Xutong Li - Academia.edu (original) (raw)
Uploads
Papers by Xutong Li
2019 Chinese Control And Decision Conference (CCDC), 2019
The paper introduces and adopts an improved and unscented kalman filtering algorithm to track mov... more The paper introduces and adopts an improved and unscented kalman filtering algorithm to track moving targets. For issues like large calculation amount, unfavorable real-time performance and non-local effects of samples of this algorithm, scale factors are adaptive selected to simplex sampling with minimum skewness. According to simulation results, on one hand, introduction of the algorithm can reduce calculation amount and increase arithmetic speed. On the other hand, it can decrease errors of non-local effects and high order, and enhance the accuracy of target tracking.
2019 Chinese Control And Decision Conference (CCDC), 2019
The purpose of applying the artificial bee colony algorithm to the traveling salesman problems pu... more The purpose of applying the artificial bee colony algorithm to the traveling salesman problems pursuant to its principle is to find out solutions to the traveling salesman problems of different cities and use local search strategy to effectively make such issues less complicated, so as to optimize the path. It is necessary to analyze the correlation between the artificial bee colony algorithm and relevant algorithm parameters and the number of cities. Simulate result denotes the artificial bee colony algorithm can be applied to settle the problems of traveling salesman and is much reliable in effectiveness, usability and researchability.
International Journal of Control, Automation and Systems, 2020
In this paper, a control algorithm based on Advantage Actor-Critic for the classical inverted pen... more In this paper, a control algorithm based on Advantage Actor-Critic for the classical inverted pendulum system has been proposed. To enrich the observed states which are used to control, a CNN feature-based state is proposed. The direct control and the indirect control algorithms are introduced to address different control situations, such as the situation which only physical states like angle, velocity, etc. provided or the situation which only the indirect states provided like images, etc. A comparison experiment between the direct control and the indirect control algorithms based on the Advantage Actor-Critic has been evaluated. Besides, the comparison experiment with the Deep Q-Network algorithm has been performed. The experiment results show that the proposed method achieves comparable performance with the PID control algorithm and better than the Deep Q-Network based algorithm.
2019 Chinese Control And Decision Conference (CCDC), 2019
The paper introduces and adopts an improved and unscented kalman filtering algorithm to track mov... more The paper introduces and adopts an improved and unscented kalman filtering algorithm to track moving targets. For issues like large calculation amount, unfavorable real-time performance and non-local effects of samples of this algorithm, scale factors are adaptive selected to simplex sampling with minimum skewness. According to simulation results, on one hand, introduction of the algorithm can reduce calculation amount and increase arithmetic speed. On the other hand, it can decrease errors of non-local effects and high order, and enhance the accuracy of target tracking.
2019 Chinese Control And Decision Conference (CCDC), 2019
The purpose of applying the artificial bee colony algorithm to the traveling salesman problems pu... more The purpose of applying the artificial bee colony algorithm to the traveling salesman problems pursuant to its principle is to find out solutions to the traveling salesman problems of different cities and use local search strategy to effectively make such issues less complicated, so as to optimize the path. It is necessary to analyze the correlation between the artificial bee colony algorithm and relevant algorithm parameters and the number of cities. Simulate result denotes the artificial bee colony algorithm can be applied to settle the problems of traveling salesman and is much reliable in effectiveness, usability and researchability.
International Journal of Control, Automation and Systems, 2020
In this paper, a control algorithm based on Advantage Actor-Critic for the classical inverted pen... more In this paper, a control algorithm based on Advantage Actor-Critic for the classical inverted pendulum system has been proposed. To enrich the observed states which are used to control, a CNN feature-based state is proposed. The direct control and the indirect control algorithms are introduced to address different control situations, such as the situation which only physical states like angle, velocity, etc. provided or the situation which only the indirect states provided like images, etc. A comparison experiment between the direct control and the indirect control algorithms based on the Advantage Actor-Critic has been evaluated. Besides, the comparison experiment with the Deep Q-Network algorithm has been performed. The experiment results show that the proposed method achieves comparable performance with the PID control algorithm and better than the Deep Q-Network based algorithm.