Cognitive Architectures for Virtual Characters

SHARESPACE utilizes Virtual Characters (VCs) to enable embodied collaboration and interaction in Social Hybrid Spaces (SHS). Up to this point, interaction in digital spaces is nowhere near as seamless as real-life communication due to the heavy loss of many physical subtleties. The academic research in SHARESPACE aims to identify social cues in movements (sensorimotor primitives), and wishes to explore if digital communication can be improved if these sensorimotor primitives are amplified by utilizing AI technology.

SHARESPACE utilizes three different categories of Virtual Characters, depending on their level of autonomization (L1, L2, L3). Each one is partially or fully driven by an AI-driven Cognitive Architecture (CA): each displaying different levels of intelligence and autonomy and level of movement amplification. The levels of autonomization are:

• L0: A human in a physical space.
• L1 (VC): These VCs are simple representations of the user’s body in the virtual world. They directly replicate the user’s movement without autonomy or amplification.
• L2 (Semi-autonomous VC): These VCs are more intelligent than L1 avatars. They can readout and understand their users’ movements and perform amplification of motion when they identify relevant sensorimotor primitives. The goal of the amplification process is to make the social cues more readable for others in the SHS. These VCs still lack autonomy and they rely on the signals given by the user. 
• L3 (Autonomous VC): These VCs are the most intelligent and autonomous. They can readout and understand other VCs’ movements. They can also learn and adapt to their environment to make their own decisions. The key objective of these kinds of VC is to perform a given task to improve human interactions in XR spaces. 

The level of intelligence and autonomy of a Virtual Character can have a significant impact on the user’s experience. L1 avatars are the most basic, but they can be useful for simple tasks. L2 VCs are more engaging, and are better suited to achieve a better transmission of intentions through movements in VR. Finally, L3 VCs offer the potential for a truly lifelike virtual experience with completely AI driven characters which can engage in group tasks and improve synchronization between individuals.