Natural Language Interaction With ISA Handling, Consequence And Basic Social Reasoning
Here we see the DIARC architecture controlling a Nao robot in a simple natural language based interaction. The robot is able to obey both literal and non-literal directives. It is also able to appropriately reject commands based on reasoning regarding action effects. In this case, it rejects commands that can possibly result in harm to itself (walking into solid objects). It also rejects directives that it is not obligated to do based on the relative social relationship between the robot and user.