{"title":"Rocket Powered Landing Guidance Using Proximal Policy Optimization","authors":"Yifan Chen, Lin Ma","doi":"10.1145/3351917.3351935","DOIUrl":"https://doi.org/10.1145/3351917.3351935","url":null,"abstract":"Rocket recovery requires advanced guidance algorithms to achieve pinpoint landing while satisfying multiple stringent constraints. In this paper, we design a guidance law based on reinforcement learning for the powered landing phase of vertical take-off and vertical landing reusable rocket. To this end, we apply the proximal policy optimization algorithm to develop a control policy that drives the rocket to land at a specified location. The policy parameterized using a neural network is updated by performing gradient ascent algorithm. After abundant amount of training, the learned policy is evaluated in a simulation of the rocket powered landing scenario considering aerodynamic drag, and the result demonstrates the ability of the proposed guidance method to successfully land the rocket from a random initial state.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121215086","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}
{"title":"Surface Multi-target Tracking Algorithm Based on Data Association of Information Fusion","authors":"Jun Song, Zhongben Zhu, Lei Wan","doi":"10.1145/3351917.3351974","DOIUrl":"https://doi.org/10.1145/3351917.3351974","url":null,"abstract":"To solve the problem that the unmanned surface vehicle is vulnerable to external environmental impact in tracking multi-target, this paper proposes a water surface multi-target tracking algorithm based on information fusion data association. By transmitting the target motion information detected by the neural network to the motion measurement model, the target location is predicted. The Mahalanobis square distance between the observed and predicted values of the targets is calculated to represent the matching degree of the target motion information. In addition, the differences and similarities between the target features preserved in the trajectory and those detected in the current frame are calculated to represent the matching degree of the appearance information of the targets. The experimental results show that the proposed algorithm can track multiple targets effectively in case of wave fluctuations, illumination changes and occlusion. The tracking accuracy and precision are 66.8% and 82.5% respectively, which shows that the algorithm has good reliability.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"2017 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127554730","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}
{"title":"Stabilization Control of Underactuated Unmanned Surface Vessels Based on Backstepping and Lyapunov Direct Method","authors":"Fangfang Hu, Chao Zeng, Gang Zhu, Shiling Li","doi":"10.1145/3351917.3351956","DOIUrl":"https://doi.org/10.1145/3351917.3351956","url":null,"abstract":"In this paper, a time-varying controller is proposed for the underactuated Unmanned Surface Vessels (USV) with non-diagonal inertia and damping matrices. By introducing a reference trajectory, the controller can guarantee global asymptotic convergence from any initial values at any moment. Firstly, with the method of global diffeomorphism equivalent and input transformation, the stabilization problem of underactuated USV can be transformed into the stabilization of two cascaded subsystems. Secondly, according to the characters of the cascaded subsystems, the stabilization problem can be reduced to the one of the second subsystem, a nonlinear time-varying controller is developed through backstepping and Lyapunov's methods, stability analysis proves that all the states can be globally regulated to the origin. Finally, simulation results demonstrate the effectiveness of the proposed control approach.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114577061","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}
{"title":"Research on the Flexible Three-Dimensional Force Sensor Based on Microstructure","authors":"Yuyun Xu, Xuehua Dong, H. Pan, F. Shuang","doi":"10.1145/3351917.3351937","DOIUrl":"https://doi.org/10.1145/3351917.3351937","url":null,"abstract":"A flexible three-dimensional force sensor based on microstructures is proposed. The structure design and fabrication of the sensor are introduced. The principle of the three-dimensional force detection is expounded. The mathematical model of the force on the sensor is established. The tactile sensing mechanism is analyzed by finite element analysis. A data acquisition system is built to calibrate and verify the sensor. The BP neural network is used to decouple the sensor. The results show that the sensor is simple and flexible in structure and can realize the three-dimensional force detection.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115158367","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}
Hao Zhang, Rong Li, Jinxia Yao, Xiaoli Hu, Chao Gu, Meng Wang
{"title":"Design and Implementation of Submarine Cable Way-points Tracking Control Based on Single Neuron Adaptive PID","authors":"Hao Zhang, Rong Li, Jinxia Yao, Xiaoli Hu, Chao Gu, Meng Wang","doi":"10.1145/3351917.3351959","DOIUrl":"https://doi.org/10.1145/3351917.3351959","url":null,"abstract":"Due to the complex work environment and open frame structure, it is difficult to accurately establish and implement the model and parameters of ROV. Therefore, ROV is suitable for adaptive controller with simple structure and can meet the change of parameters. The single neuron adaptive PID controller has simple structure, self-adaptability and strong robustness. It can learn and adjust itself online in the working process. In this paper, a single neuron adaptive PID controller is proposed to realize multi-path point tracking control. In order to verify the effectiveness and practicability of the proposed method, two tracking control experiments were carried out in a pool using a working class ROV. The experimental results verify the effectiveness of this method.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121780093","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}
{"title":"Research on Arm Shape of Manipulator Based on Trajectory and End Posture","authors":"Y. Chen, Jin-ming Zhang, Hangkuan Zhang","doi":"10.1145/3351917.3351923","DOIUrl":"https://doi.org/10.1145/3351917.3351923","url":null,"abstract":"In order to solve the problem of reasonable distribution of joint combination in the design process of manipulator. In the design of manipulator, the target trajectory of manipulator and the requirement of end attitude should be taken into account. By dividing the change of trajectory and terminal attitude according to the three components of X-Y-Z, the corresponding joint combination mode is given. The kinematics relation of the arm shape of the manipulator is established by using the D-H representation. The forward and inverse solutions are obtained by using the Robotics Toolbox in MATLAB, and the workspace is given. By checking whether there is a reasonable inverse solution to judge the appropriate joint combination mode, according to the change of the attitude at the end of the joint, it is increased according to the change of the posture at the end of the joint. Add the corresponding joint type to complete the target task. According to this method, the design idea of manipulator can be given clearly, which provides a reference for improving the rationality of manipulator joint combination.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"97 26","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113944073","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}
{"title":"Adaptive Robust Control for Electro-Hydraulic Servo System of a Projectile Transfer Arm","authors":"Chengxi Li, Hongbin Chen","doi":"10.1145/3351917.3351975","DOIUrl":"https://doi.org/10.1145/3351917.3351975","url":null,"abstract":"An adaptive robust control method is proposed to solve the problem of uncertain nonlinearity and parameter uncertainty in a kind of valve controlled asymmetric cylinder electro-hydraulic servo system of a projectile transfer arm. A backstepping method is applied to design the state feedback controller and robust control method is applied to compensate the influence of uncertain nonlinear term. An adaptive controller with a discontinuous projection algorithm is introduced to ensure boundedness of parameter estimation. The stability of the closed loop system is verified by the Lyapunov theory. A simulation is conducted on the model of the projectile transfer arm electro-hydraulic servo system. Compared with the simulation results of PID control method and backstepping robust control method, the result of adaptive robust control method has superiority in control precision and stability.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129232825","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}
Wei-rang Wu, Yu-chun Tao, Tong Yu, Xun-zong Yang, Jin Lv
{"title":"Research on Novel Televisual Automatic Inspection Methods For CPR1000 Steam Generator Secondary Side","authors":"Wei-rang Wu, Yu-chun Tao, Tong Yu, Xun-zong Yang, Jin Lv","doi":"10.1145/3351917.3351946","DOIUrl":"https://doi.org/10.1145/3351917.3351946","url":null,"abstract":"Steam generator is a vital component which is the boundary between the first loop and second loop. It is very essential to know steam generator's sludge amount and distribution to monitor its healthiness. It is preferable to use televisual method than eddy current to inspect sludge. Although tubesheet televisual inspection has been done manually every outage, however, this is not enough for monitoring the condition of steam generator continually. Automatic inspection methods for tubesheet, the first support plate, the second support plate and the 9th support plate were required and illustrated in this paper. They are all the areas that can be allowed to be inspected within the structure of CPR1000 steam generator. For every method, principle, equipment, inspection feedback and some inspection results were described. In addition, a new eddy current method was also introduced to cooperate with the televisual methods mentioned above to know the overall sludge. This is a new tendency of estimation of steam generator's healthiness.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121809382","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}
{"title":"Research on Modern Design Technology of the Recuperator Combined With Neural Network","authors":"X. Gu, Liu Yang, Yadong Xu, Yan Zou","doi":"10.1145/3351917.3351945","DOIUrl":"https://doi.org/10.1145/3351917.3351945","url":null,"abstract":"The traditional recuperator design process was cumbersome and inefficient. In order to improve the design efficiency of the recuperator, the modern design methods were introduced into the design process of the recuperator. Aiming at the problem of solving the empirical parameters in the recuperator design, the modern design technology of the recuperator combined with neural network was put forward. The past similar cases were extracted through case-based reasoning as training samples of neural network. The prediction of empirical parameters was performed by using neural network, and the solution of calculation parameters was realized by formula. On this basis, the design result was output in the form of a recuperator parametric model. Finally, the feasibility and effectiveness of the proposed method were demonstrated by taking the design of a typical single-cylinder recuperator as an example.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"312 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116354218","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}
{"title":"Applying a Bayesian Stackelberg game to secure infrastructure system: from a complex network perspective","authors":"Xueqiang Gu, Chengyi Zeng, Fengtao Xiang","doi":"10.1145/3351917.3351924","DOIUrl":"https://doi.org/10.1145/3351917.3351924","url":null,"abstract":"Protecting critical infrastructure is a challenging task for security agencies all around the world, which is exacerbated by terrorism. Many infrastructures have network characteristics, such as transportation and communication systems. Therefore, it is necessary to study them from the perspective of network science. Game theory provides a suitable theoretical tool for the study of attack-defense confrontation between rational agents. Sequential game, which is more in line with the actual situation, can better analyze the confrontation in infrastructure protection. Previous models which combine network science with game theory only consider the attacker as a single type. However, in the real world, accurate information about the type of the attacker is not always available for the defender. In this paper, we apply Bayesian Stackelberg game to model the attack-defense confrontation in the case of uncertain attacker type.","PeriodicalId":367885,"journal":{"name":"Proceedings of the 2019 4th International Conference on Automation, Control and Robotics Engineering","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126942741","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}