MaskedManipulator: Versatile Whole-Body Manipulation
This addresses the problem of creating intuitive control systems for human animation in computer graphics and robotics, though it appears incremental as it builds on existing motion capture and control methods.
The paper tackles the challenge of synthesizing versatile, physically simulated human motions for full-body object manipulation by introducing MaskedManipulator, a generative control policy that enables users to specify high-level objectives like target object poses, expanding interactive animation beyond task-specific solutions.
We tackle the challenges of synthesizing versatile, physically simulated human motions for full-body object manipulation. Unlike prior methods that are focused on detailed motion tracking, trajectory following, or teleoperation, our framework enables users to specify versatile high-level objectives such as target object poses or body poses. To achieve this, we introduce MaskedManipulator, a generative control policy distilled from a tracking controller trained on large-scale human motion capture data. This two-stage learning process allows the system to perform complex interaction behaviors, while providing intuitive user control over both character and object motions. MaskedManipulator produces goal-directed manipulation behaviors that expand the scope of interactive animation systems beyond task-specific solutions.