Technical Papers
Interactive Character Animation by Learning Multi-Objective Control
Event Type
Technical Papers
Registration Categories
TimeThursday, 6 December 20185:07pm - 5:33pm
DescriptionWe present an approach that learns to act from raw motion data for interactive
character animation. Our motion generator takes a continuous
stream of control inputs and generates the character’s motion in an online
manner. The key insight is modeling rich connections between a multitude
of control objectives and a large repertoire of actions. The model is trained
using Recurrent Neural Network conditioned to deal with spatiotemporal
constraints and structural variabilities in human motion. We also present a
new data augmentation method that allows the model to be learned even
from a small to moderate amount of training data. The learning process is
fully automatic if it learns the motion of a single character, and requires minimal
user intervention if it has to deal with props and interaction between
multiple characters.