EVA: Generating Emotional Behavior of Virtual Agents using Expressive Features of Gait and Gaze

Abstract

We present a novel, real-time algorithm, EVA, for generating virtual agents with various perceived emotions. Our approach is based on using Expressive Features of gaze and gait to convey emotions corresponding to happy, sad, angry, or neutral. We precompute a data-driven mapping between gaits and their perceived emotions. EVA uses this gait emotion association at runtime to generate appropriate walking styles in terms of gaits and gaze. Using the EVA algorithm, we can simulate gaits and gazing behaviors of hundreds of virtual agents in real-time with known emotional characteristics. We have evaluated the benefits in different multi-agent VR simulation environments. Our studies suggest that the use of expressive features corresponding to gait and gaze can considerably increase the sense of presence in scenarios with multiple virtual agents.

Generic Body Expression Recognition Based on Synthesis of Realistic Neutral Motion

“…However, considering only a sub-part of channels such as only the face of a person or the posture stays an important way to improve knowledge of the whole domain since multi-modal approaches generally combine specific approaches dedicated to a single channel [15]. Moreover, the representations and descriptors designed for recognition may be extended to propose approaches for generating virtual agents with various perceived emotions [16].…”

The Impact of a Virtual Agent's Non-Verbal Emotional Expression on a User's Personal Space Preferences

“…However, as psychological studies question the reliability of emotions perceived only from facial expressions [37], more channels should be used when designing expressive VAs. Besides the facial expressions, these expressive features [35] can be body postures, gazing behaviors, and movements [6,33]. The latter option comprises gait [33] and the trajectories chosen.…”

“…Besides the facial expressions, these expressive features [35] can be body postures, gazing behaviors, and movements [6,33]. The latter option comprises gait [33] and the trajectories chosen. As our study requires specific trajectories to sample the subjects' PS preferences, we focus on the body-language.…”

Reactive Virtual Agents

“…Intelligent Virtual Agents (IVA) should be designed to perform realistic and expressive interactions [3] that convey emotions and express personalities [23,26]. These are notably expressed by humans through nonverbal behaviours in everyday interactions [8,12].…”