{"title":"Mobile robot navigation method based on improved Q-learning algorithm","authors":"Zhiyong Tan, Tao Wang, Yao Yu","doi":"10.1109/YAC53711.2021.9486613","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486613","url":null,"abstract":"In recent years, autonomous navigation of mobile robots has become one of the hot topics in research. An improved Q-learning method (IQL) combining action selection strategy and Q function update method is proposed. A new exploration strategy of staged $varepsilon$ greedy exploration is used in IQL. In addition, the idea of backtracking is used to update the Q value to speed up the convergence speed. Experiments conducted in a grid environment show that compared with the classic algorithm, the algorithm converges faster and the program execution time is shorter.","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126182487","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":"Robotic Path Planning Based on Episodic Memory Fusion","authors":"Junyi Wu, Haidong Xu, Chong-hao Wu, Shumei Yu, Rongchuan Sun, Lining Sun","doi":"10.1109/YAC53711.2021.9486489","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486489","url":null,"abstract":"Episodic memory provides a mechanism for recalling past experience, which can be used for path planning in complex environments. This paper describes a path planning method based on memory fusion that combines an episodic memory models with the potential path detection network. In traditional path planning methods based on the episodic memory model, paths were planned based on the trajectory that the mobile robot has experienced in the environment, ignoring the surrounding potential paths. Therefore, the planned path is not necessarily globally optimal. In response to this problem, we proposed a path detection network to find potential safe paths in the environment. Our experimental results demonstrated that a better path can be found by fusing the potential path into the original episodic-cognitive map from the perspective of planned path length and number of turns.","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129775938","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":"Design of Multi-UAVs Control Platform for Control Algorithm Experiments","authors":"Xi Zhao","doi":"10.1109/YAC53711.2021.9486646","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486646","url":null,"abstract":"We build a multi-UAVs control platform that can be used for verification of multi-UAVs control algorithm and also for the construction of multi-UAVs cooperation system. The ground station program, using the improved named pipeline to connect the multi-process, supports the control and test functions of multi-UAVs stably. Through the reasonable design of the communication link between multiple processes and the proper simplification of the communication protocol flow, we make up for the disadvantages such as high process creation cost and low communication efficiency. At the same time, an experimental platform for embeddable multi-UAVs control algorithm is built. The stability and usability of the platform have been verified by simulation and real machine experiments and the observation of multi-UAVs and a single UAV has basically reached the verification requirements of the control algorithm.","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127052214","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":"Finite Time Stability of Octonion-Valued Neural Networks With Delays","authors":"Jingzhuo Wang, Xiwei Liu","doi":"10.1109/YAC53711.2021.9486459","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486459","url":null,"abstract":"In this paper, we study the finite time stability (FTS) of octonion-valued neural networks (OVNNs) with unbounded asynchronous time delays (UADs) by adopting two-phases-method (2PM) and 2-norm. Without employing traditional decomposition method or supposing the terms with delays are bounded, and utilizing a new sign function for octonion, we design the controller with only two terms only depending on the present system state, which can cut down redundancy in calculation and reasoning, and the controller would be much easier to realize in practical situations. Moreover, the adaptive FTS of OVNNs is also realized. Finally, two numerical examples are also given.","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121335575","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":"A Parallel Algorithm for Solving General Colored Traveling Salesman Problems","authors":"Penghui Ding, Xiangping Xu, Jun Li","doi":"10.1109/YAC53711.2021.9486537","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486537","url":null,"abstract":"A colored traveling salesman problem (CTSP) is a generalization of the well-known multiple traveling salesman problem. It utilizes colors to differentiate the accessibility of its cities to ward its salesmen. All the existing algorithms for solving CTSP are serial ones. This paper presents for the first time a parallel algorithm framework for solving general CTSP. Then, an improved variable neighborhood search algorithm is proposed by using this algorithm framework. Finally, extensive simulations are conducted in various test cases. The results show that the algorithm proposed is superior to the compared serial algorithms in terms of convergence and solution quality.","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121434016","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":"Attitude control for quadrotor UAV with dead zone and external disturbance","authors":"Chao Chen, N. Duan, Shuo Li, Zhizheng Xu","doi":"10.1109/YAC53711.2021.9486495","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486495","url":null,"abstract":"This paper investigates adaptive attitude control for quadrotor unmanned aerial vehicle (UAV) with dead zone and external disturbance. A attitude controller is designed based on backstepping, and adaptive law is designed to compensate the influence of input dead zone and external disturbance. The designed controller guarantees that attitude angle of quadrotor UAV can trace the desired attitude angle. Finally, simulation results have demonstrated the effectiveness of the designed scheme.","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116125267","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":"Reactive Power Control of Autonomous Wind-Diesel Hybrid Power System via Online Actor-Critic Algorithm","authors":"Nan Xu, Tianchun Xiang, Tianhao Wang, C. Mu","doi":"10.1109/YAC53711.2021.9486564","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486564","url":null,"abstract":"This thesis is concerned about the designing of the additional controller based on the online synchronization policy iteration algorithm for the typical autonomous wind-diesel hybrid power system with known dynamics. Considering the reactive power requirement of the power system, the static voltage automatic regulator is installed in parallel to supply reactive power. The designed additional controller has been verified on the strength of step disturbance and random disturbance in load reactive power. Transient responses have been shown the effectiveness of the proposed adaptive algorithm.","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123863316","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":"Robust Feature Matching Based on Adaptive ORB for Vision-based Robot Navigation","authors":"Chao Sun, Nianzu Qiao, Jia Sun","doi":"10.1109/YAC53711.2021.9486546","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486546","url":null,"abstract":"Feature matching technology is one important part for a vision navigation system to estimate robot pose according to natural landmarks. However, it is difficult for the existing techniques to solve the dilemma between accuracy, and efficiency, as well as the robustness under a complex workspace involving non-uniform illumination and texture-less. To address this issue, this paper proposes a novel feature matching algorithm that is robust, accuracy, and relatively fast in complex workspaces. The main idea of the proposed method is a multi-stage matching module consisting of K Nearest Neighbor, Threshold Filtering, Eigenvector Norm, and Random Sample Consensus (KNN-TF-EN-RANSAC) to eliminate mismatches for retaining the optimal matches. Meanwhile, the proposed matching module is computed on adaptive Oriented fast and Rotated Brief (ORB) features extracted by a variable extraction radius. Finally, extensive experiments demonstrate the robustness, accuracy, and real-time performance of the proposed method.","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131109652","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}
Kaiwen Jiang, Yixin Su, Zhiwen Leng, Zhen Wang, Lan Chen, Gang Li
{"title":"Submarine Multi-dimensional Magnetic Field Compensation System Based on Improved Whale Optimization Algorithm","authors":"Kaiwen Jiang, Yixin Su, Zhiwen Leng, Zhen Wang, Lan Chen, Gang Li","doi":"10.1109/YAC53711.2021.9486483","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486483","url":null,"abstract":"In order to avoid the spatial magnetic field distortion caused by the submarine induced magnetic field, the real-time degaussing current is input in the longitudinal, transverse and vertical directions inside the submarine, and the nine components of Ziz, Yiz, Xiz, etc. on the x, y and z three-direction windings are magnetically applied Compensation to improve the magnetic protection capability of the submarine. Aiming at the high coupling problem when the unidirectional winding is used to compensate the unidirectional component of the magnetic field, this paper proposes a new whale optimization algorithm based on adaptive weighting and simulated annealing strategy. The algorithm uses a time-varying function to control the inertia weight coefficient, and adjusts the adaptive weight to improve the convergence speed of the algorithm; The simulated annealing strategy is introduced to accept poor solutions with a certain probability, and the algorithm's global optimization capability is enhanced. Flux 3D is used to perform high-precision finite element simulation on the three-dimensional space model of the submarine, and the magnetic field distribution and change law of the three-component submarine space are studied, and the three-component magnetic field compensation curve of the submarine's longitudinal, transverse and vertical windings is obtained. Building a real-scale simulation platform to verify the accuracy of the multi-dimensional magnetic field compensation results. The results show that the improved whale optimization algorithm has a magnetic field compensation effect of more than 90% on the Ziz, Yiz, and Xiz components of the vertical winding, and it has a strong global search ability and fast convergence speed, which proves the effectiveness of the algorithm in the submarine magnetic field compensation.","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131155461","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":"Optimal Configuration Of An Island Microgrid Considering Demand Response Strategy","authors":"Hao Hao, Baole Huang, Pengcheng Ji","doi":"10.1109/YAC53711.2021.9486661","DOIUrl":"https://doi.org/10.1109/YAC53711.2021.9486661","url":null,"abstract":"In this paper, a method of island microgrid capacity optimal allocation considering demand response strategy is proposed. Aiming at the problem that traditional optimization algorithm is easy to fall into local optimal solution in the process of island capacity optimal allocation, a new chaotic binary gravitational search algorithm (IBGSA) is proposed. The results show that considering the demand response strategy in the optimal allocation process can effectively reduce the investment cost of the system, maintain the reliability of power supply, and increase the consumption of renewable energy","PeriodicalId":107254,"journal":{"name":"2021 36th Youth Academic Annual Conference of Chinese Association of Automation (YAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131217871","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}