This paper proposed an adaptive three-dimensional (3D) path-following control design for a robotic airship based on reinforcement learning. The airship 3D path-following control is decomposed into the altitude control and the planar path-following control, and the Markov decision process (MDP) models of the control problems are established, in which the scale of the state space is reduced by parameter simplification and coordinate transformation. To ensure the control adaptability without dependence on an accurate airship dynamic model, a Q-Learning algorithm is directly adopted for learning the action policy of actuator commands, and the controller is trained online based on actual motion. A cerebellar model articulation controller (CMAC) neural network is employed for experience generalization to accelerate the training process. Simulation results demonstrate that the proposed controllers can achieve comparable performance to the well-tuned proportion integral differential (PID) controllers and have a more intelligent decision-making ability.

BackgroundEnterocytozoon bieneusi is the most common pathogen of 14 microsporidian species infecting humans worldwide. In China, E. bieneusi has been reported in some common livestock and environmental specimens. However, no information is available on occurrence of E. bieneusi in reindeers. The objective of the present study was to detect and genotype E. bieneusi in reindeers in China, and assess the zoonotic potential.Findings125 fecal specimens were collected from wild reindeers in the northeast forest region of Great Hinggan Mountains of China. By PCR and sequencing of the internal transcribed spacer (ITS) region of the ribosomal RNA (rRNA) gene of E. bieneusi, an average infection rate of 16.8 % (21/125) was observed in reindeers. E. bieneusi was detected in two age groups: 7.7 % (3/39) in the youths (aged 1 to 2 years) and 22.2 % (18/81) in the adults (aged 3 to 8 years). Five genotypes were identified: one known genotype Peru6 (n = 6) and four novel genotypes named as CHN-RD1 (n = 12), and CHN-RD 2 to CHN-RD4 (one each). In phylogenetic analysis, all the novel genotypes together with known genotype Peru 6 were clustered into group 1.ConclusionsThis is the first report of E. bieneusi infection in reindeers, expanding the host range of E. bieneusi. The fact of genotype Peru 6 previously reported in humans and the result of all the novel genotypes falling into zoonotic group 1 suggest the possibility of E. bieneusi transmitted from reindeers to humans.

No abstract

No abstract

No abstract