This study proposes and develops an edge-AI-based autonomous mobile robot based on open-source software. The robot is capable of voice and object recognition; it can detect and approach an object specified by a user's voice. Because the robot is controlled by voice commands, the user can control the robot intuitively. In the present study, we used a robot operating system to facilitate the development. All functions, including voice recognition, object recognition, and motor control, were implemented in the edge AI computer based on open-source software. We conducted preliminary experiments to verify the performance of the developed system.

To alleviate social problems in agriculture such as aging and labor force shortages, automatic growth monitoring based on image measurement has been introduced to tomato cultivation in greenhouses. The overlap of leaves and fruits makes precise observations challenging. In this study, we applied context recognition to tomato growth monitoring by using a Bayesian network. The proposed method combines image recognition using convolutional networks and context recognition using Bayesian networks. It enables not only the recognition of individual tomatoes but also the evaluation of tomato plants. An accurate number of tomatoes and the condition of the stocks can be estimated based on the number of ripe and unripened tomatoes in addition to their density information. The verification experiments clarified that a more accurate number of tomatoes could be estimated than with simple tomato detection, and the stock states could also be evaluated correctly. Compared to conventional methods, the method used in this study has improved tomato decision accuracy by 23%.

As the decisions we make become increasingly influenced by suggestions from Artificial Intelligence (AI), it is important to understand how the form and the accuracy of their suggestions affect our behavior. In this study, we investigated whether our decisions were affected by the accuracy of the AI used and the form of feedback. Ten participants evaluated whether facial images were real or fake under four conditions, namely, with suggestions given by a high or low accuracy AI and with or without the AI confidence level provided. The results suggest that, in the case of a high accuracy AI, the concordance rate between the decisions the participants made and the suggestions from AI were higher when confidence levels were provided compared to when the confidence levels were not show. However, in the case of a low accuracy AI, the concordance rate was lower when confidence levels were shown. Additionally, the accuracy of participant's answers increased when confidence level was provided, for both the high accuracy and low accuracy AI. In conclusion, providing confidence level information alongside AI suggestions may change the decisions made by human and the effects may be different depending on the confidence level of the AI.

Puyo Puyo is a kind of falling block puzzle game. The purpose of the game is to operate the falling blocks and to form a chain, but it is classified as an incomplete information game because the information about the blocks that will fall in the future is not disclosed to the players. As a Puyo Puyo AI, Mayah was proposed. However, Mayah is based on exhaustive search. Furthermore, due to the short thinking time per move, we must develop more efficient estimation method. To improve the search speed, in this paper, we propose Puyo Puyo AI using Monte Carlo tree search.