Localization for estimating the position of a robot in an environment remains a challenging problem in mobile robots. However, previous studies mostly consider accurate map with correct scale before the localization task. This paper presents a novel approach for solving localization problem using the inaccurate hand-drawn map of the environment, when the exact map of the environment is not prepared before the localization task. Our proposed method firstly decomposes the hand-drawn map into the local places such as a room or corridor, then extract a set of geometric information of each segmented area to train them using convolutional neural networks (CNN) for place recognition. This technique only selects nominated segmented areas of where the possible location of the robot is. Secondly, Monte Carlo Localization (MCL) technique is used to estimate the position of the robot. Empirical studies on the standard localization technique illustrate that the proposed approach achieves superior performance to state-of-the-art localization methods regarding noisy data issues and large localization error.
{"title":"Indoor Robot Localization in Hand-Drawn Maps by using Convolutional Neural Networks and Monte Carlo Method","authors":"F. Foroughi, Ji-kai Wang, Zonghai Chen","doi":"10.1145/3351917.3351927","DOIUrl":"https://doi.org/10.1145/3351917.3351927","url":null,"abstract":"Localization for estimating the position of a robot in an environment remains a challenging problem in mobile robots. However, previous studies mostly consider accurate map with correct scale before the localization task. This paper presents a novel approach for solving localization problem using the inaccurate hand-drawn map of the environment, when the exact map of the environment is not prepared before the localization task. Our proposed method firstly decomposes the hand-drawn map into the local places such as a room or corridor, then extract a set of geometric information of each segmented area to train them using convolutional neural networks (CNN) for place recognition. This technique only selects nominated segmented areas of where the possible location of the robot is. Secondly, Monte Carlo Localization (MCL) technique is used to estimate the position of the robot. Empirical studies on the standard localization technique illustrate that the proposed approach achieves superior performance to state-of-the-art localization methods regarding noisy data issues and large localization error.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115470298","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}
3D LIDAR based environmental perception has been widely used in the field of robotics research especially for the rapid development of the vehicle's auto pilot. Coordinate transformation calibration between LIDAR and the self-driving vehicle's body is a prerequisite for environmental perception. Different from the usual LIDAR extrinsic calibration equipped with IMU, the transform matrix is calculated by using the vertical relationship between the flat ground plane and another flat plane perpendicular to the ground without depending on third-party sensors such as IMU or satellite positioning devices in the proposed method. The calibration process is divided into two steps. The first step is to determine the transform matrix from the LIDAR's frame to the self-defined ground plane's frame. The second step is to determine the transform matrix from the ground plane's frame to the vehicle's frame. The proposed calibration method is fast and valid and has been validated on a variety of LIDAR equipment including Pandar40, VLP-16, HDL-32E and so on. The calibration result is used for 3D-LIDAR based environmental perception and map reconstruction in the process of auto pilot. The experimental results show that the proposed calibration method is reliable and convenient.
{"title":"Fast Extrinsic Calibration for 3D LIDAR","authors":"Ning Li, T. Luo, Bo Su","doi":"10.1145/3351917.3351986","DOIUrl":"https://doi.org/10.1145/3351917.3351986","url":null,"abstract":"3D LIDAR based environmental perception has been widely used in the field of robotics research especially for the rapid development of the vehicle's auto pilot. Coordinate transformation calibration between LIDAR and the self-driving vehicle's body is a prerequisite for environmental perception. Different from the usual LIDAR extrinsic calibration equipped with IMU, the transform matrix is calculated by using the vertical relationship between the flat ground plane and another flat plane perpendicular to the ground without depending on third-party sensors such as IMU or satellite positioning devices in the proposed method. The calibration process is divided into two steps. The first step is to determine the transform matrix from the LIDAR's frame to the self-defined ground plane's frame. The second step is to determine the transform matrix from the ground plane's frame to the vehicle's frame. The proposed calibration method is fast and valid and has been validated on a variety of LIDAR equipment including Pandar40, VLP-16, HDL-32E and so on. The calibration result is used for 3D-LIDAR based environmental perception and map reconstruction in the process of auto pilot. The experimental results show that the proposed calibration method is reliable and convenient.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123526516","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}
Human-computer interaction has been a hot topic in the development of robots. Gesture recognition is a significant part of it. Existing snake-like robot is controlled by the handle and joystick. It is worth studying that use gesture to control robots. Existing main vision-based gesture recognition methods are based on a two-stage method: hand detection and segmentation, feature extraction and template matching process. Inspired by the YOLO[1] algorithm, this paper proposed a one-stage gesture recognition and snake-like robot control method, based on deep learning, combined image segmentation and classification, realized end-to-end recognition and robot control. The snake-like robot can react to four types of human's gestures with a rapid processing time.
{"title":"Human-Computer Interaction Control of Snake-Like Robot Based on Gesture Recognition","authors":"Yidong Chen, Wu Wei, Wenyu Xiao","doi":"10.1145/3351917.3351984","DOIUrl":"https://doi.org/10.1145/3351917.3351984","url":null,"abstract":"Human-computer interaction has been a hot topic in the development of robots. Gesture recognition is a significant part of it. Existing snake-like robot is controlled by the handle and joystick. It is worth studying that use gesture to control robots. Existing main vision-based gesture recognition methods are based on a two-stage method: hand detection and segmentation, feature extraction and template matching process. Inspired by the YOLO[1] algorithm, this paper proposed a one-stage gesture recognition and snake-like robot control method, based on deep learning, combined image segmentation and classification, realized end-to-end recognition and robot control. The snake-like robot can react to four types of human's gestures with a rapid processing time.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128996800","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}
Intelligent robots have played an important role in missions such as reconnaissance and resource utilization in unmanned lunar exploration in recent years. A new quadruped lunar robot was designed to solve problems of weak adaptability and poor obstacle surmounting ability of wheeled mobile robot in complex terrain environment. The mechanical leg structure of quadruped robot with 3 active degrees of freedom was designed based on the analysis of the physiological structure of canine legs. The kinematic analysis of the mechanical leg was carried out and the mechanical structure design was completed. The serial mechanism is applied to the leg structure of quadruped robot, which can satisfy the load and make the control of the mechanical leg easier and more efficient. The results of motion simulation show that the quadruped robot can smoothly cross a 250 mm high obstacle and has the moving speed of 500 m/h. The advantages of quadruped robot in rugged roads, its flexibility and adaptability also provide a good foundation for its later use as a mobile platform equipped with scientific instruments.
{"title":"Design and Analysis of Serial Mechanical Leg of Quadruped Lunar Robot","authors":"Yuming Wu, Shaokun Wang, Ke Wang","doi":"10.1145/3351917.3351947","DOIUrl":"https://doi.org/10.1145/3351917.3351947","url":null,"abstract":"Intelligent robots have played an important role in missions such as reconnaissance and resource utilization in unmanned lunar exploration in recent years. A new quadruped lunar robot was designed to solve problems of weak adaptability and poor obstacle surmounting ability of wheeled mobile robot in complex terrain environment. The mechanical leg structure of quadruped robot with 3 active degrees of freedom was designed based on the analysis of the physiological structure of canine legs. The kinematic analysis of the mechanical leg was carried out and the mechanical structure design was completed. The serial mechanism is applied to the leg structure of quadruped robot, which can satisfy the load and make the control of the mechanical leg easier and more efficient. The results of motion simulation show that the quadruped robot can smoothly cross a 250 mm high obstacle and has the moving speed of 500 m/h. The advantages of quadruped robot in rugged roads, its flexibility and adaptability also provide a good foundation for its later use as a mobile platform equipped with scientific instruments.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121197126","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 first sets up a dynamic model for the contacting process according to the design scheme of a paper-sticking machine, through the analysis of contact force, obtaining equations to describe the problem; then solves the equations and simulates numerically the contacting process with the help of Matlab, to get the ideal design parameters. The work of this paper is tested helpful in improving the design of the machine.
{"title":"Dynamic Model with Analysis for Plate Contacting Problem in Automatic Paper-Sticking Machine","authors":"Yanjie Miao, He Ye, Xing-bo Wang","doi":"10.1145/3351917.3351929","DOIUrl":"https://doi.org/10.1145/3351917.3351929","url":null,"abstract":"This paper first sets up a dynamic model for the contacting process according to the design scheme of a paper-sticking machine, through the analysis of contact force, obtaining equations to describe the problem; then solves the equations and simulates numerically the contacting process with the help of Matlab, to get the ideal design parameters. The work of this paper is tested helpful in improving the design of the machine.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126464785","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}
Aiming at the problem of extracting the fault features of the rotating machinery under the situation of the mixed faults and low signal-to-noise ratio (SNR), a method of fault feature extraction based onindependent component analysis with reference (ICA-R) and stochastic resonance (SR) algorithm is proposed. Firstly, the improved fault signal pre-processing is carried out by using the improved ICA-R, and the expected fault signal is extracted. Then, combining the time-domain analysis method with the artificial bee colony algorithm, the scale adaptive SR algorithm is employed to further extract fault features. The experimental results show that the proposed method is effective in diagnosing the mixed faults of rotating machinery.
{"title":"Feature Extraction of Mixed faults of Rotating Machinery Based on ICA -R and Stochastic Resonance","authors":"Gang Yu, Mang Gao, Lulu Zhao, Ying-ying Zhu","doi":"10.1145/3351917.3351957","DOIUrl":"https://doi.org/10.1145/3351917.3351957","url":null,"abstract":"Aiming at the problem of extracting the fault features of the rotating machinery under the situation of the mixed faults and low signal-to-noise ratio (SNR), a method of fault feature extraction based onindependent component analysis with reference (ICA-R) and stochastic resonance (SR) algorithm is proposed. Firstly, the improved fault signal pre-processing is carried out by using the improved ICA-R, and the expected fault signal is extracted. Then, combining the time-domain analysis method with the artificial bee colony algorithm, the scale adaptive SR algorithm is employed to further extract fault features. The experimental results show that the proposed method is effective in diagnosing the mixed faults of rotating machinery.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126416936","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}
In this paper, an indirect adaptive controller with general type-2 fuzzy neural networks (GT2FNN) approximator is proposed for a general class of SISO nonlinear systems. General type-2 fuzzy system (GT2FS) can be considered as a collection of numerous interval type-2 fuzzy systems (IT2FS) by α-plane. By using the recently introduced adaptive modulation factor into GT2FNN, the computational complexity and time-consuming are greatly reduced in the type reduction of IT2FS. The KM algorithm can be avoided in the type reduction of GT2FNN. Compared to the conventional GT2FNN, the proposed GT2FNN has obvious advantages in computational complexity and time consumption. The Lyaponov approach proves the stability of the closed-loop system. The simulation results show that the tracking performance of GT2FNN approximator is better than IT2FNN and T1FNN approximator.
{"title":"Adaptive control for a class of nonlinear system using general type-2 fuzzy neural networks approximator","authors":"Yi Hu, Haipeng Wang, T. Zhao, S. Dian","doi":"10.1145/3351917.3351944","DOIUrl":"https://doi.org/10.1145/3351917.3351944","url":null,"abstract":"In this paper, an indirect adaptive controller with general type-2 fuzzy neural networks (GT2FNN) approximator is proposed for a general class of SISO nonlinear systems. General type-2 fuzzy system (GT2FS) can be considered as a collection of numerous interval type-2 fuzzy systems (IT2FS) by α-plane. By using the recently introduced adaptive modulation factor into GT2FNN, the computational complexity and time-consuming are greatly reduced in the type reduction of IT2FS. The KM algorithm can be avoided in the type reduction of GT2FNN. Compared to the conventional GT2FNN, the proposed GT2FNN has obvious advantages in computational complexity and time consumption. The Lyaponov approach proves the stability of the closed-loop system. The simulation results show that the tracking performance of GT2FNN approximator is better than IT2FNN and T1FNN approximator.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"308 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134497513","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}
Serial and parallel configurations are mutually exclusive in performance and structure,this hinders the combination of performance advantages. To solve this problem, a novel hybrid configuration which can realize serial and parallel switching based on a motion bifurcation mechanism is proposed. First, the structure of the new configuration is introduced. Second, the mobility of the reconfigurable arm were analyzed,the mobility characteristic analysis is carried out for the overall manipulator.Then, the specific process of arm mode switching is revealed in order to realize the mode switching control of the arm in the later stage. The mechanism can be applied to both machining and manufacturing robots with a variety of station properties, as well as to the limb structure of multi-habitat bionic robots. In this study, the performance advantages of series and parallel configurations are put into full play, it promotes the practical application of reconfigurable mechanism.
{"title":"Design and Application of a Dual Operation Mode Hybrid Mechanism","authors":"Xing-Lu Yin, Chunyan Zhang, Mingjuan Xie","doi":"10.1145/3351917.3351954","DOIUrl":"https://doi.org/10.1145/3351917.3351954","url":null,"abstract":"Serial and parallel configurations are mutually exclusive in performance and structure,this hinders the combination of performance advantages. To solve this problem, a novel hybrid configuration which can realize serial and parallel switching based on a motion bifurcation mechanism is proposed. First, the structure of the new configuration is introduced. Second, the mobility of the reconfigurable arm were analyzed,the mobility characteristic analysis is carried out for the overall manipulator.Then, the specific process of arm mode switching is revealed in order to realize the mode switching control of the arm in the later stage. The mechanism can be applied to both machining and manufacturing robots with a variety of station properties, as well as to the limb structure of multi-habitat bionic robots. In this study, the performance advantages of series and parallel configurations are put into full play, it promotes the practical application of reconfigurable mechanism.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132310879","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 integrated missile guidance control system is a complex nonlinear system control problem, which needs to consider the effects of uncertainties, unmatching disturbance, and input constraints. Most of the current control methods have not been fully considered. In this paper, the controller is designed for the integrated model of missile guidance control, combined with backstepping control and sliding mode control. By using extended disturbance observer to accurately observe the complex disturbance term in the sliding mode system, the influence of the disturbance is solved and the inherent differential explosion in backstepping control is avoided. Considering the input limitation problem, the sliding mode surfaces are optimized to reduce the amplitude and chattering of the controller without changing the form of the control law. Finally, the stability of the system is analyzed and the effectiveness and superiority of my method are verified by comparison experiments.
{"title":"Multi: sliding Mode Backstepping Method for Integrated Missile Guidance and Control System","authors":"Ende Wang, Jinlei Jiao, Xukui Hou","doi":"10.1145/3351917.3351922","DOIUrl":"https://doi.org/10.1145/3351917.3351922","url":null,"abstract":"The integrated missile guidance control system is a complex nonlinear system control problem, which needs to consider the effects of uncertainties, unmatching disturbance, and input constraints. Most of the current control methods have not been fully considered. In this paper, the controller is designed for the integrated model of missile guidance control, combined with backstepping control and sliding mode control. By using extended disturbance observer to accurately observe the complex disturbance term in the sliding mode system, the influence of the disturbance is solved and the inherent differential explosion in backstepping control is avoided. Considering the input limitation problem, the sliding mode surfaces are optimized to reduce the amplitude and chattering of the controller without changing the form of the control law. Finally, the stability of the system is analyzed and the effectiveness and superiority of my method are verified by comparison experiments.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121434135","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}
Due to the narrow installation space of the ammunition supply truck, the cantilever structure is required to be light-weighted with the length of cantilever being limited. In this paper, the finite element model of the cantilever structure crane is established, through which the stress and displacement of cantilever structure in unloaded state and loaded state can be solved in order to analyze the possible failure location of cantilever structure Combined with the actual use of the cantilever structure crane, the scheme of size optimization based on Optistruct is proposed. The analyzed results of the optimized structural scheme indicate that the structure is 12.43% lighter than before meeting the stress requirements so that the cantilever structure crane is feasible.
{"title":"Size Optimization Design for Cantilever Structure of an Ammunition Supply Truck Based on Optistruct","authors":"Jian-Long Sheng, Yadong Xu, Jun Han, Z. Jia","doi":"10.1145/3351917.3351976","DOIUrl":"https://doi.org/10.1145/3351917.3351976","url":null,"abstract":"Due to the narrow installation space of the ammunition supply truck, the cantilever structure is required to be light-weighted with the length of cantilever being limited. In this paper, the finite element model of the cantilever structure crane is established, through which the stress and displacement of cantilever structure in unloaded state and loaded state can be solved in order to analyze the possible failure location of cantilever structure Combined with the actual use of the cantilever structure crane, the scheme of size optimization based on Optistruct is proposed. The analyzed results of the optimized structural scheme indicate that the structure is 12.43% lighter than before meeting the stress requirements so that the cantilever structure crane is feasible.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116226762","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：