Abstract: The EU project DustBot addresses urban hygiene. Two types of robots were designed, the DustClean robot to autonomously clean pedestrian areas, and the DustCart robot for door-to-door garbage collection. Three prototype robots were built and equipped with electronic noses so as to enable them to collect environmental data while performing their urban hygiene tasks. Essentially, the robots act as a mobile, wireless node in a sensor network. In this paper we give an overview of the DustBot platform focusing on the Air Monitoring Module (AMM). We describe the data flow between the robots through the ubiquitous network to a gas distribution modelling server, where a gas distribution model is computed. We describe the Kernel DM+V algorithm, an approach to create statistical gas distribution models in the form of predictive mean and variance discretized onto a grid map. Finally we present and discuss results obtained with the DustBot AMM during experimental trials performed in outdoor public places: a courtyard in Pontedera, Italy and a pedestrian square in Orebro, Sweden.