Guided Learning of Control Graphs for Physics-Based Characters

Abstract

The difficulty of developing control strategies has been a primary bottleneck in the adoption of physics-based simulations of human motion. We present a method for learning robust feedback strategies around given motion capture clips as well as the transition paths between clips. The output is a control graph that supports real-time physics-based simulation of multiple characters, each capable of a diverse range of robust movement skills, such as walking, running, sharp turns, cartwheels, spin-kicks, and flips. The control fragments which comprise the control graph are developed using guided learning. This leverages the results of open-loop sampling-based reconstruction in order to produce state-action pairs which are then transformed into a linear feedback policy for each control fragment using linear regression. Our synthesis framework allows for the development of robust controllers with a minimal amount of prior knowledge.

Inverse Kinematics Techniques in Computer Graphics: A Survey

“…a humanoid model, to additionally consider the importance priorities, and physiological constraints of the model. Since IK does not directly address dynamic constraints, such as momentum conservation during ballistic motion, significant efforts have been made to design physically based interactive tools to ensure the production of plausible motions [KSPW04, YLvdP07, LPY16, ATK16]. Physics‐based character animation aims at guiding the IK solvers to provide a more natural motion that remains within a feasible set of movements.…”

An Introduction to Trajectory Optimization: How to Do Your Own Direct Collocation

“…For more complex systems where the contact sequence is unknown, you can use through-contact trajectory optimization to compute the solution [40,48] (see section 9.10). If you need to use the time-stepping simulator, then you can use some of the methods developed by the computer graphics community [60,61,1,34].…”

Real‐time Locomotion Controller using an Inverted‐Pendulum‐based Abstract Model

“…Liu et al [LYvdPG12] also developed a motion controller with terrain obstacles, and the controlled character traverses given classes of terrain with dynamic gaits. Liu et al [LPY16] have also constructed control graphs based on motion capture sequences. The control graphs provide control signals that are capable of simulating physically plausible character motion.…”