Abstract
Human-robot interaction is a complex field of robotics inwhich robots are required to deal with different challenging issues. Amongother skills, HRI-capable robots need to generate plans taking humansinto account. To achieve this robots require sufficiently efficient datastructures and rich information about their environment as well as abouthumans and their abilities. An additional requirement when robots aresupposed to actively find and classify objects is the capability of reason-ing about the creation and retyping of the symbols corresponding to theobjects as a result of the actions of their plans. This paper describes howthese requirements can be met using a combination of dynamic graph-like world models and a planning system based on graph-rewriting rules.To demonstrate how the approach can be applied, the paper builds upona robot butler use-case, describing how its world model is structured andits most relevant planning rules. Qualitative and quantitative experimen-tal results are also provided.
| Original language | English |
|---|---|
| Title of host publication | International Workshop on Recognition and Action for Scene Understanding |
| Pages | 195-208 |
| Publication status | Published - 28 Oct 2015 |