For effective human-robot interaction, robots need to understand the current situation context well, but also the robots need to transfer its understanding to the human participant in efficient way. The most convenient way to deliver robot’s understanding to the human participant is that the robot expresses its understanding using voice and natural language. Recently, the artificial intelligence for video understanding and natural language process has been developed very rapidly especially based on deep learning. Thus, this paper proposes robot vision to audio description method using deep learning. The applied deep learning model is a pipeline of two deep learning models for generating natural language sentence from robot vision and generating voice from the generated natural language sentence. Also, we conduct the real robot experiment to show the effectiveness of our method in human-robot interaction.
The rate of photosynthesis (A) of leaves from 10 plant species (6 evergreen and 4 deciduous) of the family Fagaceae was measured using a portable photosynthesis analyzer, to examine which species take up CO2 most efficiently. Of the evergreen species, the photosynthetic rate of Castanopsis cuspidata var. sieboldii was highest, and remained above 82.1~106.4 μmol kg-1s-1 from July to November. Of the deciduous species, the photosynthetic rate of Quercus acutissima was higher than that of the other three species, and remained high at 83.5~116.6 μmol kg-1s-1 from September to November. The photosynthetic rate of the 10 species was positively correlated with stomatal conductance (gs) and transpiration rate (E). However, there was no correlation between photosynthetic rate and intercellular CO2 concentration (Ci), although there was a positive correlation just in three species (Q. gilva, Q. acutissima and Q. glauca). These results suggest that the CO2 fixation capacity of C. cuspidata var. sieboldii, an evergreen species, and Q. acutissima, a deciduous species, is significantly higher than that of the other species examined, and that photosynthesis is regulated by both stomatal conductance and transpiration. Therefore, C. cuspidata var. sieboldii and Q. acutissima may be valuable for the evaluation of carbon uptake in urban green spaces as well as in afforested areas.