the cleaning of the high-rise exterior wall, greatly improving the working environment and improving the cleaning efficiency. On the basis of summarizing and drawing on various adsorption models and moving mechanisms, this paper introduces the detail constitution of the cleaning robotic system and analysis on operation principle of each component. The key technology in control system of this robot is expounded and the PLC control system is also presented.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123280370","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}
This paper uses the depth learning model of sharing parameter to extract entities and relationships. The problems of pipeline model error propagation and ignoring the internal relationship between subtasks, a parameter sharing model is proposed, which uses graph convolution neural network based on syntax to capture the structural information of text. The model combined with the parameter sharing mode will be introduced in detail. The motivation of designing the model, the special labeling strategy, the structure of the model, the experimental setup and the analysis of the experimental results will be introduced respectively. From the experimental results, it can be seen that the hybrid model achieves better results in the public data set.
{"title":"Combined Model to Extract Entities and Relations Based on Sharing Parameter","authors":"W. Zhuo, Wang Fan","doi":"10.1145/3366194.3366334","DOIUrl":"https://doi.org/10.1145/3366194.3366334","url":null,"abstract":"This paper uses the depth learning model of sharing parameter to extract entities and relationships. The problems of pipeline model error propagation and ignoring the internal relationship between subtasks, a parameter sharing model is proposed, which uses graph convolution neural network based on syntax to capture the structural information of text. The model combined with the parameter sharing mode will be introduced in detail. The motivation of designing the model, the special labeling strategy, the structure of the model, the experimental setup and the analysis of the experimental results will be introduced respectively. From the experimental results, it can be seen that the hybrid model achieves better results in the public data set.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129767284","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}
This paper studies the path planning and tracking control of obstacle avoidance lane change in intelligent auto driving. Firstly, the vehicle two-degree-of-freedom model of front wheel steering is established by the knowledge of automobile kinematics and dynamics. Secondly, the trajectory planning is realized by the fifth-order polynomial curve fitting method. Then the linear time-varying model predictive control method is used to realize the tracking control of the trajectory. Finally, MATLAB simulation is used to verify the feasibility of the above ideas. The experimental results show that the fifth-order polynomial can quickly and accurately fit the ideal curve; the model predictive control can also stably control the car to follow the prescribed path.
{"title":"Path Planning and Tracking Control for Automatic Driving Obstacle Avoidance","authors":"Bo Yang, Huanhuan Zhang, Zhongshun Jiang","doi":"10.1145/3366194.3366247","DOIUrl":"https://doi.org/10.1145/3366194.3366247","url":null,"abstract":"This paper studies the path planning and tracking control of obstacle avoidance lane change in intelligent auto driving. Firstly, the vehicle two-degree-of-freedom model of front wheel steering is established by the knowledge of automobile kinematics and dynamics. Secondly, the trajectory planning is realized by the fifth-order polynomial curve fitting method. Then the linear time-varying model predictive control method is used to realize the tracking control of the trajectory. Finally, MATLAB simulation is used to verify the feasibility of the above ideas. The experimental results show that the fifth-order polynomial can quickly and accurately fit the ideal curve; the model predictive control can also stably control the car to follow the prescribed path.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125084485","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}
Xiaoliang. Yu, Zhaoqiang Wang, Zhifeng Li, Chongzhi Sun
A common wheeled excavator is used as a prototype and its monoblock boom is transformed into 2-piece boom., which form a new type of four-linkage excavator composed of arm and bucket. Kinematic analysis of the working device of the four-linkage excavator is carried out to grasp the position change of bucket tip and the relationship between the length of hydraulic cylinder and the joint angle. The model of four-linkage excavator is established and its kinematic simulation is carried out based on the robotic toolbox in MATLAB. Finally, actual measurements are made and the four-linkage excavator's parameters are compared with parameters of the prototype. The results show that the working ranges of the four-linkage excavator are much larger than that of the prototype excavator, which provide theoretical supports for the design of the working device of the excavator and the trajectory planning of the excavator.
{"title":"Design and Kinematics Analysis of Four-linkage Excavator","authors":"Xiaoliang. Yu, Zhaoqiang Wang, Zhifeng Li, Chongzhi Sun","doi":"10.1145/3366194.3366302","DOIUrl":"https://doi.org/10.1145/3366194.3366302","url":null,"abstract":"A common wheeled excavator is used as a prototype and its monoblock boom is transformed into 2-piece boom., which form a new type of four-linkage excavator composed of arm and bucket. Kinematic analysis of the working device of the four-linkage excavator is carried out to grasp the position change of bucket tip and the relationship between the length of hydraulic cylinder and the joint angle. The model of four-linkage excavator is established and its kinematic simulation is carried out based on the robotic toolbox in MATLAB. Finally, actual measurements are made and the four-linkage excavator's parameters are compared with parameters of the prototype. The results show that the working ranges of the four-linkage excavator are much larger than that of the prototype excavator, which provide theoretical supports for the design of the working device of the excavator and the trajectory planning of the excavator.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126121661","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}
This paper mainly aims at the on-board display terminal, i.mx6ul board produced by Freescale Company is used as hardware platform, ARM Cortex®-A7 processor and EJ080NA-05B LCD screen is used.The hardware wiring, Framebuffer display interface, LCD controller, driver and application program are introduced. On the basis of Framebuffer, which is the interface of display device in 2.6 kernel embedded Linux, the hardware principle and software framework are analyzed, and the driving design of LCD is carried out.
{"title":"Driving Design of Vehicle LCD Display Based on Freescale I.mx6 Platform","authors":"Weilun Cheng, Yanliang Li","doi":"10.1145/3366194.3366309","DOIUrl":"https://doi.org/10.1145/3366194.3366309","url":null,"abstract":"This paper mainly aims at the on-board display terminal, i.mx6ul board produced by Freescale Company is used as hardware platform, ARM Cortex®-A7 processor and EJ080NA-05B LCD screen is used.The hardware wiring, Framebuffer display interface, LCD controller, driver and application program are introduced. On the basis of Framebuffer, which is the interface of display device in 2.6 kernel embedded Linux, the hardware principle and software framework are analyzed, and the driving design of LCD is carried out.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126120254","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}
With the rapid development of communication technology and computer technology, autonomous driving technology has become a field of great concern. Environmental perception technology is one of the key technologies of autonomous vehicles. Binocular stereo vision technology has become an indispensable research content in environmental awareness technology because of its unique advantages. In this paper, the key technologies such as binocular ranging principle, camera calibration, stereo correction and stereo matching are studied. Based on this, a binocular stereo vision ranging system based on MATLAB and OpenCV is designed. Camera calibration is performed by MATLAB, and the calibration results are imported into OpenCV for stereo correction and stereo matching to solve the distance between the target object and the camera. The experimental results show that the measurement error is less than 2% within a distance of 30 meters.
{"title":"Research on Autopilot Vehicle Ranging System Based on Binocular Vision","authors":"Fanglin Shu, Xiaoci Huang, Wenguan Cao","doi":"10.1145/3366194.3366283","DOIUrl":"https://doi.org/10.1145/3366194.3366283","url":null,"abstract":"With the rapid development of communication technology and computer technology, autonomous driving technology has become a field of great concern. Environmental perception technology is one of the key technologies of autonomous vehicles. Binocular stereo vision technology has become an indispensable research content in environmental awareness technology because of its unique advantages. In this paper, the key technologies such as binocular ranging principle, camera calibration, stereo correction and stereo matching are studied. Based on this, a binocular stereo vision ranging system based on MATLAB and OpenCV is designed. Camera calibration is performed by MATLAB, and the calibration results are imported into OpenCV for stereo correction and stereo matching to solve the distance between the target object and the camera. The experimental results show that the measurement error is less than 2% within a distance of 30 meters.","PeriodicalId":105852,"journal":{"name":"Proceedings of the 2019 International Conference on Robotics, Intelligent Control and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131395148","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}