DynaRetarget: Dynamically-Feasible Retargeting using Sampling-Based Trajectory Optimization

TL;DR

DynaRetarget introduces a sampling-based trajectory optimization framework for retargeting human motions to humanoid robots, enabling dynamic feasibility and generalization across diverse object properties.

Contribution

The paper presents a novel SBTO framework that refines kinematic trajectories into feasible motions and generalizes across object variations, improving retargeting success.

Findings

Successfully retargeted hundreds of humanoid-object demonstrations.

Achieved higher success rates than the state of the art.

Generalized retargeting across diverse object properties.

Abstract

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.