Pub Date : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011838
Yuzhen Pan, Jiawei Wei, Huiliang Shang
In this paper, we propose a novel parallel hopping robot based on hopping animals' parallel mechanism, and analyze its kinematics model using different original mathematical methods. We adopt a bionic jumping structure with a multi-bar linkage system, enabling the robot to possess a substantial jumping ability and higher environmental adaptability compared to wheeled robots. Since this hopping robot consists of a three degrees of freedom (3 DOF) parallel linkage system, its potential energy could be magnified to a certain extent. Accordingly, we calculate the DH table in terms of the robot's sketch model, while forward kinematic problem (FKP) and inverse kinematic problem (IKP) are computed with the help of the MATLAB tool. In order to avoid its singularities, we calculate the rotation matrix and the Jacobian matrix. Afterwards, we present the CAD model and simulate the hopping robot's stiffness using finite element analysis (FEA). Finally, a novel algorithm using a ternary array is introduced on MATLAB to analyze the workspace and dynamics model of the hopping robot. As a result, this paper provides several novel analysis methods for analyzing multi-linkage and multi-degree-of-freedom robot systems through mathematical analysis, kinematic analysis and discrete numerical methods, which indicate that this novel 3-DOF parallel hopping robot possesses better adaptability for different terrain with certain hopping abilities. These analysis methods applied to the parallel hopping robot play an indispensable role in the mechanism analysis, kinematic analysis, and workspace analysis of linkage-typed robots such as legged robots.
{"title":"Mechanism Design of a Multi-linkage Parallel Hopping Robot with Kinematics Analysis","authors":"Yuzhen Pan, Jiawei Wei, Huiliang Shang","doi":"10.1109/ROBIO55434.2022.10011838","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011838","url":null,"abstract":"In this paper, we propose a novel parallel hopping robot based on hopping animals' parallel mechanism, and analyze its kinematics model using different original mathematical methods. We adopt a bionic jumping structure with a multi-bar linkage system, enabling the robot to possess a substantial jumping ability and higher environmental adaptability compared to wheeled robots. Since this hopping robot consists of a three degrees of freedom (3 DOF) parallel linkage system, its potential energy could be magnified to a certain extent. Accordingly, we calculate the DH table in terms of the robot's sketch model, while forward kinematic problem (FKP) and inverse kinematic problem (IKP) are computed with the help of the MATLAB tool. In order to avoid its singularities, we calculate the rotation matrix and the Jacobian matrix. Afterwards, we present the CAD model and simulate the hopping robot's stiffness using finite element analysis (FEA). Finally, a novel algorithm using a ternary array is introduced on MATLAB to analyze the workspace and dynamics model of the hopping robot. As a result, this paper provides several novel analysis methods for analyzing multi-linkage and multi-degree-of-freedom robot systems through mathematical analysis, kinematic analysis and discrete numerical methods, which indicate that this novel 3-DOF parallel hopping robot possesses better adaptability for different terrain with certain hopping abilities. These analysis methods applied to the parallel hopping robot play an indispensable role in the mechanism analysis, kinematic analysis, and workspace analysis of linkage-typed robots such as legged robots.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130084616","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011707
Xingyue Hu, Mengyue Li, N. Jiao, Lianqing Liu
Creatures in nature complete deformation and movement through the anisotropic stretching of muscles. Soft materials for artificial muscles, such as hydrogels, need to be fabricated into anisotropic complex structures. 3D printing is an excellent manufacturing method. However, traditional hydrogels cannot be prepared by inkjet printing because of their physical properties. Here, a novel magnetic thermo-sensitive hydrogel and a non-thermo-sensitive hydrogel that can be 3D printed were synthesized. A bilayer beam as thermal deformation unit was formed by two types of hydrogels. 2D and 3D anisotropic deformable structures can be fabricated by 3D printing. In addition, we navigate the hydrogel structure out of the maze through the magnetic field. Finally, the 3D-printed structures were shown to be magnetically actuated while having more flexible thermo-responsive deformations. Dual-sensitive hydrogels have the printability to produce more flexible, precise, and perfect multi-function robots in the future, and will promote the application in the fields of micromanipulation and medical treatment.
{"title":"Magnetic/thermo dual-sensitive hydrogel-based 3D Printable millirobots","authors":"Xingyue Hu, Mengyue Li, N. Jiao, Lianqing Liu","doi":"10.1109/ROBIO55434.2022.10011707","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011707","url":null,"abstract":"Creatures in nature complete deformation and movement through the anisotropic stretching of muscles. Soft materials for artificial muscles, such as hydrogels, need to be fabricated into anisotropic complex structures. 3D printing is an excellent manufacturing method. However, traditional hydrogels cannot be prepared by inkjet printing because of their physical properties. Here, a novel magnetic thermo-sensitive hydrogel and a non-thermo-sensitive hydrogel that can be 3D printed were synthesized. A bilayer beam as thermal deformation unit was formed by two types of hydrogels. 2D and 3D anisotropic deformable structures can be fabricated by 3D printing. In addition, we navigate the hydrogel structure out of the maze through the magnetic field. Finally, the 3D-printed structures were shown to be magnetically actuated while having more flexible thermo-responsive deformations. Dual-sensitive hydrogels have the printability to produce more flexible, precise, and perfect multi-function robots in the future, and will promote the application in the fields of micromanipulation and medical treatment.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130513560","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011809
Qixin Gao, Qiang Diao, Wenrui Chen, Cuo Yan, Yaonan Wang
The goal of the existing dexterous hands is to achieve multi-function, compact structure, and simple control, which makes it difficult to be installed and disassembled, and the application of fingers is limited. In order to realize the flexibility and convenience of dexterous hand application, this paper proposes the design and experiments of a modular dexterous hand based on human hand biology. Firstly, the movement characteristics of the human hand are combined with its biological tissue structure to analyze its movement laws. The synergy and independence of finger movements were summarized. Secondly, based on the biological proper-ties of the human hand, a design method for a modular dexterous hand is proposed. The flexion and extension (F /E) of the finger adopts the design method of compliance drive and flexible coupling, so that it can achieve great adaptability to the object. Combined with independent adduction and abduction (Ad/ Ab), the dexterity of the fingers is guaranteed. Finally, through the rapid combination of modular fingers, two-fingered hand, three-fingered hand, and humanoid hand were developed, and grasping and manipulation experiments were carried out to verify the feasibility of the design.
{"title":"Design and Experiments of a Modular Dexterous Hand","authors":"Qixin Gao, Qiang Diao, Wenrui Chen, Cuo Yan, Yaonan Wang","doi":"10.1109/ROBIO55434.2022.10011809","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011809","url":null,"abstract":"The goal of the existing dexterous hands is to achieve multi-function, compact structure, and simple control, which makes it difficult to be installed and disassembled, and the application of fingers is limited. In order to realize the flexibility and convenience of dexterous hand application, this paper proposes the design and experiments of a modular dexterous hand based on human hand biology. Firstly, the movement characteristics of the human hand are combined with its biological tissue structure to analyze its movement laws. The synergy and independence of finger movements were summarized. Secondly, based on the biological proper-ties of the human hand, a design method for a modular dexterous hand is proposed. The flexion and extension (F /E) of the finger adopts the design method of compliance drive and flexible coupling, so that it can achieve great adaptability to the object. Combined with independent adduction and abduction (Ad/ Ab), the dexterity of the fingers is guaranteed. Finally, through the rapid combination of modular fingers, two-fingered hand, three-fingered hand, and humanoid hand were developed, and grasping and manipulation experiments were carried out to verify the feasibility of the design.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"421 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130585583","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011970
Hai-ying Li, Meng Li, Xiaozhi Qi, Yuanyuan Yang, Ying Hu
To optimize the operation ability of the autonomous robot under the background of complex surgery, this paper extracted the state features of milling video sequence images to realize bone layer perception and improve the perception ability of the spinal robot. The bone layer sensing algorithm mainly consists of four parts: improved moving object detection algorithm, moving object tracking algorithm, state feature extraction algorithm and bone layer recognition algorithm. Aiming at the shortcomings of the existing moving target detection methods, this paper proposes an improved moving target detection algorithm based on the existing Background Subtractor MOG algorithm, which is suitable for milling video sequences. The grinding machine state obtained by the improved algorithm is used as the input of the moving target tracking algorithm, and the kernel correlation filter (KCF) is used to realize the target tracking. According to the tracking of the moving target, the state features of the milling area are extracted and the bone layer is identified, so as to realize the bone layer perception in the milling process.
{"title":"Bone Layer Perception in Milling Process Based on Video Sequence Images during Robot-assisted Laminectomy*","authors":"Hai-ying Li, Meng Li, Xiaozhi Qi, Yuanyuan Yang, Ying Hu","doi":"10.1109/ROBIO55434.2022.10011970","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011970","url":null,"abstract":"To optimize the operation ability of the autonomous robot under the background of complex surgery, this paper extracted the state features of milling video sequence images to realize bone layer perception and improve the perception ability of the spinal robot. The bone layer sensing algorithm mainly consists of four parts: improved moving object detection algorithm, moving object tracking algorithm, state feature extraction algorithm and bone layer recognition algorithm. Aiming at the shortcomings of the existing moving target detection methods, this paper proposes an improved moving target detection algorithm based on the existing Background Subtractor MOG algorithm, which is suitable for milling video sequences. The grinding machine state obtained by the improved algorithm is used as the input of the moving target tracking algorithm, and the kernel correlation filter (KCF) is used to realize the target tracking. According to the tracking of the moving target, the state features of the milling area are extracted and the bone layer is identified, so as to realize the bone layer perception in the milling process.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130743662","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011802
Kunxu Zhao, Zhengxi Hu, Qianyi Zhang, Jingtai Liu
As an important way of understanding human in-tentions, gaze estimation has always been a research hotspot in the field of human-robot interaction. Most studies now estimate gaze direction by analyzing head features and head detection is required before gaze estimation. For these two sequential tasks, the current research usually adopts two different networks, which increases the memory occupation of the graphics card and is not easy to deploy on the edge device. In this paper, we propose a unified network for simultaneous head detection and gaze estimation, unifying these two tasks into a multi-task learning model. In this network framework, head detection and gaze estimation share the same set of features, which enables them to promote each other to improve detection accuracy. We evaluated our model on gaze360 dataset and the gaze error dropped to 19.62 degrees while running at 23 fps.
{"title":"RTHG: Towards Real- Time Head Detection And Gaze Estimation","authors":"Kunxu Zhao, Zhengxi Hu, Qianyi Zhang, Jingtai Liu","doi":"10.1109/ROBIO55434.2022.10011802","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011802","url":null,"abstract":"As an important way of understanding human in-tentions, gaze estimation has always been a research hotspot in the field of human-robot interaction. Most studies now estimate gaze direction by analyzing head features and head detection is required before gaze estimation. For these two sequential tasks, the current research usually adopts two different networks, which increases the memory occupation of the graphics card and is not easy to deploy on the edge device. In this paper, we propose a unified network for simultaneous head detection and gaze estimation, unifying these two tasks into a multi-task learning model. In this network framework, head detection and gaze estimation share the same set of features, which enables them to promote each other to improve detection accuracy. We evaluated our model on gaze360 dataset and the gaze error dropped to 19.62 degrees while running at 23 fps.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132418325","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011940
Junfeng Wu, N. Jiao, Xingyue Hu, Lianqing Liu
In this paper, a facile method was used to synthesize flower-like silica (SiO2) nanoparticles. Given the advantages of porous structure for molecule decoration and drug carrying, chemical/magnetic dual-responsive nanorobots were fabricated based on these flower-like nanoparticles. Urease served as a chemical engine using urea as fuel, which provided chemical driving force for nanorobots by its biocatalytic degradation ability. Fe304 nanoparticles as a magnetic engine were responsible for the control over advance direction of nanorobots. Furthermore, dual-responsive nanorobots showed a good synergistic motion behavior without negative effect. Compared with traditional imporous nanoparticles, the flower-like structure displayed a great improvement in drug-loading properties owing to the large surface area. Furthermore, dual-responsive nanorobots lead to a higher mortality of cancer cells through an enhanced endocytosis caused by autonomous motion. Thus, the reported nanorobots are promising candidates for targeting drug delivery.
{"title":"Chemical/magnetic dual-responsive nanorobots with flower-like structure for drug delivery","authors":"Junfeng Wu, N. Jiao, Xingyue Hu, Lianqing Liu","doi":"10.1109/ROBIO55434.2022.10011940","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011940","url":null,"abstract":"In this paper, a facile method was used to synthesize flower-like silica (SiO2) nanoparticles. Given the advantages of porous structure for molecule decoration and drug carrying, chemical/magnetic dual-responsive nanorobots were fabricated based on these flower-like nanoparticles. Urease served as a chemical engine using urea as fuel, which provided chemical driving force for nanorobots by its biocatalytic degradation ability. Fe304 nanoparticles as a magnetic engine were responsible for the control over advance direction of nanorobots. Furthermore, dual-responsive nanorobots showed a good synergistic motion behavior without negative effect. Compared with traditional imporous nanoparticles, the flower-like structure displayed a great improvement in drug-loading properties owing to the large surface area. Furthermore, dual-responsive nanorobots lead to a higher mortality of cancer cells through an enhanced endocytosis caused by autonomous motion. Thus, the reported nanorobots are promising candidates for targeting drug delivery.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132901871","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011880
Zhaoran. Meng, Jianhui. Bi, Huafeng Ding
This paper presents a new representation method to illustrate the six-dimensional (6-D) complete workspace of six-degree-of-freedom (6-DOF) parallel manipulators. Taking a typical Steward parallel manipulator as an object. First, the inverse position model of the manipulator is derived. Second, the position workspace and rotation ability of the Steward parallel manipulator are analyzed. Then, a new method to represent the complete workspace of 6-DOF parallel manipulators is presented. At last, based on the new method, a visible six-dimensional workspace of the Steward platform is obtained. This paper provides a novel approach for the complete workspace analysis of 6-DOF parallel manipulators.
{"title":"A new method for the complete workspace representation of six-degree-of-freedom parallel manipulators*","authors":"Zhaoran. Meng, Jianhui. Bi, Huafeng Ding","doi":"10.1109/ROBIO55434.2022.10011880","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011880","url":null,"abstract":"This paper presents a new representation method to illustrate the six-dimensional (6-D) complete workspace of six-degree-of-freedom (6-DOF) parallel manipulators. Taking a typical Steward parallel manipulator as an object. First, the inverse position model of the manipulator is derived. Second, the position workspace and rotation ability of the Steward parallel manipulator are analyzed. Then, a new method to represent the complete workspace of 6-DOF parallel manipulators is presented. At last, based on the new method, a visible six-dimensional workspace of the Steward platform is obtained. This paper provides a novel approach for the complete workspace analysis of 6-DOF parallel manipulators.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132970478","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}
Mimetic octopus can imitate up to fifteen animal shape. By observing the morphological change video of mimetic octopus frame by frame, the law of octopus morphologic is drawn. We propose a Gaussian mixture model (GMM) to study the imitation behavior of octopus trajectory. By establishing and training the teaching sample data, the sample feature points are extracted and the teaching behavior characteristics are obtained. And then, set up the discrete modeling of mimetic octopus robot based on the assumption of piecewise constant curvature by setting a series of D-H parameters in Robotics Toolbox. The mimetic octopus robot is composed of eight flexible arms and a hemispherical cover. Finally, simulation of transformation of the robot is implemented by setting the D-H parameters of the initial state and the target state of the end position. It can not only imitate the shape of a star fish but also imitate that of a sea snake. And, the trajectory of the end position and the speed change of each joint are both smooth during the transform process.
{"title":"Analysis and Simulation of Modeling for Transformable Robot Bio-inspired by Mimetic Octopus","authors":"Liwei Pan, Yan Wu, Qiuxuan Wu, Hongkun Zhou, Qingshan She, Botao Zhang, Jian Wang, Farong Gao","doi":"10.1109/ROBIO55434.2022.10011874","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011874","url":null,"abstract":"Mimetic octopus can imitate up to fifteen animal shape. By observing the morphological change video of mimetic octopus frame by frame, the law of octopus morphologic is drawn. We propose a Gaussian mixture model (GMM) to study the imitation behavior of octopus trajectory. By establishing and training the teaching sample data, the sample feature points are extracted and the teaching behavior characteristics are obtained. And then, set up the discrete modeling of mimetic octopus robot based on the assumption of piecewise constant curvature by setting a series of D-H parameters in Robotics Toolbox. The mimetic octopus robot is composed of eight flexible arms and a hemispherical cover. Finally, simulation of transformation of the robot is implemented by setting the D-H parameters of the initial state and the target state of the end position. It can not only imitate the shape of a star fish but also imitate that of a sea snake. And, the trajectory of the end position and the speed change of each joint are both smooth during the transform process.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133014475","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011998
Colin Pak Yu Chan, Kin Hei Shiu, Chun Ho So, Keng Huat Koh, Musthafa Farhan, Chun Yiu Ho, Tsz Hei Wong, K. Lai
Implementing in-pipe robots for rehabbing underground pipelines can keep frontline workers safe and enhance operational efficiency. A powerful and robust shape transformation in-pipe spraying robot with heavy-duty spraying equipment is developed to perform spray-in-place pipe (SIPP) rehabilitation operations on underground pipelines. The SIPP rehabilitation performance of this spraying robotic system was successfully demonstrated using the remote rotary mixing and spraying of plural component protective coating technique. The novelties of this in-pipe adaptive spraying robot are its ability to carry heavy spraying equipment with a compact and robust design locomotion module and integrated spraying module design installed on its hollow body. It can also pass through the bent elbows and long straight pipes to remotely perform the excellent spraying operation. The adaptive robot's mechanical design, kinematics, and spraying performance are experimentally validated. The proposed spraying approach can perform trenchless underground pipe rehabilitation for multiple pipe diameters over a long distance.
{"title":"Locomotion Design of In-pipe Spraying Robot with Multiple Modules for Trenchless Rehabilitation of Underground Pipe","authors":"Colin Pak Yu Chan, Kin Hei Shiu, Chun Ho So, Keng Huat Koh, Musthafa Farhan, Chun Yiu Ho, Tsz Hei Wong, K. Lai","doi":"10.1109/ROBIO55434.2022.10011998","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011998","url":null,"abstract":"Implementing in-pipe robots for rehabbing underground pipelines can keep frontline workers safe and enhance operational efficiency. A powerful and robust shape transformation in-pipe spraying robot with heavy-duty spraying equipment is developed to perform spray-in-place pipe (SIPP) rehabilitation operations on underground pipelines. The SIPP rehabilitation performance of this spraying robotic system was successfully demonstrated using the remote rotary mixing and spraying of plural component protective coating technique. The novelties of this in-pipe adaptive spraying robot are its ability to carry heavy spraying equipment with a compact and robust design locomotion module and integrated spraying module design installed on its hollow body. It can also pass through the bent elbows and long straight pipes to remotely perform the excellent spraying operation. The adaptive robot's mechanical design, kinematics, and spraying performance are experimentally validated. The proposed spraying approach can perform trenchless underground pipe rehabilitation for multiple pipe diameters over a long distance.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"173 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132081564","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 : 2022-12-05DOI: 10.1109/ROBIO55434.2022.10011807
He Xu, Siqing Chen, Chen Yang, Xin Li
At present, underwater robots are increasingly widely used in the fields of ocean exploration and resource extraction. However, the development of related technologies is not comprehensive enough. Due to the defects of visual algorithm and results, the accuracy and safety of operation under different working conditions cannot be guaranteed. Many researchers pay attention to the development and design of underwater vision technology. In this paper, based on deep learning and binocular vision technology, the underwater tar-get object detection algorithm and the underwater ranging algorithm are established to achieve visual recognition and positioning. Visual decontamination structure are designed to prevent visual occlusion in case of emergency. The accuracy and feasibility of the related techniques are verified by experiments.
{"title":"Contaminants detection and Cleaning of Underwater Robot Vision Based on Deep Learning","authors":"He Xu, Siqing Chen, Chen Yang, Xin Li","doi":"10.1109/ROBIO55434.2022.10011807","DOIUrl":"https://doi.org/10.1109/ROBIO55434.2022.10011807","url":null,"abstract":"At present, underwater robots are increasingly widely used in the fields of ocean exploration and resource extraction. However, the development of related technologies is not comprehensive enough. Due to the defects of visual algorithm and results, the accuracy and safety of operation under different working conditions cannot be guaranteed. Many researchers pay attention to the development and design of underwater vision technology. In this paper, based on deep learning and binocular vision technology, the underwater tar-get object detection algorithm and the underwater ranging algorithm are established to achieve visual recognition and positioning. Visual decontamination structure are designed to prevent visual occlusion in case of emergency. The accuracy and feasibility of the related techniques are verified by experiments.","PeriodicalId":151112,"journal":{"name":"2022 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131652916","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：