Abstract
Recently, the activity of a robot in dynamic environments where a person lies is expected. When the robot works in dynamic environments, the robot has to achieve a path planning, considering human movements. However, it is difficult to acquire the information on dynamic environments or human movements by only using the sensor mounted on the robot. In this research, the sensors are distributed in the environmental side, and human's walking route is observed. Then, we propose "Human Frequency Map (HFM)" that is a grid map based on the observed human position and frequency in a term. By using the HFM and the distributed sensor data, in addition to the current position of human the possibility of encountering human and the width of passage can be considered in a path planning. In this paper, a path planning was simulated by using the observed human position data, and the usefulness of the path planning was shown with a HFM in dynamic environments.
