In theory, Log-Periodic Antenna (LPA) is a linearly polarized antenna with frequency independent properties on the input impedance and gain patterns. Owing to these characteristics, LPA has gained research interests a...In theory, Log-Periodic Antenna (LPA) is a linearly polarized antenna with frequency independent properties on the input impedance and gain patterns. Owing to these characteristics, LPA has gained research interests and been employed for many wideband applications. A Printed Log-Periodic Dipole Antenna (PLPDA) with multiple notched bands is proposed for Ultra-WideBand (UWB) applications. An antenna with the notched frequencies of 1.03 GHz, 1.28 GHz, 1.72 GHz, 2.24 GHz and 2.51 GHz is designed, fabricated, and measured. An antenna model was established on the substrate of FR4 and feed by a stripline. The simulation results show that the antenna can achieve an impendence wide bandwidth from 0.89 to 2.58 GHz with return loss less than -10 dB and exhibit stable antenna gain. Furthermore, the measurement result is better consistent with simulation result.展开更多
Robot learning in unstructured environments has been proved to be an extremely challenging problem, mainly because of many uncertainties always present in the real world. Human beings, on the other hand, seem to cope ...Robot learning in unstructured environments has been proved to be an extremely challenging problem, mainly because of many uncertainties always present in the real world. Human beings, on the other hand, seem to cope very well with uncertain and unpredictable environments, often relying on perception-based information. Furthermore, humans beings can also utilize perceptions to guide their learning on those parts of the perception-action space that are actually relevant to the task. Therefore, we conduct a research aimed at improving robot learning through the incorporation of both perception-based and measurement-based information. For this reason, a fuzzy reinforcement learning (FRL) agent is proposed in this paper. Based on a neural-fuzzy architecture, different kinds of information can be incorporated into the FRL agent to initialise its action network, critic network and evaluation feedback module so as to accelerate its learning. By making use of the global optimisation capability of GAs (genetic algorithms), a GA-based FRL (GAFRL) agent is presented to solve the local minima problem in traditional actor-critic reinforcement learning. On the other hand, with the prediction capability of the critic network, GAs can perform a more effective global search. Different GAFRL agents are constructed and verified by using the simulation model of a physical biped robot. The simulation analysis shows that the biped learning rate for dynamic balance can be improved by incorporating perception-based information on biped balancing and walking evaluation. The biped robot can find its application in ocean exploration, detection or sea rescue activity, as well as military maritime activity.展开更多
In the process of Chinas social and economic sustainable development, the environmental pollution in Chinas cities is also gradually aggravating. Among all types of pollution, air pollution has a greater impact on urb...In the process of Chinas social and economic sustainable development, the environmental pollution in Chinas cities is also gradually aggravating. Among all types of pollution, air pollution has a greater impact on urban residents. Since 2015, smog has been continuously produced in cities of our country, which is also a manifestation of air pollution. Air pollution will not only adversely affect the normal production and life of urban residents, but also lead to the slowdown of economic development in our country. Based on this, people need to explore how to manage the urban ecological environment in the process of governance of urban internal air pollution application strategy.展开更多
文摘In theory, Log-Periodic Antenna (LPA) is a linearly polarized antenna with frequency independent properties on the input impedance and gain patterns. Owing to these characteristics, LPA has gained research interests and been employed for many wideband applications. A Printed Log-Periodic Dipole Antenna (PLPDA) with multiple notched bands is proposed for Ultra-WideBand (UWB) applications. An antenna with the notched frequencies of 1.03 GHz, 1.28 GHz, 1.72 GHz, 2.24 GHz and 2.51 GHz is designed, fabricated, and measured. An antenna model was established on the substrate of FR4 and feed by a stripline. The simulation results show that the antenna can achieve an impendence wide bandwidth from 0.89 to 2.58 GHz with return loss less than -10 dB and exhibit stable antenna gain. Furthermore, the measurement result is better consistent with simulation result.
文摘Robot learning in unstructured environments has been proved to be an extremely challenging problem, mainly because of many uncertainties always present in the real world. Human beings, on the other hand, seem to cope very well with uncertain and unpredictable environments, often relying on perception-based information. Furthermore, humans beings can also utilize perceptions to guide their learning on those parts of the perception-action space that are actually relevant to the task. Therefore, we conduct a research aimed at improving robot learning through the incorporation of both perception-based and measurement-based information. For this reason, a fuzzy reinforcement learning (FRL) agent is proposed in this paper. Based on a neural-fuzzy architecture, different kinds of information can be incorporated into the FRL agent to initialise its action network, critic network and evaluation feedback module so as to accelerate its learning. By making use of the global optimisation capability of GAs (genetic algorithms), a GA-based FRL (GAFRL) agent is presented to solve the local minima problem in traditional actor-critic reinforcement learning. On the other hand, with the prediction capability of the critic network, GAs can perform a more effective global search. Different GAFRL agents are constructed and verified by using the simulation model of a physical biped robot. The simulation analysis shows that the biped learning rate for dynamic balance can be improved by incorporating perception-based information on biped balancing and walking evaluation. The biped robot can find its application in ocean exploration, detection or sea rescue activity, as well as military maritime activity.
文摘In the process of Chinas social and economic sustainable development, the environmental pollution in Chinas cities is also gradually aggravating. Among all types of pollution, air pollution has a greater impact on urban residents. Since 2015, smog has been continuously produced in cities of our country, which is also a manifestation of air pollution. Air pollution will not only adversely affect the normal production and life of urban residents, but also lead to the slowdown of economic development in our country. Based on this, people need to explore how to manage the urban ecological environment in the process of governance of urban internal air pollution application strategy.
