Figure: Relationship of Work Packages
The iterative working procedure proposed is considered the most effective mean to cope with the enormous variety of the home environments. The R&D approach needs to be driven by the scenario and its continuous evaluation. Only this will lead to a more and more refined and finally complete list of requirements and robot capabilities. It is not thought feasible to achieve this in one step or jump. The iterations are the mean to continuously learn about the more and more complex problems and to progress towards the fulfilment of the objectives as given in Section B.1.
As a consequence we chose the loop structure of the WPs. The milestones mirror this approach by proposing three more and more demanding scenarios (note that the CoSy project, specifically A. Sloman, made a similar proposition to develop along refining the scenario).
M12 -> Prototype of sizeable platform coping with basic room and floor types and first table classification,
M24 -> Room layout learned by “showing the robot around”, classify main types of furniture, and then safely navigation in the home, and
M36 -> Platforms learn four homes and safely navigate to each room and ten annotated pieces of furniture.