Affordance-based reasoning for robotics

Humans are able to come up with plans to achieve their goals, and to adapt them to changes in their environment, finding fixes, alternatives and taking advantages of opportunities without much deliberation.  Despite decades of research, artificial agents, such as robots, are not as robust or as flexible.  If we look at how we manage to get things done despite the ever-changing environments and our own lack of omniscience we find that this is most often accomplished by making substitutions for missing or unavailable objects and making assumptions about objects for which we have limited information. Enabling service robots, operating in domestic environments to use these two techniques to support human users is the aim of the work of doctoral student Iman Awaad.