Host: The Japanese Society for Artificial Intelligence
Name : The 36th Annual Conference of the Japanese Society for Artificial Intelligence
Number : 36
Location : [in Japanese]
Date : June 14, 2022 - June 17, 2022
Appropriate mental tension is necessary for maintaining concentration in tasks. In this study, we considered that tension has both positive and negative effects on performance and motivation in tasks, and aimed to investigate how to maintain concentration on a task by dynamically adjusting tension according to the situation in the task. For this, we took an approach in which the agent maintains an appropriate tension state by dynamically switching between arousal and relaxation of tension depending on the state of the person or task in human-agent interaction. We compared two types of agents in a darts task, with and without dynamic adjustment, to investigate whether task engagement of the participant would be improved. Experimental results showed that when a dynamic adjustment agent intervened, mental workload increased while participant's confidence in the task improved. This suggests that the proposed dynamic adjustment method provided appropriate tension control and helped improve task engagement.