Advances in artificial intelligence are stimulating interest in neuroscience. However, most
attention is given to discrete tasks with simple action spaces, such as board games and …

Reinforcement Learning is an area of Machine Learning focused on how agents can be
trained to make sequential decisions, and achieve a particular goal within an arbitrary …

Denoising diffusion models hold great promise for generating diverse and realistic human
motions. However, existing motion diffusion models largely disregard the laws of physics in …

A longstanding goal in character animation is to combine data-driven specification of
behavior with a system that can execute a similar behavior in a physical simulation, thus …

Simulations are attractive environments for training agents as they provide an abundant
source of data and alleviate certain safety concerns during the training process. But the …

In this work we present a novel, robust transition generation technique that can serve as a
new tool for 3D animators, based on adversarial recurrent neural networks. The system …

High-quality motion capture datasets are now publicly available, and researchers have used
them to create kinematics-based controllers that can generate plausible and diverse human …

Accurate estimation of 3D human motion from monocular video requires modeling both
kinematics (body motion without physical forces) and dynamics (motion with physical …

Quadruped motion includes a wide variation of gaits such as walk, pace, trot and canter, and
actions such as jumping, sitting, turning and idling. Applying existing data-driven character …

Many anatomical factors, such as bone geometry and muscle condition, interact to affect
human movements. This work aims to build a comprehensive musculoskeletal model and its …