Behavior-based search of human by an autonomous indoor mobile robot in simulation

The paper focuses on the development of a behavior-based strategy for an indoor autonomous mobile robot to find an elderly person living alone in an unstructured home environment. A perception of presence of human being in different rooms at different times of the day is maintained. Based on this perception, the estimation of possible locations of a person is carried out using Markov decision process. The implemented methodology mainly focuses on the two criteria for searching the person, namely distance to the destination and the probability of finding the person at that location. It also takes into account the last known position of the human being for the final estimation of the possible location. The robot navigates autonomously to the desired location by planning a path and avoiding the obstacles in the way. Upon reaching the destination, the process of detecting the human being in the surrounding environment is carried out. In order to validate all aspects of the robotic behavior over a longer period of time, prior to be used in an elderly care environment, a simulated environment resembling the real home apartment has been created. To make the simulation more realistic, an animated human character has also been developed which walks in to different rooms and exhibit different postures during its movements. The promising results from the 3D simulation show the effectiveness of the developed methodology.