Perceptual System of a Mobile Robot for Autonomous Adaptation to Environmental Changes

In the “ultra-smart society”, which aims for symbiosis between humans and robots, mobile robots that can move freely in a variety of environments are expected. However, the appropriate parameters for any navigation method depend on the characteristics of the environment and often need to be adjusted to the environment in which it is implemented. Especially in dynamic environments that include pedestrians, avoidance is difficult and it cannot be handled only by adjusting parameters. Therefore, we propose a perceptual system for a mobile robot that can autonomously adapt to environmental changes by adjusting internal parameters based on perceptual information obtained by the robot in environments with multiple different characteristics, such as a space where many pedestrians freely pass by and a complex space with many obstacles.