-
Notifications
You must be signed in to change notification settings - Fork 15
Baseline
The Baseline of an agent is defined as a set of fixed parameters (Expressivity Parameters) that represent the agent’s general, underlying behavior tendencies. It is a static global parameter.
A Baseline (or Dynamicline) is a list of modalities. A modality is composed of a preference value and a list of expressivity parameters.
We report two examples of Baseline. The first represents an agent that has a tendency to equally use its modalities and that is highly activated on each modality:
Lines 2, 11 and 20 define the modality preference, while lines 03-07, 12-16 and 21-25 contain the values of the expressivity parameters for each modality.
The Baseline below instead refers to an agent which is less active. This can be deduced from the OAC parameter for each modality: they are all equal to 0.2 which is quite a low value. Moreover, the agent’s expressivity is different: movements are more contracted (the SPC parameter is lower on each modality), slower (TMP is lower), smoother (FLD is higher), weaker (PWR is lower).
The Baseline .XML files are stored in the folder <GRETA_DIR>/bin/BehaviorPlanner/Baseline/
.
Below an example of a generic baseline:
In the Baseline the expressivity parameters are specified for each type of non-verbal behavior.
The Baseline used for each character is specified in the character .ini file (in the folder <GRETA_DIR>/bin/Common/Data/characters/
). In these files there is an attribute BASELINE that has the path of the file took as baseline. You can change the value of this attribute with the path of the baseline file that you want to use.
If you change the value of this attribute when the platform is running, to see the modification you should stop and restart the platform.
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