Dialog Managers are logic components responsible for the state and flow of a conversation between agents. This data flow could be between Human-Machine agents (interaction Human-Robots or Human-Virtual Agents), or Machine-Machine agents.
In the +i Project is defined a typical architecture for a Dialog Manager based on a Finite-state machine component. This FSM has been created using the SCXML standard that has been used for several types of conversation modelling between Human and virtual Agent, e.g. on Domotic applications or automatic spoken menus.
This is a basic example of a scxml schema:
<scxml xmlns="http://www.w3.org/2005/07/scxml" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.w3.org/2005/07/scxml http://www.w3.org/2011/04/SCXML/scxml.xsd" version="1.0" datamodel="python"> <final id="hello"> <onentry> <log expr="'hello world'" /> </onentry> </final> </scxml>
This is a state-flow graph related to the +i Project that describes the FSM transitions from a state to a new one:
Home - Developmental AI
Developmental AI is a new branch of AI that aims to program a minimal initial system able to develop its intelligence by itself. If implemented in a robot, it will initially behave like a newborn baby, then it will become increasingly intelligent as it interacts with the world.
In this video, part of the IDEAL MOOC of the Lyon University, you can see how developmental virtual agents as sharks, generate natural learning behaviors such as playing together and exploring a dynamic and imprecise environment.