Character Control With Neural Networks And Machine Learning In this 2018 GDC talk, Ubisoft’s Daniel Holden (@anorangeduck) shows how data-driven systems can vastly reduce the complexity...
DReCon: Data-Driven Responsive Control Of Physics-Based Characters “[Ubisoft] propose a two-step approach for building responsive simulated character controllers from unstructured motion capture data. First, meaningful...
Phase-Functioned Neural Networks For Character Control This exciting research from Daniel Holden, (University of Edinburgh), Taku Komura, (University of Edinburgh) & Jun Saito, (Method...