http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Robot Search Path Planning Method Based on Prioritized Deep Reinforcement Learning
Yanglong Liu,Zuguo Chen,Ming Lu,Chaoyang Chen,Xuzhuo Zhang,Yonggang Li 제어·로봇·시스템학회 2022 International Journal of Control, Automation, and Vol.20 No.8
The path planning process of the robot relies too much on environmental information, which makes it difficult to obtain the optimal search path when the search and rescue tasks are carried out in a complex postdisaster environment. Thus, a path planning method based on prioritized deep reinforcement learning is proposed in the paper. The core idea of the method is that the robot first builds an environment mathematical model based on the obtained information through the sensors. Then, to make the robot can obtain the optimal search policy in an extremely complex environment, the prioritized replay mechanism is used to improve deep reinforcement learning. Finally, the simulation results show that the search path planning method based on prioritized deep reinforcement learning proposed can not only improve the convergence speed of the model but also is endowed good robustness in this paper.
Yongxia Miao,Xiaohui Liu,Yanglong Guo,Yanqin Wang,Yun Guo,Guanzhong Lu 한국공업화학회 2010 Journal of Industrial and Engineering Chemistry Vol.16 No.1
The MoO3/SiO2 catalysts containing different surface molybdenum species were prepared by a sol–gel method, and the effects of the preparation condition and MoO3 loading on the surface molybdenum species and property of MoO3/SiO2 were studied. The XRD, FT-IR, UV–vis and Raman spectroscopies were used to characterize the surface molybdenum species, and temperature-programmed desorption of NH3 adsorbed on a catalyst was used to detect the surface acidic properties. The results show that, therewere the dispersed polymolybdate, a-MoO3, b-MoO3, monomeric molybdenum species and silicomolybdic acid on the MoO3/SiO2 catalyst, and their distributions and subsistence states were affected by the preparation condition and MoO3 loading. Different molybdenum species exhibit different catalytic activities for the epoxidation of propylene with cumene hydroperoxide. In the 15 wt% MoO3/SiO2 catalyst synthesized at pH 9.1 and dried appropriately, there are the small size b-MoO3 and monomeric molybdenum species that they are mainly effective catalyst components for the epoxidation of propylene. Using this catalyst, the ~100% conversion of cumene hydroperoxide and ~100% selectivity to propylene oxide can be obtained in the tert-butyl alcohol solvent at 2.6 MPa and 80 8C for 4 h.