Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164590
Bingchao Zhao, Cong Peng
Optical flow estimation is one of the classic tasks in the field of vision. It calculates the motion of the target based on two continuous images. In most of the past work, the estimated optical flow often has errors in scenes of large motion or noise interference because the convolutional neural network structure often focuses on local features. To overcome the problems mentioned above, we propose a feature enhancement module that is based on the self-attention mechanism to enhance the dependencies of long-range features. Additionally, It can filter part of the noise, such as the interference of illumination in the input image. We evaluate our approach on standard benchmarks to verify motion estimation ability. To compare different results intuitively, we visualize flow fields for qualitative analysis. Eventually, we use the heat map to visualize the output of the attention layer to explore the mechanism of the attention algorithm.
{"title":"The Optical Flow Estimation Method Based on the Attention Feature Enhancement Module","authors":"Bingchao Zhao, Cong Peng","doi":"10.1109/ISAS59543.2023.10164590","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164590","url":null,"abstract":"Optical flow estimation is one of the classic tasks in the field of vision. It calculates the motion of the target based on two continuous images. In most of the past work, the estimated optical flow often has errors in scenes of large motion or noise interference because the convolutional neural network structure often focuses on local features. To overcome the problems mentioned above, we propose a feature enhancement module that is based on the self-attention mechanism to enhance the dependencies of long-range features. Additionally, It can filter part of the noise, such as the interference of illumination in the input image. We evaluate our approach on standard benchmarks to verify motion estimation ability. To compare different results intuitively, we visualize flow fields for qualitative analysis. Eventually, we use the heat map to visualize the output of the attention layer to explore the mechanism of the attention algorithm.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124958550","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 : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164446
Donglin Chen, Dehong Cong, Xiangman Song
In order to improve the locomotion capability of quadruped robot in the sloping terrain and enhance whose adaptability to the environment, this paper proposes a method to realize dynamic locomotion of quadruped robot in sloping terrain completely based on model predictive control (MPC) and proprioception. According to the foot contact signal and the robot body posture information measured by inertial measurement unit (IMU), quadruped robot actively changes whose body posture to adapt to different sloping terrains. This paper builds quadruped robot virtual prototype and test terrain in Webots simulation environment. The experimental results show that with this method, the roll angle fluctuation range of the quadruped robot is less than 0.05rad and the yaw angle fluctuation range is not more than 0.003rad. At the same time, when the angle of slope changes, the terrain adaptation time of the quadruped robot is less than 1.8s. The above results show that quadruped robot has excellent movement ability in sloping terrain and environmental adaptability under the condition of ensuring stability with the method proposed in this paper.
{"title":"Dynamic Locomotion of Quadruped Robot in Sloping Terrain","authors":"Donglin Chen, Dehong Cong, Xiangman Song","doi":"10.1109/ISAS59543.2023.10164446","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164446","url":null,"abstract":"In order to improve the locomotion capability of quadruped robot in the sloping terrain and enhance whose adaptability to the environment, this paper proposes a method to realize dynamic locomotion of quadruped robot in sloping terrain completely based on model predictive control (MPC) and proprioception. According to the foot contact signal and the robot body posture information measured by inertial measurement unit (IMU), quadruped robot actively changes whose body posture to adapt to different sloping terrains. This paper builds quadruped robot virtual prototype and test terrain in Webots simulation environment. The experimental results show that with this method, the roll angle fluctuation range of the quadruped robot is less than 0.05rad and the yaw angle fluctuation range is not more than 0.003rad. At the same time, when the angle of slope changes, the terrain adaptation time of the quadruped robot is less than 1.8s. The above results show that quadruped robot has excellent movement ability in sloping terrain and environmental adaptability under the condition of ensuring stability with the method proposed in this paper.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128926175","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 : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164488
Min Wang, Yongchun Xie, Yan Su
The configuration of spacecraft thrusters directly affects the realization of precise automatic control and propellant consumption. At present, the design of thruster configuration lacks of theoretical guidance. Spacecraft carrying out complex space missions such as rendezvous and docking are often equipped with too many thrusters. This paper proposed a theoretical design method of thruster configuration for six-dimensional position and attitude control missions. Firstly, the mathematical description of thruster configuration is introduced. Then, a general design method of thruster configuration for six-dimensional control task is proposed. Finally, simulation of relative position and attitude control of rendezvous and docking task is taken as an example to verify the correctness and validity of the above method.
{"title":"A Thruster Configuration Method for Spacecraft Six-Dimensional Control","authors":"Min Wang, Yongchun Xie, Yan Su","doi":"10.1109/ISAS59543.2023.10164488","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164488","url":null,"abstract":"The configuration of spacecraft thrusters directly affects the realization of precise automatic control and propellant consumption. At present, the design of thruster configuration lacks of theoretical guidance. Spacecraft carrying out complex space missions such as rendezvous and docking are often equipped with too many thrusters. This paper proposed a theoretical design method of thruster configuration for six-dimensional position and attitude control missions. Firstly, the mathematical description of thruster configuration is introduced. Then, a general design method of thruster configuration for six-dimensional control task is proposed. Finally, simulation of relative position and attitude control of rendezvous and docking task is taken as an example to verify the correctness and validity of the above method.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"141 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129113514","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 : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164572
Yijiang Wu, Jia You, Zhicong Dong, Huibin Zhou, Mengxin Shi
There are some problems with the double-joint flexible robotic manipulator itself, and the classic PID control method has the defect of slow convergence rate. Therefore, in order to deal with the defect of slow convergence rate of classical PID control methods in the control problem of dual-joint flexible manipulators, a robust finite-time control method is proposed. A two-stage finite-time sliding mode surface with fast convergence characteristics is designed, which the manipulator moves at a uniform speed when the system state is far from the equilibrium point, and the fractional-order feedback is designed to achieve finite-time control when the system state is approaching the equilibrium point, thereby maintaining a fast convergence rate of the system during the full control process. Aiming at the disturbance problems such as flexible vibration, external disturbance, and model uncertainty in the control process, an improved sign function term is designed to suppress them and avoid high-frequency oscillations near the equilibrium point, and a robust controller is further designed to achieve the convergence of the system state under disturbance conditions. The proposed method is verified by Lyapunov stability theory, numerical simulation and physical simulation, and the experimental results show that the proposed robust finite-time control method improves the convergence rate by more than 50% compared with the classical PID method, and achieves fast, stable and precise control objectives.
{"title":"A Robust Finite-Time Control Method for Two-Joint Flexible Manipulator","authors":"Yijiang Wu, Jia You, Zhicong Dong, Huibin Zhou, Mengxin Shi","doi":"10.1109/ISAS59543.2023.10164572","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164572","url":null,"abstract":"There are some problems with the double-joint flexible robotic manipulator itself, and the classic PID control method has the defect of slow convergence rate. Therefore, in order to deal with the defect of slow convergence rate of classical PID control methods in the control problem of dual-joint flexible manipulators, a robust finite-time control method is proposed. A two-stage finite-time sliding mode surface with fast convergence characteristics is designed, which the manipulator moves at a uniform speed when the system state is far from the equilibrium point, and the fractional-order feedback is designed to achieve finite-time control when the system state is approaching the equilibrium point, thereby maintaining a fast convergence rate of the system during the full control process. Aiming at the disturbance problems such as flexible vibration, external disturbance, and model uncertainty in the control process, an improved sign function term is designed to suppress them and avoid high-frequency oscillations near the equilibrium point, and a robust controller is further designed to achieve the convergence of the system state under disturbance conditions. The proposed method is verified by Lyapunov stability theory, numerical simulation and physical simulation, and the experimental results show that the proposed robust finite-time control method improves the convergence rate by more than 50% compared with the classical PID method, and achieves fast, stable and precise control objectives.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"129 35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132850432","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 proposes a fractional order distributed optimization algorithm for balanced directed graphs by introducing nabla fractional calculus. The proposed algorithm is shown to converge at the rate of Mittag-Leffler to the exact solution of the distributed optimization problem on balanced connected digraph topological network structure with strong convex and smooth objective function. A numerical example is provided to verify the effectiveness of the algorithm and demonstrate the potential of fractional calculus in addressing distributed optimization problems.
{"title":"Nabla fractional distributed optimization algorithm with directed communication topology","authors":"Xiaolin Hong, Yikun Zeng, Shuaiyu Zhou, Yiheng Wei","doi":"10.1109/ISAS59543.2023.10164582","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164582","url":null,"abstract":"This paper proposes a fractional order distributed optimization algorithm for balanced directed graphs by introducing nabla fractional calculus. The proposed algorithm is shown to converge at the rate of Mittag-Leffler to the exact solution of the distributed optimization problem on balanced connected digraph topological network structure with strong convex and smooth objective function. A numerical example is provided to verify the effectiveness of the algorithm and demonstrate the potential of fractional calculus in addressing distributed optimization problems.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130470675","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 : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164323
Yanan Cao, Dongbin Zhao, Xiang Cao
Intelligent agent navigation has broad application scenarios, one of the hot research directions in this field is agent dynamic path planning. For the target network in deep reinforcement learning to gradually deviate from online reinforcement learning, a new softmax operator is applied to replace the max operator in the original network after deleting the target network. New prioritized experience replay is applied to enhance the experience utilization of the agent and dueling network is employed to improve the perceptions of the environment in the path planning process. A modified dynamic ϵ-greedy algorithm is then developed to select actions. The experimental results in the simulation environment show that even after deleting the target network, the algorithm in this paper can still converge to a higher value within limited episodes, which proves its effectiveness.
{"title":"A New Deep Reinforcement Learning Based Robot Path Planning Algorithm without Target Network","authors":"Yanan Cao, Dongbin Zhao, Xiang Cao","doi":"10.1109/ISAS59543.2023.10164323","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164323","url":null,"abstract":"Intelligent agent navigation has broad application scenarios, one of the hot research directions in this field is agent dynamic path planning. For the target network in deep reinforcement learning to gradually deviate from online reinforcement learning, a new softmax operator is applied to replace the max operator in the original network after deleting the target network. New prioritized experience replay is applied to enhance the experience utilization of the agent and dueling network is employed to improve the perceptions of the environment in the path planning process. A modified dynamic ϵ-greedy algorithm is then developed to select actions. The experimental results in the simulation environment show that even after deleting the target network, the algorithm in this paper can still converge to a higher value within limited episodes, which proves its effectiveness.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127894106","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 : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164548
Shaohua Yang, Xia Li, Z. Liu, Yanjun Zhang
This paper considers a regulation problem for a longitudinal dynamical model of hypersonic vehicles with strong nonlinearies. The problem is reduced to a stabilization problem by shifting the desired equilibrium position to the origin. By means of a control input domination idea and suitable coordinate transformations, the longitudinal dynamics of hypersonic vehicles with engine throttle setting dynamics are divided into a flight-path angle controlled subsystem and a velocity controlled subsystem. A new nonlinear state-feedback control scheme is proposed using a parameter separation technique for dealing with strong nonlinearies and a backstepping approach for designing virtual and actual controllers. The proposed controller ensures the closed-loop signals global boundedness and achieves exponential regulation throughout the vehicle’s operational envelope. Simulation results show the desired control system performance for the hypersonic vehicle models with strong nonlinearies.
{"title":"Globally Exponential Regulation of Hypersonic Vehicle with Strong Nonlinearies","authors":"Shaohua Yang, Xia Li, Z. Liu, Yanjun Zhang","doi":"10.1109/ISAS59543.2023.10164548","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164548","url":null,"abstract":"This paper considers a regulation problem for a longitudinal dynamical model of hypersonic vehicles with strong nonlinearies. The problem is reduced to a stabilization problem by shifting the desired equilibrium position to the origin. By means of a control input domination idea and suitable coordinate transformations, the longitudinal dynamics of hypersonic vehicles with engine throttle setting dynamics are divided into a flight-path angle controlled subsystem and a velocity controlled subsystem. A new nonlinear state-feedback control scheme is proposed using a parameter separation technique for dealing with strong nonlinearies and a backstepping approach for designing virtual and actual controllers. The proposed controller ensures the closed-loop signals global boundedness and achieves exponential regulation throughout the vehicle’s operational envelope. Simulation results show the desired control system performance for the hypersonic vehicle models with strong nonlinearies.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129223586","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 : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164342
Hejia Gao, Zele Yu, Juqi Hu
In recent years, flexible systems that effectively combine the properties of flexibility and adaptability of flexible materials have become increasingly popular in various fields such as aerospace, robotics, industrial production, and civil engineering. Due to their lightweight, low energy consumption, high flexibility, and good initial conditions, these systems are now employed in a wide range of applications, such as flexible multi-linked manipulator systems, flexible bionic fluttering aircraft, intelligent flexible building systems, and flexible intelligent structural systems. However, there are still unresolved issues related to the dynamics modeling and control methods in the field of flexible systems. These include the trajectory tracking of flexible manipulators, the dynamics modeling and intelligent control of flexible flapping aircraft, and the vibration control of high-rise building structures in complex environments. This article aims to summarize and analyze the modeling methods and intelligent control strategies of flexible systems. Firstly, we categorize flexible system modeling methods into two types: those based on ordinary differential equations and partial differential equations. Secondly, we classify intelligent control strategies into two categories: classical control methods and intelligent control methods. We then discuss the strengths, weaknesses, and application scenarios of these different methods. Finally, we raise several questions regarding the current research status of modeling and intelligent control of flexible systems, and provide potential future research directions.
{"title":"A Survey on Modeling and Control Methods For Flexible Systems","authors":"Hejia Gao, Zele Yu, Juqi Hu","doi":"10.1109/ISAS59543.2023.10164342","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164342","url":null,"abstract":"In recent years, flexible systems that effectively combine the properties of flexibility and adaptability of flexible materials have become increasingly popular in various fields such as aerospace, robotics, industrial production, and civil engineering. Due to their lightweight, low energy consumption, high flexibility, and good initial conditions, these systems are now employed in a wide range of applications, such as flexible multi-linked manipulator systems, flexible bionic fluttering aircraft, intelligent flexible building systems, and flexible intelligent structural systems. However, there are still unresolved issues related to the dynamics modeling and control methods in the field of flexible systems. These include the trajectory tracking of flexible manipulators, the dynamics modeling and intelligent control of flexible flapping aircraft, and the vibration control of high-rise building structures in complex environments. This article aims to summarize and analyze the modeling methods and intelligent control strategies of flexible systems. Firstly, we categorize flexible system modeling methods into two types: those based on ordinary differential equations and partial differential equations. Secondly, we classify intelligent control strategies into two categories: classical control methods and intelligent control methods. We then discuss the strengths, weaknesses, and application scenarios of these different methods. Finally, we raise several questions regarding the current research status of modeling and intelligent control of flexible systems, and provide potential future research directions.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129262773","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 : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164538
Jiangnan Zhou, Yajie Ma, Bin Jiang, N. Lu, H. Zhang, Yang Liu
Rolling bearing is an important component for equipments, and failure caused by bearings may cause heavy casualties and realistic losses. Therefore, remaining useful life prediction for bearings has important practical significance. The degraded vibration signals is taken as the research object, and the end-to-end life prediction under different working conditions is taken as application background. In order to improve the prediction accuracy of remaining useful life, the prediction method based on residual convolutional network and long short-term memory is proposed. This method makes training of deeper convolutional network more effective by introducing skip connections in the network to construct different residual unit modules. It can avoid the disappearance of gradient or the degradation of network caused by too many layers, and effectively extract deep-level features of data. In view of time series features representation for degradation process, the deep long short-term memory network is used to construct the trend features of bearing degradation signal. Finally, simulation results indicate the superiority in life prediction.
{"title":"A Bearing Remaining Useful Life Prediction Method based on Residual Convolutional Network and LSTM","authors":"Jiangnan Zhou, Yajie Ma, Bin Jiang, N. Lu, H. Zhang, Yang Liu","doi":"10.1109/ISAS59543.2023.10164538","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164538","url":null,"abstract":"Rolling bearing is an important component for equipments, and failure caused by bearings may cause heavy casualties and realistic losses. Therefore, remaining useful life prediction for bearings has important practical significance. The degraded vibration signals is taken as the research object, and the end-to-end life prediction under different working conditions is taken as application background. In order to improve the prediction accuracy of remaining useful life, the prediction method based on residual convolutional network and long short-term memory is proposed. This method makes training of deeper convolutional network more effective by introducing skip connections in the network to construct different residual unit modules. It can avoid the disappearance of gradient or the degradation of network caused by too many layers, and effectively extract deep-level features of data. In view of time series features representation for degradation process, the deep long short-term memory network is used to construct the trend features of bearing degradation signal. Finally, simulation results indicate the superiority in life prediction.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121322348","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 : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164292
Kaijiang Zhao, Haitao Xie, Yaohong Qu
The autonomous landing of unmanned helicopter is one of the necessary technical means to complete modern and complex tasks. Aiming at the problems such as poor real-time performance and little content in the process of acquiring terrain information, we proposed a multi-information point cloud registration algorithm. This algorithm integrates the color information and echo intensity information of the point cloud into the traditional registration algorithm and solves the problems of poor registration accuracy and convergence speed when the traditional algorithm deals with the point cloud. In order to further verify the proposed algorithm, the performance of different registration algorithms was evaluated and compared on the ford campus data set provided by the University of Michigan. The final results show that the proposed algorithm has the advantages of high precision and fast speed compared with the traditional algorithm.
{"title":"Point cloud registration algorithm for autonomous landing based on color and intensity information","authors":"Kaijiang Zhao, Haitao Xie, Yaohong Qu","doi":"10.1109/ISAS59543.2023.10164292","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164292","url":null,"abstract":"The autonomous landing of unmanned helicopter is one of the necessary technical means to complete modern and complex tasks. Aiming at the problems such as poor real-time performance and little content in the process of acquiring terrain information, we proposed a multi-information point cloud registration algorithm. This algorithm integrates the color information and echo intensity information of the point cloud into the traditional registration algorithm and solves the problems of poor registration accuracy and convergence speed when the traditional algorithm deals with the point cloud. In order to further verify the proposed algorithm, the performance of different registration algorithms was evaluated and compared on the ford campus data set provided by the University of Michigan. The final results show that the proposed algorithm has the advantages of high precision and fast speed compared with the traditional algorithm.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122234354","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：