Pub Date : 2018-06-01DOI: 10.1109/ICIST.2018.8426186
Rong Zhou, Kemin Zhou, Menghua Wu, Jing Teng
Tracking maneuvering target is a challenging problem and Interactive Multiple Model (IMM) is proved an effective solution for it. In multiple model, the constant turn model (CT) is usually used to describe the target's turning motion. However, fixed or partially adaptive turn angular rate μ is usually adopted in CT which leads to tracking accuracy decrease. In this paper, an improved interactive multiple model set based on self-adaptive CT model is proposed. In self-adaptive CT model, the value of the turn angular rate ωis calculated based on both x and y velocity instead of only one of them or fixed value. To verify the improvement, particle filter, which is proved an effective way to solve non Gaussian nonlinear problem, is used to track maneuvering target. The performance of the proposed multiple model set is verified in two different scenarios and compared to two widely used multiple model sets. Simulation results show that the proposed model set has better performance both in tracking accuracy and computational cost.
{"title":"Improved Interactive Multiple Models Based on Self-Adaptive Turn Model for Maneuvering Target Tracking","authors":"Rong Zhou, Kemin Zhou, Menghua Wu, Jing Teng","doi":"10.1109/ICIST.2018.8426186","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426186","url":null,"abstract":"Tracking maneuvering target is a challenging problem and Interactive Multiple Model (IMM) is proved an effective solution for it. In multiple model, the constant turn model (CT) is usually used to describe the target's turning motion. However, fixed or partially adaptive turn angular rate μ is usually adopted in CT which leads to tracking accuracy decrease. In this paper, an improved interactive multiple model set based on self-adaptive CT model is proposed. In self-adaptive CT model, the value of the turn angular rate ωis calculated based on both x and y velocity instead of only one of them or fixed value. To verify the improvement, particle filter, which is proved an effective way to solve non Gaussian nonlinear problem, is used to track maneuvering target. The performance of the proposed multiple model set is verified in two different scenarios and compared to two widely used multiple model sets. Simulation results show that the proposed model set has better performance both in tracking accuracy and computational cost.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130972929","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}
StarCraft II is one of the most popular real-time strategy games and has become an important benchmark for AI research as it provides a complex environment with numerous challenges. The build order problem is one of the key challenges which concern the order and type of buildings and units to produce based on current game situation. In contrast to existing hand-craft methods, we propose two reinforcement learning based models: Neural Network Fitted Q-Learning (NNFQ) and Convolutional Neural Network Fitted Q-Learning (CNNFQ). NNFQ and CNNFQ have been applied into a simple bot for fighting against the enemy race. Experimental results show that both these two models are capable of finding the most effective production sequence to defeat the opponent.
{"title":"Reinforcement Learning for Build-Order Production in StarCraft II","authors":"Zhentao Tang, Dongbin Zhao, Yuanheng Zhu, Ping Guo","doi":"10.1109/ICIST.2018.8426160","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426160","url":null,"abstract":"StarCraft II is one of the most popular real-time strategy games and has become an important benchmark for AI research as it provides a complex environment with numerous challenges. The build order problem is one of the key challenges which concern the order and type of buildings and units to produce based on current game situation. In contrast to existing hand-craft methods, we propose two reinforcement learning based models: Neural Network Fitted Q-Learning (NNFQ) and Convolutional Neural Network Fitted Q-Learning (CNNFQ). NNFQ and CNNFQ have been applied into a simple bot for fighting against the enemy race. Experimental results show that both these two models are capable of finding the most effective production sequence to defeat the opponent.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121709452","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 : 2018-06-01DOI: 10.1109/ICIST.2018.8426081
X. Ji, Zhuangzhuang Jin, Jiangtao Cao, Yangyang Wang
The existing methods of two-person interaction action recognition based on RGB image is greatly affected by illumination change, object occlusion and environmental change. Considering the respective advantages of the RGB image and the depth image, and the characteristics of information complementarity, this paper proposed a multi - source information fusion algorithm. In our proposed method, the recognition probability of the RGB image and the depth image are weighted fused for the two-person interaction action recognition. Firstly, the frame difference method and ViBe algorithm are respectively used for moving object detection and segmentation. Secondly, histogram of oriented gradient (HOG) features are respectively extracted from the moving regions of the RGB image and the depth image. Thirdly, the nearest neighbor classifier algorithm is used to recognize the actions of the RGB image and the depth image. Finally, the recognition results of the RGB image and the depth image are weighted fused. Experimental results show that the method achieves the better recognition rate.
{"title":"Two-Person Interaction Action Recognition Based on Multi-Source Information Fusion Algorithm","authors":"X. Ji, Zhuangzhuang Jin, Jiangtao Cao, Yangyang Wang","doi":"10.1109/ICIST.2018.8426081","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426081","url":null,"abstract":"The existing methods of two-person interaction action recognition based on RGB image is greatly affected by illumination change, object occlusion and environmental change. Considering the respective advantages of the RGB image and the depth image, and the characteristics of information complementarity, this paper proposed a multi - source information fusion algorithm. In our proposed method, the recognition probability of the RGB image and the depth image are weighted fused for the two-person interaction action recognition. Firstly, the frame difference method and ViBe algorithm are respectively used for moving object detection and segmentation. Secondly, histogram of oriented gradient (HOG) features are respectively extracted from the moving regions of the RGB image and the depth image. Thirdly, the nearest neighbor classifier algorithm is used to recognize the actions of the RGB image and the depth image. Finally, the recognition results of the RGB image and the depth image are weighted fused. Experimental results show that the method achieves the better recognition rate.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124385503","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 : 2018-06-01DOI: 10.1109/ICIST.2018.8426143
Dong Wang, J. Yin, Wei Wang
This paper proposes a novel distributed optimal protocol with a fixed step size for discrete time multi-agent systems to solve a distributed convex optimization problem over a weighted unbalanced digraph. The considered digraph is described by a row stochastic matrix. Each agent with an individual local cost function acquires the state information of in-neighbor agents constantly to update its state estimation. We analyze the existence of the optimal solution and obtain the approximate linear convergence rate through the mean value theorem and the Lyapunov function method. Finally, the validity of the algortthm is verified by the numerical simulation.
{"title":"Design of Fixed Step-Size Distributed Optimization Protocol of Multiagent Systems Over Weighted Unbalanced Digraphs","authors":"Dong Wang, J. Yin, Wei Wang","doi":"10.1109/ICIST.2018.8426143","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426143","url":null,"abstract":"This paper proposes a novel distributed optimal protocol with a fixed step size for discrete time multi-agent systems to solve a distributed convex optimization problem over a weighted unbalanced digraph. The considered digraph is described by a row stochastic matrix. Each agent with an individual local cost function acquires the state information of in-neighbor agents constantly to update its state estimation. We analyze the existence of the optimal solution and obtain the approximate linear convergence rate through the mean value theorem and the Lyapunov function method. Finally, the validity of the algortthm is verified by the numerical simulation.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130484523","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 : 2018-06-01DOI: 10.1109/ICIST.2018.8426162
Yibo Zhang, Dan Wang, Zhouhua Peng
In this paper, we investigate a containment maneuvering problem for uncertain nonlinear systems in MIMO strict-feedback form. The outputs of followers are driven to converge to a convex hull spanned by multiple parameterized paths and path variables need to satisfy a given dynamic task. A containment maneuvering controller is proposed based on a modular design approach. First, an estimation module is developed based on an RBF network, and adaption laws are proposed based on a concurrent learning method. Then, a controller module is proposed based on a modified dynamic surface control method using a second-order nonlinear tracking differentiator. At last, a path update law is designed by using a distributed maneuvering error feedback. Input-to-state stability theory and cascade theory are utilized to analyze the stability of the closed-loop system. The proposed design is a distributed method and attains adaption without the persistent excitation condition.
{"title":"Containment Maneuvering for a Class of Uncertain Nonlinear Systems Based on Concurrent Learning","authors":"Yibo Zhang, Dan Wang, Zhouhua Peng","doi":"10.1109/ICIST.2018.8426162","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426162","url":null,"abstract":"In this paper, we investigate a containment maneuvering problem for uncertain nonlinear systems in MIMO strict-feedback form. The outputs of followers are driven to converge to a convex hull spanned by multiple parameterized paths and path variables need to satisfy a given dynamic task. A containment maneuvering controller is proposed based on a modular design approach. First, an estimation module is developed based on an RBF network, and adaption laws are proposed based on a concurrent learning method. Then, a controller module is proposed based on a modified dynamic surface control method using a second-order nonlinear tracking differentiator. At last, a path update law is designed by using a distributed maneuvering error feedback. Input-to-state stability theory and cascade theory are utilized to analyze the stability of the closed-loop system. The proposed design is a distributed method and attains adaption without the persistent excitation condition.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116472104","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 : 2018-06-01DOI: 10.1109/ICIST.2018.8426152
Wenqian Du, F. Gu, Hao Zhou, Chunlei Di, Junfeng Xiong, Yuqing He
UGVs' application are always restrained in complicated environment because of its limited perception ability. One of the solution is cooperation with UAV which has large perception scale. Thus, the fusion of the air-ground perceptive information is the key problem. Focused on this problem, the ESMF based 2.5D elevation modeling method is first proposed for its bound rather than probabilistic information is robust and reliable for path planning of UGVs. In the second, the fast fusion method between air and ground vehicles is designed, which achieve data fusion by updating the perception of UGV with UAV instead of intersecting the two observation sets. In the third the traversability is analyzed based on the elevation model described with bounded information, which shows the robust and reliable of the proposed method. In the last based on two typical limited perception ability: negative and ultrahigh obstacle an experiment is designed to verify the feasibility and validity of the propose method.
{"title":"Air-Ground Cooperative Environment Modeling with Bounded Elevation Map","authors":"Wenqian Du, F. Gu, Hao Zhou, Chunlei Di, Junfeng Xiong, Yuqing He","doi":"10.1109/ICIST.2018.8426152","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426152","url":null,"abstract":"UGVs' application are always restrained in complicated environment because of its limited perception ability. One of the solution is cooperation with UAV which has large perception scale. Thus, the fusion of the air-ground perceptive information is the key problem. Focused on this problem, the ESMF based 2.5D elevation modeling method is first proposed for its bound rather than probabilistic information is robust and reliable for path planning of UGVs. In the second, the fast fusion method between air and ground vehicles is designed, which achieve data fusion by updating the perception of UGV with UAV instead of intersecting the two observation sets. In the third the traversability is analyzed based on the elevation model described with bounded information, which shows the robust and reliable of the proposed method. In the last based on two typical limited perception ability: negative and ultrahigh obstacle an experiment is designed to verify the feasibility and validity of the propose method.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123974657","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 : 2018-06-01DOI: 10.1109/ICIST.2018.8426074
Shaoxin Li, Nankun Mu, X. Liao
Privacy preserving frequent itemsets mining (PP-FIM) aims at transforming a database so as to efficiently achieve frequent itemsets mining without revealing any sensitive knowledge. However, the majority of the proposed PPFIM methods are based on the idea of sanitizing database. The conflict between knowledge mining and privacy preserving is hard to avoid. To this end, we propose a novel PPFIM algorithm based on database reconstruction called DR-PPFIM, which can afford high data utility as well as high degree of privacy. In DR-PPFIM, a sanitization algorithm is first performed to remove all sensitive knowledge. Then a novel database reconstruction scheme is designed to reconstruct a new database based on the remained non-sensitive frequent itemsets. In addition, we propose a further hiding strategy to further decrease the importance of sensitive itemsets so that the threat of disclosing confidential knowledge can be reduced. Experimental evaluations of the proposed DR-PPFIM on real datasets are reported to show the superiority of DR-PPFIM compared with other state-of-the-art algorithms.
{"title":"Privacy Preserving Frequent Itemsets Mining Based on Database Reconstruction","authors":"Shaoxin Li, Nankun Mu, X. Liao","doi":"10.1109/ICIST.2018.8426074","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426074","url":null,"abstract":"Privacy preserving frequent itemsets mining (PP-FIM) aims at transforming a database so as to efficiently achieve frequent itemsets mining without revealing any sensitive knowledge. However, the majority of the proposed PPFIM methods are based on the idea of sanitizing database. The conflict between knowledge mining and privacy preserving is hard to avoid. To this end, we propose a novel PPFIM algorithm based on database reconstruction called DR-PPFIM, which can afford high data utility as well as high degree of privacy. In DR-PPFIM, a sanitization algorithm is first performed to remove all sensitive knowledge. Then a novel database reconstruction scheme is designed to reconstruct a new database based on the remained non-sensitive frequent itemsets. In addition, we propose a further hiding strategy to further decrease the importance of sensitive itemsets so that the threat of disclosing confidential knowledge can be reduced. Experimental evaluations of the proposed DR-PPFIM on real datasets are reported to show the superiority of DR-PPFIM compared with other state-of-the-art algorithms.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125501497","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 : 2018-06-01DOI: 10.1109/ICIST.2018.8426184
Dan-Ting Duan, Yue-jiao Gong, Ting Huang, Jun Zhang
Multimodal optimization problems which widely exist in the scientific research and engineering applications, has aroused a wide interest of researchers. For solving multimodal optimization problems, numerous niching algorithms have been proposed to locate and track multiple optima. However, most of these algorithms need a very strict choice of the population size parameter. This paper presents a new niching differential evolution algorithm which adaptively adjusts population size during the evolution. Particularly, we propose three techniques for performance enhancement: a heuristic clustering method, a population adaptation strategy, and an auxiliary movement strategy for the best individuals. The algorithm divides the population into several subpopulations and adaptively adjust the number of individuals and subpopulations according to the evolutionary state. In this way, the diversity of population is increased, while the computational cost is reduced. Experimental results verify that the proposed algorithm outperforms the other niching algorithms for multimodal optimization.
{"title":"Adaptive Clustering-Based Differential Evolution for Multimodal Optimization","authors":"Dan-Ting Duan, Yue-jiao Gong, Ting Huang, Jun Zhang","doi":"10.1109/ICIST.2018.8426184","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426184","url":null,"abstract":"Multimodal optimization problems which widely exist in the scientific research and engineering applications, has aroused a wide interest of researchers. For solving multimodal optimization problems, numerous niching algorithms have been proposed to locate and track multiple optima. However, most of these algorithms need a very strict choice of the population size parameter. This paper presents a new niching differential evolution algorithm which adaptively adjusts population size during the evolution. Particularly, we propose three techniques for performance enhancement: a heuristic clustering method, a population adaptation strategy, and an auxiliary movement strategy for the best individuals. The algorithm divides the population into several subpopulations and adaptively adjust the number of individuals and subpopulations according to the evolutionary state. In this way, the diversity of population is increased, while the computational cost is reduced. Experimental results verify that the proposed algorithm outperforms the other niching algorithms for multimodal optimization.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126892060","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 : 2018-06-01DOI: 10.1109/ICIST.2018.8426154
N. Zhang, Jiang Xiong, Jing Zhong, Lara A. Thompson
This paper develops a hybrid binary particle swarm optimization (BPSO) and evolutionary algorithm (EA) based feature selection method. Inspired by the concept of binary PSO, the particle's position updating process is designed in a binary search space. The fitness function is defined as the accuracy of the ENN classifier. The feature selection method using a hybrid BPSO-EA learning algorithm is developed and described. The experiments include the comparison of ENN classification accuracy with and without the BPSO-EA feature selection method. The feature reduction rate between the proposed BPSO-EA-ENN method and the BPSO+C4.5 method is also compared. In addition, a comparison of BPSO-EA-ENN to other classification methods is provided. The experimental results demonstrate that the proposed BPSO-EA feature selection method improves the classification accuracy. In addition, our proposed method has higher improved accuracy and feature reduction rate than the BPSO+C4.5 feature selection method on the Ionosphere data set, as well as better accuracy rate than the BPSO+C4.5 method on the Movement Libra data set. Further, the overall classification accuracy of our proposed BPSO-EA-ENN outperforms ENN, KNN, Naïve Bayes, and LDA classification methods on the eight UCI data sets.
提出了一种基于二元粒子群优化(BPSO)和进化算法(EA)的混合特征选择方法。受二进制粒子群的概念启发,在二进制搜索空间中设计了粒子的位置更新过程。适应度函数定义为ENN分类器的准确率。提出并描述了基于混合BPSO-EA学习算法的特征选择方法。实验包括使用和不使用BPSO-EA特征选择方法对新神经网络分类精度的比较。比较了BPSO- ea - enn方法与BPSO+C4.5方法的特征约简率。此外,还将BPSO-EA-ENN与其他分类方法进行了比较。实验结果表明,提出的BPSO-EA特征选择方法提高了分类精度。此外,本文提出的方法在电离层数据集上比BPSO+C4.5特征选择方法具有更高的改进精度和特征约简率,在天秤座运动数据集上比BPSO+C4.5方法具有更高的准确率。此外,我们提出的BPSO-EA-ENN在8个UCI数据集上的总体分类精度优于ENN、KNN、Naïve贝叶斯和LDA分类方法。
{"title":"Feature Selection Method Using BPSO-EA with ENN Classifier","authors":"N. Zhang, Jiang Xiong, Jing Zhong, Lara A. Thompson","doi":"10.1109/ICIST.2018.8426154","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426154","url":null,"abstract":"This paper develops a hybrid binary particle swarm optimization (BPSO) and evolutionary algorithm (EA) based feature selection method. Inspired by the concept of binary PSO, the particle's position updating process is designed in a binary search space. The fitness function is defined as the accuracy of the ENN classifier. The feature selection method using a hybrid BPSO-EA learning algorithm is developed and described. The experiments include the comparison of ENN classification accuracy with and without the BPSO-EA feature selection method. The feature reduction rate between the proposed BPSO-EA-ENN method and the BPSO+C4.5 method is also compared. In addition, a comparison of BPSO-EA-ENN to other classification methods is provided. The experimental results demonstrate that the proposed BPSO-EA feature selection method improves the classification accuracy. In addition, our proposed method has higher improved accuracy and feature reduction rate than the BPSO+C4.5 feature selection method on the Ionosphere data set, as well as better accuracy rate than the BPSO+C4.5 method on the Movement Libra data set. Further, the overall classification accuracy of our proposed BPSO-EA-ENN outperforms ENN, KNN, Naïve Bayes, and LDA classification methods on the eight UCI data sets.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126046358","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 : 2018-06-01DOI: 10.1109/ICIST.2018.8426187
Zhankui Song, Jun Wang
The paper addresses the problem of trajectory tracking control of a quad-rotor system, aiming to improve the performance of path tracking and obtain a better “adverse factors” rejection property. In response to a hybrid effect that external disturbance, inertia parameters uncertainty and control input constraints coexist in a dynamic system, an adaptive compensated controller with back-stepping technique is proposed. The designed control system can compensate for errors caused by the hybrid effect without the need for an accurate model. Furthermore, a fuzzy monitoring strategy is introduced to improve adaptive ability of the closed loop control structure and achieve better transients. Adaptive laws in the control system are derived by Lyapunov stability analysis such that the trajectories of tracking error converge to a small neighborhood of equilibrium point. Finally, simulation results are discussed to demonstrate the effectiveness of the proposed control method.
{"title":"Adaptive Trajectory Tracking Control of a Quad-Rotor System Based on Fuzzy Monitoring Strategy","authors":"Zhankui Song, Jun Wang","doi":"10.1109/ICIST.2018.8426187","DOIUrl":"https://doi.org/10.1109/ICIST.2018.8426187","url":null,"abstract":"The paper addresses the problem of trajectory tracking control of a quad-rotor system, aiming to improve the performance of path tracking and obtain a better “adverse factors” rejection property. In response to a hybrid effect that external disturbance, inertia parameters uncertainty and control input constraints coexist in a dynamic system, an adaptive compensated controller with back-stepping technique is proposed. The designed control system can compensate for errors caused by the hybrid effect without the need for an accurate model. Furthermore, a fuzzy monitoring strategy is introduced to improve adaptive ability of the closed loop control structure and achieve better transients. Adaptive laws in the control system are derived by Lyapunov stability analysis such that the trajectories of tracking error converge to a small neighborhood of equilibrium point. Finally, simulation results are discussed to demonstrate the effectiveness of the proposed control method.","PeriodicalId":331555,"journal":{"name":"2018 Eighth International Conference on Information Science and Technology (ICIST)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131126202","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}