Presentation
Synthesizing Physical Character-scene Interactions
DescriptionWe present a system that uses adversarial imitation learning and reinforcement learning to train physically simulated characters that perform scene interaction tasks without manual annotation. Using an efficient approach to randomize the training objects during training enables our method to generalize beyond the objects and scenarios in the training dataset.
Event Type
Technical Paper
TimeThursday, 10 August 202311:17am - 11:27am PDT
LocationPetree Hall C
Research & Education
Livestreamed
Recorded
Animation/Simulation
Artificial Intelligence/Machine Learning
FC
FCS
V
VS
EFC