A long-running research line in which robots maintain predictive internal models, generate expected observations, direct perception toward informative discrepancies, and use simulation to plan.
Uses a dynamic 3-D internal world model to predict what a robot should see; discrepancies between prediction and observation drive active visual processing and obstacle avoidance.
Compares real video with synthetic imagery generated from an internal simulation so behaviorally significant differences can be detected and tracked efficiently.
Maintains a real-time virtual copy of robot and environment, compares expected and observed data through Match-Mediated Difference, and uses simulation of possible futures for planning.
Extends predictive internal world modeling to human–robot coordination, using active perception, simulation, and task-dependent visual context to support interaction.
Uses a synchronized 3-D virtual world as a common representation for physical understanding, cognitive understanding, prediction, and human–robot collaboration.
Continues the predictive world-model lineage using Unreal Engine 5 to maintain a robot mental model synchronized with the physical environment.