Understanding a public environment via continuous robot observations

This paper presents a study on a point cloud analysis captured by a robot navigating in a shopping mall environment. It investigates the type and how much information the robot could extract from the environment. For this purpose, information regarding environmental changes and the number of people in shops was extracted and analyzed. First, the robot was manually controlled to collect data in a typical shopping mall having different types of shops and a food court. As the robot navigated thoroughly around the environment, seven data recordings of data obtained from various onboard sensors were recorded during afternoon hours over three consecutive days. We built a composite map by overlaying 3D point clouds for each recording sharing the same coordinate frame, which reveals the changes in the environment’s static objects. The number of humans at each shop in each recording was computed using a human tracker. Then, we computed a fourteen-dimensional vector for each shop: seven dimensions for environmental changes and seven for human density. Experimental results show that the environmental changes and the human density at each shop are consistent with the visual changes that occurred in the shops and the number of people who visited the shops. Correlation analysis was done among shop changes, shop open space, and human density where results suggest that change in shop configurations are often done in smaller shops and shops with larger open space tend to attract larger number of customers. Finally, information extracted from shops was used to categorize the shops according to similarity.