DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization
Addresses the bottleneck of generating large-scale humanoid loco-manipulation datasets for training control policies.
DynaRetarget retargets human motions to humanoid control policies using a Sampling-Based Trajectory Optimization framework that refines kinematic trajectories into dynamically feasible motions, achieving higher success rates than prior methods across diverse object properties.
In this paper, we introduce DynaRetarget, a complete pipeline for retargeting human motions to humanoid control policies. The core component of DynaRetarget is a novel Sampling-Based Trajectory Optimization (SBTO) framework that refines imperfect kinematic trajectories into dynamically feasible motions. SBTO incrementally advances the optimization horizon, enabling optimization over the entire trajectory for long-horizon tasks. We validate DynaRetarget by successfully retargeting hundreds of humanoid-object demonstrations and achieving higher success rates than the state of the art. The framework also generalizes across varying object properties, such as mass, size, and geometry, using the same tracking objective. This ability to robustly retarget diverse demonstrations opens the door to generating large-scale synthetic datasets of humanoid loco-manipulation trajectories, addressing a major bottleneck in real-world data collection.