-
Notifications
You must be signed in to change notification settings - Fork 15
TopicPlanner
The topic planner allows adapting the (sub)topics of an interaction in real-time to the engagement of the user. For a detailed explanation see the thesis of Nadine.
The topic planner is originally made for a museum context (project A1:1) where each topic corresponds to the discussion of an artwork. Each subtopic correspond to an artwork's characteristic.
To use the module, in Greta's modular the TopicPlanner should be connected to the DiscoPlanner AND the other way around (in 2 directions). The engagement of the user can be manually entered by clicking on the module (an unlimited number of times, at any moment during the ongoing interaction). Configurations of the topic planner can be set if you right-click on the module.
The topic planner uses a disco scenario that it adapts on the fly during the interaction. An example of such an adaptable disco scenario is <GRETA_DIR>/bin/Projects/A11/DiscoScenarios/D4G/TopicPlannerExample.xml
. New scenarios should follow this structure. The scenario should be loaded by the Disco Planner module.
To add a potential topic of the interaction (= e.g. museum object):
- Add object (=topic) to XML file that lists all objects, as in
<GRETA_DIR>/bin/Projects/A11/ParameterFiles/MuseumObjectsPreferencesEval.xml
- Add object's characteristics (=subtopics) to XML files that list object characteristics, as in
<GRETA_DIR>/bin/Projects/A11/ParameterFiles/PeriodsSimilaritiesPreferencesEval.xml
- Make sure that XML files and their entries are parsed by the topic planner in greta.auxiliary.topicplanner.data files
- Make FMLs (agent behaviour) and add disco tasks in disco scenario to realise (sub)topics.
Advanced
- Generating New Facial expressions
- Generating New Gestures
- Generating new Hand configurations
- Torso Editor Interface
- Creating an Instance for Interaction
- Create a new virtual character
- Creating a Greta Module in Java
- Modular Application
- Basic Configuration
- Signal
- Feedbacks
- From text to FML
- Expressivity Parameters
- Text-to-speech, TTS
-
AUs from external sources
-
Large language model (LLM)
-
Automatic speech recognition (ASR)
-
Extentions
-
Integration examples
Nothing to show here