MAP GENERATION BY COOPERATIVE LOW-COST ROBOTS IN STRUCTURED UNKNOWN ENVIRONMENTS

In this paper we present some results obtained with a troupe of low-co st robots designed to cooperatively explore unknown structured orthogo nal environments. In order to improve the covering of the explored zon e the robots show different behaviours (routine, normal and anxious) a nd cooperate by transferring each other the perceived environment when they meet; therefore, not all the information of the non-returning ro bots is lost provided that they had encountered robots that safely ret urned. The returning robots deliver to a host their perceived and comm unicated (by other robots) partial maps and the host incrementally gen erates the most plausible map of the environment. To perform the map g eneration, a fusion, completion and alignment process of the partial m aps, based on fuzzy techniques, has been developed.