Flexible ureteroscopy is an important natural orifice transluminal endoscopic surgery in urology. It has the advantages of minimal invasion and high treatment efficiency. However, there remain some challenges and drawbacks in clinic. Although some robotic systems were developed to improve traditional flexible ureteroscopy, there are still some issues to be addressed, such as manipulating force sensing and intrarenal pressure monitoring. Therefore, aiming to further improve the traditional flexible ureteroscopy, in this paper we designed a novel robotic system with irrigation and sensing functions, and also conducted an animal experiment to preliminarily verify it.
{"title":"Design of the robotic system for natural orifice transluminal endoscopic surgery in urology","authors":"Xiongpeng Shu, Qi Chen, Peng Hua, Shuang Wang, Ling Zhang, Le Xie","doi":"10.1109/RCAR54675.2022.9872228","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872228","url":null,"abstract":"Flexible ureteroscopy is an important natural orifice transluminal endoscopic surgery in urology. It has the advantages of minimal invasion and high treatment efficiency. However, there remain some challenges and drawbacks in clinic. Although some robotic systems were developed to improve traditional flexible ureteroscopy, there are still some issues to be addressed, such as manipulating force sensing and intrarenal pressure monitoring. Therefore, aiming to further improve the traditional flexible ureteroscopy, in this paper we designed a novel robotic system with irrigation and sensing functions, and also conducted an animal experiment to preliminarily verify it.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115517122","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 : 2022-07-17DOI: 10.1109/RCAR54675.2022.9872262
Yi Lu, Ji Huang, Zhenlong Xiao, Xin Wang, Desheng Zhang
The consensus problem of position synchronization for general multi-agent systems in static directed network is discussed in this paper. A distributed synchronous periodic sampling control law is proposed, which is applied to the multi-agent system where all agents move with an uniform acceleration. Furthermore, we show that position synchronization consensus may be obtained as long as the sample period of all agents are less than a clearly calculated threshold. Finally, the efficiency of the proposed method is demonstrated through simulation and experiment.
{"title":"Sample-data Consensus of Position Synchronization in Static Directed Networks","authors":"Yi Lu, Ji Huang, Zhenlong Xiao, Xin Wang, Desheng Zhang","doi":"10.1109/RCAR54675.2022.9872262","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872262","url":null,"abstract":"The consensus problem of position synchronization for general multi-agent systems in static directed network is discussed in this paper. A distributed synchronous periodic sampling control law is proposed, which is applied to the multi-agent system where all agents move with an uniform acceleration. Furthermore, we show that position synchronization consensus may be obtained as long as the sample period of all agents are less than a clearly calculated threshold. Finally, the efficiency of the proposed method is demonstrated through simulation and experiment.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"265 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115666210","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 : 2022-07-17DOI: 10.1109/RCAR54675.2022.9872187
Run Gao, Yingchi Liu, Jiarong Wang, Luzheng Bi
In this paper, we propose a method to decode the both-hand movement multi-direction based on electroencephalogram (EEG) signals. We use two kinds of decoding features, which are the potential amplitudes and power sums of EEG signals. One-versus-rest and decision tree are adopted as classification strategies, and linear discriminant analysis (LDA) classifier is used for classification. We apply an experimental paradigm to demonstrate the proposed method. The best four-class classification performance using the power sums of EEG signals with the one-versus-rest classification strategy is close to 70%. The experimental results show the feasibility of decoding both-hand movement multi-directions based on EEG signals. This work can promote the development of brain-computer interfaces for the assistance of hand-impaired patients.
{"title":"Multi-Direction Decoding of Both-Hand Movement Using EEG Signals","authors":"Run Gao, Yingchi Liu, Jiarong Wang, Luzheng Bi","doi":"10.1109/RCAR54675.2022.9872187","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872187","url":null,"abstract":"In this paper, we propose a method to decode the both-hand movement multi-direction based on electroencephalogram (EEG) signals. We use two kinds of decoding features, which are the potential amplitudes and power sums of EEG signals. One-versus-rest and decision tree are adopted as classification strategies, and linear discriminant analysis (LDA) classifier is used for classification. We apply an experimental paradigm to demonstrate the proposed method. The best four-class classification performance using the power sums of EEG signals with the one-versus-rest classification strategy is close to 70%. The experimental results show the feasibility of decoding both-hand movement multi-directions based on EEG signals. This work can promote the development of brain-computer interfaces for the assistance of hand-impaired patients.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115862448","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 : 2022-07-17DOI: 10.1109/RCAR54675.2022.9872230
Ci Chen, Dongqi Wang, Jiyu Yu, Pingyu Xiang, Haojian Lu, Yue Wang, R. Xiong
In the process of operating, robots will inevitably encounter damage due to external or internal factors, such as motors blockage. For the legged robot, when the motors of joints are failing, if other motors still act according to the original instructions, it will cause the robot to deviate from the predetermined trajectory, which is unacceptable for legged robots. Inspired by the fact that the model trained by supervised learning on the training set can be generalized to the testing set, our goal is to obtain a dynamic model that can be generalized to all kinds of motor damage situations. It can predict what state will be reached in the next step when an action is applied in the current state. With this dynamics model, we use the Monte Carlo particles to optimize the feasible actions in a model predictive control (MPC) fashion and achieve the expected goal (such as making the robot walk in a straight line). The comparison experiment adopt two meta-learning model and vanilla dynamics model approaches, the results show that the proposed method is superior to the three baselines, which proves the effectiveness of the proposed method.
{"title":"Fast Adaptation Dynamics Model for Robot’s Damage Recovery","authors":"Ci Chen, Dongqi Wang, Jiyu Yu, Pingyu Xiang, Haojian Lu, Yue Wang, R. Xiong","doi":"10.1109/RCAR54675.2022.9872230","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872230","url":null,"abstract":"In the process of operating, robots will inevitably encounter damage due to external or internal factors, such as motors blockage. For the legged robot, when the motors of joints are failing, if other motors still act according to the original instructions, it will cause the robot to deviate from the predetermined trajectory, which is unacceptable for legged robots. Inspired by the fact that the model trained by supervised learning on the training set can be generalized to the testing set, our goal is to obtain a dynamic model that can be generalized to all kinds of motor damage situations. It can predict what state will be reached in the next step when an action is applied in the current state. With this dynamics model, we use the Monte Carlo particles to optimize the feasible actions in a model predictive control (MPC) fashion and achieve the expected goal (such as making the robot walk in a straight line). The comparison experiment adopt two meta-learning model and vanilla dynamics model approaches, the results show that the proposed method is superior to the three baselines, which proves the effectiveness of the proposed method.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130675101","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 : 2022-07-17DOI: 10.1109/RCAR54675.2022.9872222
Shanming Bai, Juan Cui, Zhidong Zhang, Yongqiu Zheng, Chenyang Xue
The burden of doctors is heavy and the consumption of medical supplies is large in the process of traditional moxibustion treatment. Currently, the robot that can replace doctors to complete moxibustion treatment has a simple structure, low degree of freedom and intelligence, and only completes simple operation control at fixed points. Hence, there is still a lack of moxibustion robots that can realistically simulate moxibustion techniques with complex angles. In this paper, a trajectory planning algorithm for moxibustion manipulations is designed based on the 6-DOF manipulator. The robot can complete the collection of acupuncture points, which in different directions of the human body, and truly reproduce the complex and changeable moxibustion techniques. It can realize the precise control and intelligent transformation of different techniques in the treatment process. At the same time, the robot combines temperature monitoring and feedback system. It makes therapy of robot more realistic, friendlier and improves the safety of mechanical arm. Finally, the feasibility and accuracy of the robot are verified by system test. The moxibustion auxiliary robot is not only expected to be used for professional physiotherapy in hospitals, but also can be promoted to individual users for realizing the family self-help physiotherapy model, and has broad market and application prospects.
{"title":"Manipulative Control Algorithm of Moxibustion Robot Based on 6-DOF Manipulator","authors":"Shanming Bai, Juan Cui, Zhidong Zhang, Yongqiu Zheng, Chenyang Xue","doi":"10.1109/RCAR54675.2022.9872222","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872222","url":null,"abstract":"The burden of doctors is heavy and the consumption of medical supplies is large in the process of traditional moxibustion treatment. Currently, the robot that can replace doctors to complete moxibustion treatment has a simple structure, low degree of freedom and intelligence, and only completes simple operation control at fixed points. Hence, there is still a lack of moxibustion robots that can realistically simulate moxibustion techniques with complex angles. In this paper, a trajectory planning algorithm for moxibustion manipulations is designed based on the 6-DOF manipulator. The robot can complete the collection of acupuncture points, which in different directions of the human body, and truly reproduce the complex and changeable moxibustion techniques. It can realize the precise control and intelligent transformation of different techniques in the treatment process. At the same time, the robot combines temperature monitoring and feedback system. It makes therapy of robot more realistic, friendlier and improves the safety of mechanical arm. Finally, the feasibility and accuracy of the robot are verified by system test. The moxibustion auxiliary robot is not only expected to be used for professional physiotherapy in hospitals, but also can be promoted to individual users for realizing the family self-help physiotherapy model, and has broad market and application prospects.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125008453","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 : 2022-07-17DOI: 10.1109/RCAR54675.2022.9872210
Ying Chang, Yinan Wu, Yongchun Fang, Zhi Fan
In this study, a novel method combining pulse coupled neural network (PCNN) and social network search (SNS) is proposed to achieve accurate image segmentation for an atomic force microscopy (AFM). The proposed method utilizes the biological visual characteristics of PCNN and the solution space search ability of SNS to determine the optimal key parameters, which can address the issue of incorrect image segmentation caused by different topographic heights of specimens in an AFM image. In the tests, the performance of the proposed method is compared with the traditional PCNN method and the Otsu method, which demonstrates that the proposed method can automatically segment the AFM image with higher accuracy and robustness.
{"title":"Image Segmentation Based on An Improved Pulse Coupled Neural Network for Atomic Force Microscopy","authors":"Ying Chang, Yinan Wu, Yongchun Fang, Zhi Fan","doi":"10.1109/RCAR54675.2022.9872210","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872210","url":null,"abstract":"In this study, a novel method combining pulse coupled neural network (PCNN) and social network search (SNS) is proposed to achieve accurate image segmentation for an atomic force microscopy (AFM). The proposed method utilizes the biological visual characteristics of PCNN and the solution space search ability of SNS to determine the optimal key parameters, which can address the issue of incorrect image segmentation caused by different topographic heights of specimens in an AFM image. In the tests, the performance of the proposed method is compared with the traditional PCNN method and the Otsu method, which demonstrates that the proposed method can automatically segment the AFM image with higher accuracy and robustness.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125573349","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}
Biped robots have great practical value. High stability and anti-disturbance ability are the prerequisites for the practical applications of biped robots. For standing stability research, the current methods could be roughly divided into three groups: ankle strategy, hip strategy, step strategy. For the first two strategies, the virtual model control method is always used. However, many above methods adopt virtual spring damping model as the basic control model, which is too stiff and lacks flexibility. Therefore, the robots controlled by the virtual spring damping model may be easy to fall down when the disturbance is large. To solve the problem of spring damping model’s poor performance while dealing with large disturbance, the viscoelastic model is introduced in this paper, and this paper proposes a control algorithm for the underactuated biped robot to stand stably and resist disturbance in the two-dimensional environment. The new algorithm makes the robot perform a higher flexibility. The method includes the construction of linear quadratic regulator(LQR) with using viscoelastic model, the use of LQR controller to control the stable standing of biped robot and the realization of anti-disturbance function, etc. The comparsion simulations prove the better performance of the virtual viscoelastic model than the virtual spring damping model. The validity and effectiveness of the algorithm are verified through experiments.
{"title":"Biped Robots’ Push Recovery based on Viscoelastic Model*","authors":"Jiaheng Du, Xuechao Chen, Lianqiang Han, Qingqing Li, Zhifa Gao, Zhangguo Yu","doi":"10.1109/RCAR54675.2022.9872202","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872202","url":null,"abstract":"Biped robots have great practical value. High stability and anti-disturbance ability are the prerequisites for the practical applications of biped robots. For standing stability research, the current methods could be roughly divided into three groups: ankle strategy, hip strategy, step strategy. For the first two strategies, the virtual model control method is always used. However, many above methods adopt virtual spring damping model as the basic control model, which is too stiff and lacks flexibility. Therefore, the robots controlled by the virtual spring damping model may be easy to fall down when the disturbance is large. To solve the problem of spring damping model’s poor performance while dealing with large disturbance, the viscoelastic model is introduced in this paper, and this paper proposes a control algorithm for the underactuated biped robot to stand stably and resist disturbance in the two-dimensional environment. The new algorithm makes the robot perform a higher flexibility. The method includes the construction of linear quadratic regulator(LQR) with using viscoelastic model, the use of LQR controller to control the stable standing of biped robot and the realization of anti-disturbance function, etc. The comparsion simulations prove the better performance of the virtual viscoelastic model than the virtual spring damping model. The validity and effectiveness of the algorithm are verified through experiments.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121281337","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 : 2022-07-17DOI: 10.1109/RCAR54675.2022.9872197
Yongbai Liu, Gang-Yi Wang, Zhenda Tian, Keping Liu, Zhongbo Sun
Continuous motion angle estimation based on surface electromyography (sEMG) signals is a significant part of human active motion intention recognition, which plays an crucial effect in the aspect of natural human-robot interaction and rehabilitation therapy. In this paper, to predict the upper limb multi-joint angle based on multichannel sEMG signals, the Elman neural network model (ELNN) is applied and investigated to estimate upper limb multi-joint motion angle from multichannel sEMG signals under different motion modes of the upper limbs. Specifically, the sEMG signals of anterior deltoid (AD), posterior deltoid (PD), biceps brachii (BB), triceps brachii (TB), extensor carpi radialis (ECR) and flexor carpi radialis (FCR) will be collected and preprocessed, then, the ELNN model based on multichannel sEMG signals is employed to predict the multi-joint motion angles of the upper limbs including shoulder, elbow and wrist. Theoretical analysis, experimental results and root-mean-square error (RMSE) analysis indicate that the presented ELNN model has better prediction accuracy and dynamic characteristics than BP network in continuous estimation of upper limb multi-joint motion angle.
{"title":"Upper Limb Multi-Joint Angle Estimation Based on Multichannel sEMG Signals Using Elman Neural Network","authors":"Yongbai Liu, Gang-Yi Wang, Zhenda Tian, Keping Liu, Zhongbo Sun","doi":"10.1109/RCAR54675.2022.9872197","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872197","url":null,"abstract":"Continuous motion angle estimation based on surface electromyography (sEMG) signals is a significant part of human active motion intention recognition, which plays an crucial effect in the aspect of natural human-robot interaction and rehabilitation therapy. In this paper, to predict the upper limb multi-joint angle based on multichannel sEMG signals, the Elman neural network model (ELNN) is applied and investigated to estimate upper limb multi-joint motion angle from multichannel sEMG signals under different motion modes of the upper limbs. Specifically, the sEMG signals of anterior deltoid (AD), posterior deltoid (PD), biceps brachii (BB), triceps brachii (TB), extensor carpi radialis (ECR) and flexor carpi radialis (FCR) will be collected and preprocessed, then, the ELNN model based on multichannel sEMG signals is employed to predict the multi-joint motion angles of the upper limbs including shoulder, elbow and wrist. Theoretical analysis, experimental results and root-mean-square error (RMSE) analysis indicate that the presented ELNN model has better prediction accuracy and dynamic characteristics than BP network in continuous estimation of upper limb multi-joint motion angle.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"563 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116203379","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}
To meet the needs of intelligent metering platform in the future, the current status of metering automation system and problems have been described and a new system solutions based on cloud computing is presents in this paper. The feasibility and necessity of cloud computing applications in the intelligent metering platform are analyzed. A distributed cloud computing method is proposed in the light of massive electric data and a massive electric data cloud computing platform based on Hadoop is built. In this platform, virtualization technology is used to get the unified organization for various types of heterogeneous hardware and software, while he HDFS and HBase technologies are used to get the efficient distributed storage and management for massive and MapReduce technology is used to get distributed paralleled processing for user service and resource scheduling. Now, the new intelligent metering platform has practical applications, third-party test results show that most of the functions the system meet the requirement in the future smart metering platform.
{"title":"A Study on Intelligent Metering Platform Based on Cloud Computing","authors":"Xinyi Li, H. Sun, Chen Chen, X. Ou, Tianqiang Dong, Hongzhong Zhang","doi":"10.1109/RCAR54675.2022.9872268","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872268","url":null,"abstract":"To meet the needs of intelligent metering platform in the future, the current status of metering automation system and problems have been described and a new system solutions based on cloud computing is presents in this paper. The feasibility and necessity of cloud computing applications in the intelligent metering platform are analyzed. A distributed cloud computing method is proposed in the light of massive electric data and a massive electric data cloud computing platform based on Hadoop is built. In this platform, virtualization technology is used to get the unified organization for various types of heterogeneous hardware and software, while he HDFS and HBase technologies are used to get the efficient distributed storage and management for massive and MapReduce technology is used to get distributed paralleled processing for user service and resource scheduling. Now, the new intelligent metering platform has practical applications, third-party test results show that most of the functions the system meet the requirement in the future smart metering platform.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"23 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116313859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aiming at the time-varying and nonlinear problems of fixed-wing unmanned aerial vehicle (UAV) system, a UAV flight control algorithm was proposed based on PID control algorithm and the adaptive genetic algorithm (GA). On the basis of the traditional algorithm, the settling time was considered as the influencing factors of the objective function. The optimal index was determined by using the overshoot, rise time and settling time of the system response as variables, and adjusting the corresponding weight according to the actual situation to change the system response result. Moreover, the crossover probability and mutation probability in GA could be adaptively changed, so that the optimal parameters in the PID control process could be quickly and accurately found. Based on the rigid body dynamics model and kinematic model of the fixed-wing UAV, the simulation models of five control loops were designed in MATLAB/Simulink, namely the pitch angle, roll angle, yaw angle, speed and height control loops. Compared with the traditional PID controller, the system responses of the five control loops were significantly improved with faster response speed, and less than 5% overshoot. The proposed algorithm had strong adaptability and anti-interference ability.
{"title":"Control of Fixed-wing UAV Using Optimized PID Controller with the Adaptive Genetic Algorithm","authors":"Xincheng Yu, Lirong Yan, Zhizhou Guan, Yibo Wu, Fuming Peng, Fuwu Yan","doi":"10.1109/RCAR54675.2022.9872224","DOIUrl":"https://doi.org/10.1109/RCAR54675.2022.9872224","url":null,"abstract":"Aiming at the time-varying and nonlinear problems of fixed-wing unmanned aerial vehicle (UAV) system, a UAV flight control algorithm was proposed based on PID control algorithm and the adaptive genetic algorithm (GA). On the basis of the traditional algorithm, the settling time was considered as the influencing factors of the objective function. The optimal index was determined by using the overshoot, rise time and settling time of the system response as variables, and adjusting the corresponding weight according to the actual situation to change the system response result. Moreover, the crossover probability and mutation probability in GA could be adaptively changed, so that the optimal parameters in the PID control process could be quickly and accurately found. Based on the rigid body dynamics model and kinematic model of the fixed-wing UAV, the simulation models of five control loops were designed in MATLAB/Simulink, namely the pitch angle, roll angle, yaw angle, speed and height control loops. Compared with the traditional PID controller, the system responses of the five control loops were significantly improved with faster response speed, and less than 5% overshoot. The proposed algorithm had strong adaptability and anti-interference ability.","PeriodicalId":304963,"journal":{"name":"2022 IEEE International Conference on Real-time Computing and Robotics (RCAR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128086687","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：