Prioritized motion retargeting improves humanoid robot movements
PriMoRetarget: Humanoid Motion Transfer Through Prioritized Motion Retargeting
RoboticsGraphics
Summary
Motion retargeting means copying human motions onto robots, but it gets tricky when robots interact with objects or other characters. The authors propose a method that prioritizes important parts of the motion, like foot placement and hand contacts, over less important details. This makes the robot movements more accurate and reliable, especially for tasks involving interactions. Their method works better than older approaches that try to balance everything at once.
What this means in practice
- •For robotics engineers: Produce more accurate and reliable humanoid robot motions that preserve critical contact points during manipulation and interaction tasks.
- •For animation studios: Generate realistic humanoid animation sequences that better maintain interactions with objects and other characters by prioritizing key motion features.
Authors
Nicholas Ioannidis, Dun Yang, Max Smith, Tue Vu, Ziyu Zhang, Shayegan Omidshafiei, Xue Bin Peng
Abstract
Motion retargeting is a critical preprocessing step for transferring human motion data to humanoid robots. While existing methods are effective for single-character motions, interactions involving multiple characters and objects introduce additional contacts and spatial relationships that must be preserved. Retargeting is commonly formulated as a weighted multi-objective optimization problem, where conflicting objectives can require careful tuning of relative weights and can still compromise important motion characteristics. We introduce PriMoRetarget, a prioritized motion-retargeting framework that replaces relative objective weighting with an explicit priority hierarchy. Lower-priority updates are constrained to preserve higher-priority objectives, allowing critical characteristics such as foot placement and interaction contacts to take precedence over lower-priority pose objectives. The method is evaluated on four datasets spanning single-character motion, character-object manipulation, and character-character interactions. The resulting motions better preserve task-relevant interactions and provide reference trajectories that can be tracked more reliably than those produced by widely used retargeting methods.