Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164518
Peng Wu, Wenhui Liu
This paper investigates the issue of event-triggered fixed-time adaptive neural control for time-delay nonlinear systems. First, the radial basis function neural networks (RBFNNs) are employed to approximate uncertain nonlinearities. Then, the effect of input delay is solved via the Pade approximation method. Moreover, an event-triggered mechanism is incorporated into controller to avoid the over-consumption of network resources. Based on Lyapunov stability theory and the fixed-time command filtering technology, the designed controller can ensure the boundedness of all closed-loop signals, and handle the issue of “explosion of complexity”. Finally, a practical instance is simulated to demonstrate the usefulness of the designed controller.
{"title":"Event-triggered fixed-time adaptive neural control for time-delay nonlinear systems","authors":"Peng Wu, Wenhui Liu","doi":"10.1109/ISAS59543.2023.10164518","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164518","url":null,"abstract":"This paper investigates the issue of event-triggered fixed-time adaptive neural control for time-delay nonlinear systems. First, the radial basis function neural networks (RBFNNs) are employed to approximate uncertain nonlinearities. Then, the effect of input delay is solved via the Pade approximation method. Moreover, an event-triggered mechanism is incorporated into controller to avoid the over-consumption of network resources. Based on Lyapunov stability theory and the fixed-time command filtering technology, the designed controller can ensure the boundedness of all closed-loop signals, and handle the issue of “explosion of complexity”. Finally, a practical instance is simulated to demonstrate the usefulness of the designed controller.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"138 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":"115269559","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/ISAS59543.2023.10164457
Jingjing Wang, Xi Li
The task of cross-view geo-location is to get a corresponding image from a dataset of Global Positioning System (GPS) labeled aerial-view images, given a ground-view query image with an unknown location. This task presents challenges due to the significant differences in viewpoint and appearance between the two types of images. To overcome these challenges, we have developed a novel attention-based method that leverages a key localization cue. The cross-attention-based Swap Encoder Module (SEM) is proposed, which effectively aligns features by directing the network’s focus towards relevant information. Additionally, we employ an Image Proposal Network (IPN) to ensure consistent inputs of both aerial and ground-view images that correspond, during both training and validation phases. Experimental results show that our proposed network significantly outperforms existing benchmarking CVUSA dataset, with significant improvements for top-1 recall from 61.4% to 71.45%, and for top-10 from 90.49% to 92.30%.
{"title":"Cross-Attention Network for Cross-View Image Geo-Localization","authors":"Jingjing Wang, Xi Li","doi":"10.1109/ISAS59543.2023.10164457","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164457","url":null,"abstract":"The task of cross-view geo-location is to get a corresponding image from a dataset of Global Positioning System (GPS) labeled aerial-view images, given a ground-view query image with an unknown location. This task presents challenges due to the significant differences in viewpoint and appearance between the two types of images. To overcome these challenges, we have developed a novel attention-based method that leverages a key localization cue. The cross-attention-based Swap Encoder Module (SEM) is proposed, which effectively aligns features by directing the network’s focus towards relevant information. Additionally, we employ an Image Proposal Network (IPN) to ensure consistent inputs of both aerial and ground-view images that correspond, during both training and validation phases. Experimental results show that our proposed network significantly outperforms existing benchmarking CVUSA dataset, with significant improvements for top-1 recall from 61.4% to 71.45%, and for top-10 from 90.49% to 92.30%.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"18 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":"124273184","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, the practical finite-time leaderless bipartite consensus problem for uncertain nonlinear multi-agent systems (MASs) with actuation failures is considered. With the unknown nonlinear dynamics, time-varying and unknown control gains, and undetectable actuation failures, the distributed finite-time controller design for such systems becomes more challenging. In response to this challenge, an adaptive faulttolerant distributed control protocol is proposed in this work, with which not only the neighborhood state error can converge to a sufficient small compact set within finite time, but also both the neighborhood error and the convergence time are tuned to the expected small range by adjusting the design parameters.
{"title":"Practical Finite-time Bipartite Consensus for Nonlinear Multi-agent Systems under Antagonistic Interactions and Actuation Failures","authors":"Xingyi Chen, Xiao Yang, Jiajie Li, Yujuan Wang, Qing Chen","doi":"10.1109/ISAS59543.2023.10164621","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164621","url":null,"abstract":"In this paper, the practical finite-time leaderless bipartite consensus problem for uncertain nonlinear multi-agent systems (MASs) with actuation failures is considered. With the unknown nonlinear dynamics, time-varying and unknown control gains, and undetectable actuation failures, the distributed finite-time controller design for such systems becomes more challenging. In response to this challenge, an adaptive faulttolerant distributed control protocol is proposed in this work, with which not only the neighborhood state error can converge to a sufficient small compact set within finite time, but also both the neighborhood error and the convergence time are tuned to the expected small range by adjusting the design parameters.","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":"124281095","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/ISAS59543.2023.10164494
Shiao-ping Lu, Hao Yang, Bin Jiang
This paper considers a class of distributed weakly acyclic games under best replies, where the faults appearing in decision level maliciously provide the additional payoff to players by changing the decision mechanism. Firstly, the admissible interval of each player’s payoff is established around the optimal payoff in the healthy case; Secondly, the fault tolerance as well as the incentive-based fault tolerant control is discussed in the faulty case; Finally, an example of distributed traffic routing is used to show the effectiveness of the methods.
{"title":"Incentive-based fault tolerant control of distributed weakly acyclic games","authors":"Shiao-ping Lu, Hao Yang, Bin Jiang","doi":"10.1109/ISAS59543.2023.10164494","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164494","url":null,"abstract":"This paper considers a class of distributed weakly acyclic games under best replies, where the faults appearing in decision level maliciously provide the additional payoff to players by changing the decision mechanism. Firstly, the admissible interval of each player’s payoff is established around the optimal payoff in the healthy case; Secondly, the fault tolerance as well as the incentive-based fault tolerant control is discussed in the faulty case; Finally, an example of distributed traffic routing is used to show the effectiveness of the methods.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"145 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":"127507769","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/ISAS59543.2023.10164508
Shanbin Li, Qingsheng Xiao
Traditional point feature-based visual odometry (VO) makes it difficult to find reliable point features to estimate the camera pose in low-texture environments, resulting in a significant decrease in the positioning accuracy and robustness of the system. To address the above issues, we integrate line features into VO based on point features to improve the performance of the system in low-texture scenes. Specifically, we adopt an adaptive line feature extraction strategy based on the richness of scene texture information to solve the problem of difficulty in extracting sufficient point features in low-texture scenes while ensuring the real-time performance of the system. Then, we propose a line segment merging algorithm to improve the EDLines algorithm (LM-EDLines), making the extracted line segments more complete and improving the quality of line features. To reduce the positioning error of the system when the camera turns or changes speed sharply, we propose a motion model selection strategy based on error analysis. Finally, the experimental findings on the KITTI and EuRoC datasets demonstrate that the suggested technique outperforms previous state-of-the-art systems in terms of overall performance.
{"title":"Fast Stereo Visual Odometry with Point-line Features Using Improved EDLines Algorithm","authors":"Shanbin Li, Qingsheng Xiao","doi":"10.1109/ISAS59543.2023.10164508","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164508","url":null,"abstract":"Traditional point feature-based visual odometry (VO) makes it difficult to find reliable point features to estimate the camera pose in low-texture environments, resulting in a significant decrease in the positioning accuracy and robustness of the system. To address the above issues, we integrate line features into VO based on point features to improve the performance of the system in low-texture scenes. Specifically, we adopt an adaptive line feature extraction strategy based on the richness of scene texture information to solve the problem of difficulty in extracting sufficient point features in low-texture scenes while ensuring the real-time performance of the system. Then, we propose a line segment merging algorithm to improve the EDLines algorithm (LM-EDLines), making the extracted line segments more complete and improving the quality of line features. To reduce the positioning error of the system when the camera turns or changes speed sharply, we propose a motion model selection strategy based on error analysis. Finally, the experimental findings on the KITTI and EuRoC datasets demonstrate that the suggested technique outperforms previous state-of-the-art systems in terms of overall performance.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"22 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":"125347517","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/ISAS59543.2023.10164526
Zhen Zhang, Yifan Luo, Y. Qu
In this study, with an undirected communication topology, the control problem of formation keeping for the multiple hypersonic gliding vehicles (HGVs) is investigated. On the basis of the theory of fixed-time consensus, virtual control signals are designed to reduce the complexity for formation keeping problem of multiple HGVs. The formation keeping problem is addressed by control laws that makes the altitude and path angle of each vehicle consensus. Therefore, the virtual control signals for the altitude and path angle keeping controller are designed by using first-order fixed-time and second-order fixed-time consensus theory respectively. Meanwhile, upper bound of the settling time for virtual signals can be estimated ahead of time with the information of communication topology and the given control parameters. Simulation result is carried out to demonstrated the formation keeping control laws.
{"title":"Distributed Formation Keeping Control for Multiple Hypersonic Gliding Vehicles Based on Fixed-time Consensus Theory","authors":"Zhen Zhang, Yifan Luo, Y. Qu","doi":"10.1109/ISAS59543.2023.10164526","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164526","url":null,"abstract":"In this study, with an undirected communication topology, the control problem of formation keeping for the multiple hypersonic gliding vehicles (HGVs) is investigated. On the basis of the theory of fixed-time consensus, virtual control signals are designed to reduce the complexity for formation keeping problem of multiple HGVs. The formation keeping problem is addressed by control laws that makes the altitude and path angle of each vehicle consensus. Therefore, the virtual control signals for the altitude and path angle keeping controller are designed by using first-order fixed-time and second-order fixed-time consensus theory respectively. Meanwhile, upper bound of the settling time for virtual signals can be estimated ahead of time with the information of communication topology and the given control parameters. Simulation result is carried out to demonstrated the formation keeping control laws.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"20 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":"123537340","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/ISAS59543.2023.10164502
Shuxin Liu, X. Dai, Yan Zong, Zhian Jia, Dong Zhou, D. Cui
Time synchronization is of significance in the Industrial Internet of Things (IIoT). For the impact of energy-constrained batteries for power in IIoT, a novel low-overhead time synchronization algorithm via one-way single packet exchange, i.e., improved packet-coupled oscillators (I-PkCOs), is proposed in this paper, which mainly consists of time-information packet exchange protocol according to a time-division multiple access scheme and an adaptive proportional-integral feedback clock adjustment algorithm. For clock adjustment, a proportional-integral controller is used to generate the clock adjustment amount and an adaptive algorithm is introduced to adjust the clock offset first and the clock skew later. This algorithm schedules Sync packets to be transmitted in different time slots, which can avoid packet collision and channel sniffing. Moreover, a node only needs to send one Sync packet per synchronization cycle, which effectively reduces the communication overhead and energy consumption. Hardware experiments on the SAM R21 board of processing the 32.768 MHz oscillator show that the proposed method reduces packet transmission by 50% compared to the Time synchronization Protocol for Sensor Networks (TPSN). Moreover, it has better synchronization accuracy and stability than the Packet-Coupled Oscillators (PkCOs) protocol and PISync algorithm and can achieve 1.61μs synchronization accuracy in a single-cluster network.
{"title":"Low-Overhead Time Synchronization for Energy-Constraint Industrial Internet of Things","authors":"Shuxin Liu, X. Dai, Yan Zong, Zhian Jia, Dong Zhou, D. Cui","doi":"10.1109/ISAS59543.2023.10164502","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164502","url":null,"abstract":"Time synchronization is of significance in the Industrial Internet of Things (IIoT). For the impact of energy-constrained batteries for power in IIoT, a novel low-overhead time synchronization algorithm via one-way single packet exchange, i.e., improved packet-coupled oscillators (I-PkCOs), is proposed in this paper, which mainly consists of time-information packet exchange protocol according to a time-division multiple access scheme and an adaptive proportional-integral feedback clock adjustment algorithm. For clock adjustment, a proportional-integral controller is used to generate the clock adjustment amount and an adaptive algorithm is introduced to adjust the clock offset first and the clock skew later. This algorithm schedules Sync packets to be transmitted in different time slots, which can avoid packet collision and channel sniffing. Moreover, a node only needs to send one Sync packet per synchronization cycle, which effectively reduces the communication overhead and energy consumption. Hardware experiments on the SAM R21 board of processing the 32.768 MHz oscillator show that the proposed method reduces packet transmission by 50% compared to the Time synchronization Protocol for Sensor Networks (TPSN). Moreover, it has better synchronization accuracy and stability than the Packet-Coupled Oscillators (PkCOs) protocol and PISync algorithm and can achieve 1.61μs synchronization accuracy in a single-cluster network.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"205 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":"116225518","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/ISAS59543.2023.10164361
Jiyu Zhu, Qikun Shen
This paper studies fault-tolerant control problem for a class of 1-D nonlinear systems with actuator failures and unknown powers. On the basis of Lyapunov stability theory, an adaptive control strategy is put forward and adopted for offsetting actuator failures to ensure the system’s output can follow reference signal. In existing works, actuator failures occur in nonlinear systems have been addressed. However, the input powers of these systems, especially the powers of controllers are either limited to one or a known positive integer. To relax such restrictions, we consider more general situation where controllers’ input powers are extended to an unknown integer greater than one and both efficiency loss and bias occur in the above actuators. Finally, a numerical example demonstrates the general effectiveness of developed algorithm.
{"title":"Neural Network-Based Adaptive Fault-Tolerant Control for a Class of 1-D System with Actuator Failures and Unknown Input Powers","authors":"Jiyu Zhu, Qikun Shen","doi":"10.1109/ISAS59543.2023.10164361","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164361","url":null,"abstract":"This paper studies fault-tolerant control problem for a class of 1-D nonlinear systems with actuator failures and unknown powers. On the basis of Lyapunov stability theory, an adaptive control strategy is put forward and adopted for offsetting actuator failures to ensure the system’s output can follow reference signal. In existing works, actuator failures occur in nonlinear systems have been addressed. However, the input powers of these systems, especially the powers of controllers are either limited to one or a known positive integer. To relax such restrictions, we consider more general situation where controllers’ input powers are extended to an unknown integer greater than one and both efficiency loss and bias occur in the above actuators. Finally, a numerical example demonstrates the general effectiveness of developed algorithm.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"8 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":"121466431","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/ISAS59543.2023.10164452
Tianbao Zhang, Hongbin Wang, D. Niu, Chunlei Shi, Xisong Chen, Yulong Jin
Precipitation prediction, especially accurate rainstorm warning, is a fundamental research direction in preventing major natural disasters and is of great significance. Despite the emergence of numerous deep learning models in recent years, existing CNN-based methods often struggle to effectively extract global spatiotemporal features due to limitations in the convolution kernel, greatly reducing the model’s expressive power. Additionally, relying solely on radar echo maps as a single data source also limits the accuracy of short-term precipitation prediction. In this work, we introduce a multi-modal spatiotemporal feature fusion framework called MMSTP, which utilizes multi-modal data information from satellite images and radar echo maps. The encoder module of MMSTP is designed to combine the advantages of CNN and Transformer in local feature extraction and global information perception, respectively, and uses self-attention mechanism to model temporal features and perform multi-modal fusion. MMSTP is an end-to-end multi-modal, multi-scale, and multi-frame feature fusion framework that can significantly improve the accuracy of short-term precipitation prediction. It provides a new approach to spatiotemporal sequence forecasting problems. Based on our experimental results, MMSTP surpasses the state-of-the-art (SOTA) performance on benchmark datasets.
{"title":"MMSTP: Multi-modal Spatiotemporal Feature Fusion Network for Precipitation Prediction","authors":"Tianbao Zhang, Hongbin Wang, D. Niu, Chunlei Shi, Xisong Chen, Yulong Jin","doi":"10.1109/ISAS59543.2023.10164452","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164452","url":null,"abstract":"Precipitation prediction, especially accurate rainstorm warning, is a fundamental research direction in preventing major natural disasters and is of great significance. Despite the emergence of numerous deep learning models in recent years, existing CNN-based methods often struggle to effectively extract global spatiotemporal features due to limitations in the convolution kernel, greatly reducing the model’s expressive power. Additionally, relying solely on radar echo maps as a single data source also limits the accuracy of short-term precipitation prediction. In this work, we introduce a multi-modal spatiotemporal feature fusion framework called MMSTP, which utilizes multi-modal data information from satellite images and radar echo maps. The encoder module of MMSTP is designed to combine the advantages of CNN and Transformer in local feature extraction and global information perception, respectively, and uses self-attention mechanism to model temporal features and perform multi-modal fusion. MMSTP is an end-to-end multi-modal, multi-scale, and multi-frame feature fusion framework that can significantly improve the accuracy of short-term precipitation prediction. It provides a new approach to spatiotemporal sequence forecasting problems. Based on our experimental results, MMSTP surpasses the state-of-the-art (SOTA) performance on benchmark datasets.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":" 10","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113949764","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/ISAS59543.2023.10164462
Fanliang Meng, Congwei Zhao, Qianzhang Ren, Xinhua Wang
The Tail-Sitter VTOL UAV is a new type of unmanned aerial vehicle (UAVS), and it has been the focus and difficulty of domestic and foreign scholars because of the large state changes and high control difficulty in the transition process. In this paper, an improved L1 adaptive control method was proposed to solve the problem that the aerodynamic parameters of Tail-Sitter VTOL UAV changed greatly during the transition process. Finally, the design process of the improved L1 adaptive controller is introduced in detail, and the digital simulation is carried out to verify the feasibility and effectiveness of the improved L1 adaptive controller in the UAV transition process. Finally, the digital simulation results of the whole process of Tail-Sitter VTOL UAV are given and analyzed.
{"title":"Research of Tail-Sitter VTOL UAV in Transition Process Based on an Improved L1 Adaptive Control Method","authors":"Fanliang Meng, Congwei Zhao, Qianzhang Ren, Xinhua Wang","doi":"10.1109/ISAS59543.2023.10164462","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164462","url":null,"abstract":"The Tail-Sitter VTOL UAV is a new type of unmanned aerial vehicle (UAVS), and it has been the focus and difficulty of domestic and foreign scholars because of the large state changes and high control difficulty in the transition process. In this paper, an improved L1 adaptive control method was proposed to solve the problem that the aerodynamic parameters of Tail-Sitter VTOL UAV changed greatly during the transition process. Finally, the design process of the improved L1 adaptive controller is introduced in detail, and the digital simulation is carried out to verify the feasibility and effectiveness of the improved L1 adaptive controller in the UAV transition process. Finally, the digital simulation results of the whole process of Tail-Sitter VTOL UAV are given and analyzed.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"72 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":"126297104","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：