RESUMO
Research is currently being conducted on the use of robots as human labor support technology. In particular, the service industry needs to allocate more manpower, and it will be important for robots to support people. This study focuses on using a humanoid robot as a social service robot to convey information in a shopping mall, and the types of robot behaviors were analyzed. In order to convey the information, two processes must occur. Pedestrians must stop in front of the robot, and the robot must continue the engagement with them. For the purpose of this study, three types of autonomous robot behaviors were analyzed and compared in these processes in the experiment: greeting, in-trouble, dancing behaviors. After interactions were attempted with 5,000+ pedestrians, this study revealed that the in-trouble behavior can make pedestrians stop more and stay longer. In addition, in order to evaluate the effectiveness of the robot in a real environment, the comparative results between three robot behaviors and human advertisers revealed that (1) the results of the greeting and dancing behavior are comparable to those of the humans, and (2) the performance of the in-trouble behavior in providing information tasks is higher than that of all human advertisers. These findings demonstrate that the performance of robots is comparable to that of humans in providing information tasks in a limited environment; therefore, it is expected that service robots as a labor support technology will be able to perform well in the real world.
RESUMO
The goal of this study is to propose a data driven approach method to characterize muscular activities of complex actions in sports such as golf from a lot of EMG channels. Two problems occur in a many channel measurement. The first problem is that it takes a lot of time to check the many channel data because of combinatorial explosion. The second problem is that it is difficult to understand muscle activities related with complex actions. To solve these problems, we propose an analysis method of multi EMG channels using Non-negative Matrix Factorization and adopt the method to driver swings in golf. We measured 26 EMG channels about 4 professional coaches of golf. The results show that the proposed method detected 9 muscle synergies and the activation of each synergy were mostly fitted by sigmoid curve (R2=0.85).