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 …

Synthesizing graceful and life-like behaviors for physically simulated characters has been a
fundamental challenge in computer animation. Data-driven methods that leverage motion …

Human motion synthesis is an important problem for applications in graphics and gaming,
and even in simulation environments for robotics. Existing methods require accurate motion …

Learning locomotion skills is a challenging problem. To generate realistic and smooth
locomotion, existing methods use motion capture, finite state machines or morphology …

While a lot of progress has recently been made in dynamic motion planning for humanoid
robots, much of this work has remained limited to simulation. Here we show that executing …

We present a framework that enables the discovery of diverse and natural-looking motion
strategies for athletic skills such as the high jump. The strategies are realized as control …

Using joint actuators to drive the skeletal movements is a common practice in character
animation, but the resultant torque patterns are often unnatural or infeasible for real humans …

Emerging research in computer graphics, inverse problems, and machine learning requires
us to differentiate and optimize parametric discontinuities. These discontinuities appear in …

This paper explores the benefits of using multiple gaits in a single robot. Inspired by nature,
where humans and animals use different gaits to increase their energetic economy, we …

Predictive simulation is a powerful approach for analyzing human locomotion. Unlike
techniques that track experimental data, predictive simulations synthesize gaits by …