Olfaction is a valuable source of information about the environment that has not been su ciently exploited in mobile robotics
yet. Certainly, odor information can contribute to other sensing modalities, e.g. vision, to successfully accomplish high-level robot
activities, such as task planning or execution in human environments. This paper describes the developments carried out in the scope of the IRO project, which aims at making progress in this direction by investigating mechanisms that exploit odor information (usually coming in the form of the type of volatile and its concentration) in problems like object recognition and scene-activity understanding. A distinctive aspect of this research is the special attention paid to the role of semantics within the robot perception and decisionmaking processes. The results of the IRO project have improved the robot capabilities in terms of efciency, autonomy and usefulness.