Developing frameworks for multicharacter navigation, enabling the use of multiple heterogeneous problem domains of differing complexities for navigation in large, complex, dynamic virtual environments. ("Multi-Domain Real-time Planning in Dynamic Environments")
Exploring the effect of posture and dynamics on the perception of emotion using data from our motion capture facility. ("Effect of Posture and Dynamics on the Perception of Emotion")
Maximizing efficiency of rendering of 3D animated character crowds through an algorithm that computes discrete solutions as a pre-process, minimizing the graphics processing unit footprint and maintaining animation independence. ("Efficient rendering of animated characters through optimized per-joint impostors")
Analyzing effects of responsiveness on game players’ enjoyment, performance, and perceptions of the game, as well as players’ adaptability to delays. ("How Responsiveness Affects Players Perception in Digital Games")
Investigating the potential for an active approach to player metric collection that collects data more efficiently with less cost. ("Game-based Data Capture for Player Metrics")
Modeling sound propagation and its perception for autonomous agents in dynamic environments. ("SPREAD: Sound Propagation and Perception for Autonomous Agents in Dynamic Environments")
Creating a framework for distributing conversations among virtual embodied agents in a real-time simulation, using behavior trees so that the resulting animated conversations demonstrate reasonable variety and variability within the environmental context. ("Animating synthetic dyadic conversations with variations based on context and agent attributes")
Testing for the best approach for authoring multi-actor behaviors in crowds with diverse personalities. ("Authoring Multi-Actor Behaviors in Crowds with Diverse Personalities")
Developing a platform for designing and authoring function, purposeful human characters in a rich virtual environment that incorporates character animation, navigation, and behavior with modular interchangeable components to produce narrative scenes. ("ADAPT: The Agent Development and Prototyping Testbed")
Designing a data structure to provide an efficient mapping from key sequences to motions to improve the efficiency of using large motion data sets in real-time applications. ("Efficient Motion Retrieval in Large Motion Databases")
Identifying limitations in the representation, control, locomotion, and authoring of autonomous virtual humans that must be addressed to enter the new age of interactive virtual world applications. ("What's Next? The New Era of Autonomous Virtual Humans")
Computing predicted anomalies in crowd movement using context-sensitive crowd simulation that assesses individuals rather than assuming population-wide homogeneity. ("Pedestrian Anomaly Detection using Context-Sensitive Crowd Simulation")
Creating a framework for local path-planning and steering that can be easily extended to perform high-level behaviors based on the concept of affordances. ("Parallelized Egocentric Fields for Autonomous Navigation")
RCTA: The RCTA is a large, multi-year, multi-partner project to build effective, efficient, intelligent and collaborative human-robot teams. Our team plays two roles in this effort:
Multi-Modal Communication. The task objective is to develop a multi-modal tactical communication protocol for human-robot communication, and enable the preprocessing of raw tactical and mission relevant communication data to inform Perception and Intelligence (e.g., world model, ACT-R). Additionally, this capability will directly support mission relevant shared mental models (SMM) and contribute to all communication aspects of the capstone vision.
Dynamics of operating within a social and cultural environment. The objective of this task is to provide a real-time interactive simulation of (for example) a Middle Eastern populace exhibiting indigenous cultural factors and behaviors while interacting with a human-robot soldier team. The deliverables of this task will provide a readily authorable interactive virtual and visual test bed for soldiers and robots to experience and interact with a Middle Eastern populace and facilitate experimentation and collaboration in a visually, socially, culturally relevant setting. The results of this subtask will enable HRI to study behaviors and predictive models of HRT on realistic missions set in a virtual marketplace characteristic of the Middle East. Authoring and recording variations in the simulation will provide valuable synthetic training data for Perception research. Finally, the ability to provide an interactive populace will provide a valuable test-bed to exercise and prototype robot and team cognition and tactical capabilities. Long term goals include the use of planning methods to generate simulations with global narrative constraints and unanticipated events (user input), and introduce parameters to control culture and character psychology at the animation layer.
Parameterized Action Representation (PAR) for digital human embodied agent models
Crowd simulation
Digital human modeling software tools
Understanding the bi-directional relationships between human movement, natural languages, instructions, and communication
Archaeology and cultural heritage sites