Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053886
Wanmin Wu, Huawei Su, Zeen Gou
A visual servo control algorithm based on back propagation (BP) neural network and genetic algorithm is proposed for the problem of slow recognition speed and low accuracy of visual servo control. The algorithm models the robot and image complex Jacobi matrix to get the initial BP neural network visual servo controller, and then uses genetic algorithm to train the initial weights and thresholds of the controller to finally obtain the hybrid optimized visual control model, which can effectively combine the good global search ability of genetic algorithm with the accurate local search function of BP neural network. The experimental results show that the convergence speed is accelerated while the error is reduced to 4.6% of the original one, which provides a simple and effective method for robot control.
{"title":"Research on Precision Motion Control of Micro-motion Platform Based on Uncalibrated Visual Servo","authors":"Wanmin Wu, Huawei Su, Zeen Gou","doi":"10.1109/ICCR55715.2022.10053886","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053886","url":null,"abstract":"A visual servo control algorithm based on back propagation (BP) neural network and genetic algorithm is proposed for the problem of slow recognition speed and low accuracy of visual servo control. The algorithm models the robot and image complex Jacobi matrix to get the initial BP neural network visual servo controller, and then uses genetic algorithm to train the initial weights and thresholds of the controller to finally obtain the hybrid optimized visual control model, which can effectively combine the good global search ability of genetic algorithm with the accurate local search function of BP neural network. The experimental results show that the convergence speed is accelerated while the error is reduced to 4.6% of the original one, which provides a simple and effective method for robot control.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121767982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053851
Xuxiang Feng, An Li, Hongqun Zhang, Shengpu Shi
Estimating the probability distribution of an image is the key issue in lossless image compression. Though image compression can benefit from both global and local information, few works have been proposed to utilize both in lossless image compression. In this work, we propose to use a neural network for multiscale feature learning, the learned features are used to estimate the distribution of the image in a chain rule. In a further step, we utilize a context model to learn local features from the image. Finally, we combine the multiscale features with local features for image distribution learning. Our work surpasses state-of-the-art learning algorithms and several traditional codecs in several challenging datasets.
{"title":"Lossless Image Compression with Learned Local and Global Features","authors":"Xuxiang Feng, An Li, Hongqun Zhang, Shengpu Shi","doi":"10.1109/ICCR55715.2022.10053851","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053851","url":null,"abstract":"Estimating the probability distribution of an image is the key issue in lossless image compression. Though image compression can benefit from both global and local information, few works have been proposed to utilize both in lossless image compression. In this work, we propose to use a neural network for multiscale feature learning, the learned features are used to estimate the distribution of the image in a chain rule. In a further step, we utilize a context model to learn local features from the image. Finally, we combine the multiscale features with local features for image distribution learning. Our work surpasses state-of-the-art learning algorithms and several traditional codecs in several challenging datasets.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"168 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122047997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053848
Zhou Yuanyuan, Shan Chunlin, Zhu Guiqing, Yao Songpu
With the continuous development of expressways' convenient and unconscious toll collection, it is crucial to improve the accuracy of highway vehicle authentication while reducing the time delay of highway vehicle charging. Based on the characteristics of multi-body and multi-stage operation status of highway vehicles, starting from the dynamic authentication of highway vehicle driving process, we propose the highway reliable driving trajectory authentication based on heterogeneous blockchain technology. It realized the real-time inspection of vehicle information and the reliable track authentication of expressway vehicles based on track information chain association.
{"title":"A Vehicle Information Authentication Method of Expressway Based on Heterogeneous Blockchain Technology","authors":"Zhou Yuanyuan, Shan Chunlin, Zhu Guiqing, Yao Songpu","doi":"10.1109/ICCR55715.2022.10053848","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053848","url":null,"abstract":"With the continuous development of expressways' convenient and unconscious toll collection, it is crucial to improve the accuracy of highway vehicle authentication while reducing the time delay of highway vehicle charging. Based on the characteristics of multi-body and multi-stage operation status of highway vehicles, starting from the dynamic authentication of highway vehicle driving process, we propose the highway reliable driving trajectory authentication based on heterogeneous blockchain technology. It realized the real-time inspection of vehicle information and the reliable track authentication of expressway vehicles based on track information chain association.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"125 1-3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116706292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053909
Zhitong Zhang, Honglei An, Qing Wei, Hongxu Ma
Nowadays, reinforcement learning (RL) and model predictive control (MPC) are two of the most widely used methods in robotics community. Model-based MPC enable the robot with stable locomotion capabilities, while Model-free RL provide an automatic approach to learn the policy to maximization the corresponding task performance. In this work, be aiming at utilize the advantages of these two approaches, we propose a Learning-Based Model Predictive Control (LBMPC) methodology for quadruped robot which improves MPC performance by learning the upper-layer decision parameters for MPC though a Heuristic Monte-Carlo Expectation-Maximization (HMCEM) algorithm. We validate this framework with the problem of dynamic locomotion on slippery ground by learning the friction factor which be fixed in standard MPC algorithm. Simulation results show that our LBMPC succeeds in find the optimal friction factor respect to different ground, and our heuristic overcome the problem that the conventional EM algorithms is sensitive to the initial value of policy. At last, we deduce a heuristic strategy for crude but fast ground classification based on empirical data.
{"title":"Learning-Based Model Predictive Control for Quadruped Locomotion on Slippery Ground","authors":"Zhitong Zhang, Honglei An, Qing Wei, Hongxu Ma","doi":"10.1109/ICCR55715.2022.10053909","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053909","url":null,"abstract":"Nowadays, reinforcement learning (RL) and model predictive control (MPC) are two of the most widely used methods in robotics community. Model-based MPC enable the robot with stable locomotion capabilities, while Model-free RL provide an automatic approach to learn the policy to maximization the corresponding task performance. In this work, be aiming at utilize the advantages of these two approaches, we propose a Learning-Based Model Predictive Control (LBMPC) methodology for quadruped robot which improves MPC performance by learning the upper-layer decision parameters for MPC though a Heuristic Monte-Carlo Expectation-Maximization (HMCEM) algorithm. We validate this framework with the problem of dynamic locomotion on slippery ground by learning the friction factor which be fixed in standard MPC algorithm. Simulation results show that our LBMPC succeeds in find the optimal friction factor respect to different ground, and our heuristic overcome the problem that the conventional EM algorithms is sensitive to the initial value of policy. At last, we deduce a heuristic strategy for crude but fast ground classification based on empirical data.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121842190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053907
Ningxian Sun, Zheng Chen, Changlei Ju, Y. Jin, Ye Cao, Zijing Wang, Yujun Guo, Song Xiao
Aiming at the electrochemical corrosion problem of bogie, this paper applies the digital twin technology that is rapidly developing and widely used, proposes to build a digital twin model, and establishes a fault monitoring and early warning system based on this. After clarifying the exact functions of the system, the difficulty of model construction and data processing is reduced through deep transfer learning and algorithms. After the digital twin model is built, various test is done to verify its function. Finally, the comparison between the measured data and the twin data verifies that the model is highly correlated with reality, and the fault monitoring and early warning function works normally.
{"title":"The Application of Digital-Twin in Bogie Fault Monitoring and Early Warning","authors":"Ningxian Sun, Zheng Chen, Changlei Ju, Y. Jin, Ye Cao, Zijing Wang, Yujun Guo, Song Xiao","doi":"10.1109/ICCR55715.2022.10053907","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053907","url":null,"abstract":"Aiming at the electrochemical corrosion problem of bogie, this paper applies the digital twin technology that is rapidly developing and widely used, proposes to build a digital twin model, and establishes a fault monitoring and early warning system based on this. After clarifying the exact functions of the system, the difficulty of model construction and data processing is reduced through deep transfer learning and algorithms. After the digital twin model is built, various test is done to verify its function. Finally, the comparison between the measured data and the twin data verifies that the model is highly correlated with reality, and the fault monitoring and early warning function works normally.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126768192","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053853
Qingyun Wang, Li Yan, Zhenfeng Cui
The main technical challenges in the operation of automated warehouses with two-end access platforms are related to low operational efficiency and racks instability. This paper proposed a modified mathematical model with the optimization objectives of improving the handling efficiency of the stacker crane, reducing the center of gravity of the goods and approaching the quality of the goods in the same aisle. Meanwhile, an improved genetic algorithm based on cosine adaptive is used to optimize the objective function. The findings demonstrate that the developed mathematical model can successfully optimize the warehouse level and that the improved genetic algorithm is more effective than the conventional adaptive algorithm at resolving the allocation issue in the double-access automated warehouse.
{"title":"Optimization of Two-end Access Platform Automated Warehouse Storage Allocation","authors":"Qingyun Wang, Li Yan, Zhenfeng Cui","doi":"10.1109/ICCR55715.2022.10053853","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053853","url":null,"abstract":"The main technical challenges in the operation of automated warehouses with two-end access platforms are related to low operational efficiency and racks instability. This paper proposed a modified mathematical model with the optimization objectives of improving the handling efficiency of the stacker crane, reducing the center of gravity of the goods and approaching the quality of the goods in the same aisle. Meanwhile, an improved genetic algorithm based on cosine adaptive is used to optimize the objective function. The findings demonstrate that the developed mathematical model can successfully optimize the warehouse level and that the improved genetic algorithm is more effective than the conventional adaptive algorithm at resolving the allocation issue in the double-access automated warehouse.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"160 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114140441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053932
Jiawei Zhuang, Shiguo Peng, Yonghua Wang
This article addresses the secure leader-following consensus (SLFC) problem of nonlinear stochastic multi-agent systems, which suffer from randomly occurring uncertainties, stochastic disturbances and deception attacks. As a typical type of deception attacks, randomly occurring stealthy false data-injection (FDI) attacks imply that sensor-to-controller channels are probably injected with false signals by adversaries intending to damage consensus. The malicious attacker's behavior can be measured by the Bernoulli distribution variable. By jointly employing the Lyapunov function, the linear matrix inequality method and the definition of average impulsive interval, several sufficient conditions with less conservative are derived, which means that impulsive control scheme can ensure the achievement of SLFC within a given error bound. Finally, one simple simulation example is reported to verify the reliability and effectiveness of our developed results.
{"title":"Secure Consensus of Stochastic Multi-agent Systems Subject to Deception Attacks via Impulsive Control","authors":"Jiawei Zhuang, Shiguo Peng, Yonghua Wang","doi":"10.1109/ICCR55715.2022.10053932","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053932","url":null,"abstract":"This article addresses the secure leader-following consensus (SLFC) problem of nonlinear stochastic multi-agent systems, which suffer from randomly occurring uncertainties, stochastic disturbances and deception attacks. As a typical type of deception attacks, randomly occurring stealthy false data-injection (FDI) attacks imply that sensor-to-controller channels are probably injected with false signals by adversaries intending to damage consensus. The malicious attacker's behavior can be measured by the Bernoulli distribution variable. By jointly employing the Lyapunov function, the linear matrix inequality method and the definition of average impulsive interval, several sufficient conditions with less conservative are derived, which means that impulsive control scheme can ensure the achievement of SLFC within a given error bound. Finally, one simple simulation example is reported to verify the reliability and effectiveness of our developed results.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116394762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053930
Yuting Zhu, Liang Cao, Yi Qin, Pengxiang Zhang
The finite-time funnel control problem is addressed for stochastic nonlinear systems with actuator faults. In the case of stochastic disturbance and actuator faults, a funnel function is designed to reduce the overshoot of the system and improve the tracking performance of system, where the tracking error reaches the desired accuracy. An adaptive finite-time controller compensates the effect of the actuator fault. A second-order tracking differentiator is adopted to address the “complexity explosion” issue caused by the repeated differentiations of the virtual controller. By applying the Lyapunov stability method, the stabilization of the closed-loop systems can be pledged. Finally, simulation results are given to prove the effectiveness of the proposed algorithm.
{"title":"Adaptive Finite-Time Funnel Control for Stochastic Nonlinear Systems with Actuator Faults","authors":"Yuting Zhu, Liang Cao, Yi Qin, Pengxiang Zhang","doi":"10.1109/ICCR55715.2022.10053930","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053930","url":null,"abstract":"The finite-time funnel control problem is addressed for stochastic nonlinear systems with actuator faults. In the case of stochastic disturbance and actuator faults, a funnel function is designed to reduce the overshoot of the system and improve the tracking performance of system, where the tracking error reaches the desired accuracy. An adaptive finite-time controller compensates the effect of the actuator fault. A second-order tracking differentiator is adopted to address the “complexity explosion” issue caused by the repeated differentiations of the virtual controller. By applying the Lyapunov stability method, the stabilization of the closed-loop systems can be pledged. Finally, simulation results are given to prove the effectiveness of the proposed algorithm.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129527650","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053917
Jing Zhang, Wenwen Kang
This paper addresses the problem of observer design for a reaction-diffusion equation with delayed boundary measurement. The predictor method is employed for the delay compensation. The reaction coefficient of the plant is considered, which may lead to the instability. To obtain the stability result, the backstepping transformation is introduced to determine the observer gains. Linear matrix inequalities (LMIs) conditions are derived to guarantee the exponential stability of the error system. The numerical simulation is provided to validate the proposed results.
{"title":"Observer Design for a Reaction-Diffusion Equation with Delayed Boundary Measurement","authors":"Jing Zhang, Wenwen Kang","doi":"10.1109/ICCR55715.2022.10053917","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053917","url":null,"abstract":"This paper addresses the problem of observer design for a reaction-diffusion equation with delayed boundary measurement. The predictor method is employed for the delay compensation. The reaction coefficient of the plant is considered, which may lead to the instability. To obtain the stability result, the backstepping transformation is introduced to determine the observer gains. Linear matrix inequalities (LMIs) conditions are derived to guarantee the exponential stability of the error system. The numerical simulation is provided to validate the proposed results.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128252549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-02DOI: 10.1109/ICCR55715.2022.10053922
Yajun Gao, G. Duan
The problem of robust pole assignment for the uncertain high-order system is formulated. On the strength of a previous eigenstructure assignment result for the high-order system, by introducing the sensitivity of uncertain parameters in the system model to the closed-loop poles, the parametric expression of the state feedback gain matrix to the problem of robust pole assignment is obtained. The robust optimal solution can be derived by a simple independent optimization algorithm. The closed-loop poles can be fixed or chosen within certain desired regions on the complex plane, which further improves the robustness. The example illustrates robust state feedback controller obtained by the proposed algorithm has better robustness.
{"title":"Robust Pole Assignment via State Feedback for Uncertain High-order System","authors":"Yajun Gao, G. Duan","doi":"10.1109/ICCR55715.2022.10053922","DOIUrl":"https://doi.org/10.1109/ICCR55715.2022.10053922","url":null,"abstract":"The problem of robust pole assignment for the uncertain high-order system is formulated. On the strength of a previous eigenstructure assignment result for the high-order system, by introducing the sensitivity of uncertain parameters in the system model to the closed-loop poles, the parametric expression of the state feedback gain matrix to the problem of robust pole assignment is obtained. The robust optimal solution can be derived by a simple independent optimization algorithm. The closed-loop poles can be fixed or chosen within certain desired regions on the complex plane, which further improves the robustness. The example illustrates robust state feedback controller obtained by the proposed algorithm has better robustness.","PeriodicalId":441511,"journal":{"name":"2022 4th International Conference on Control and Robotics (ICCR)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129584341","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：