ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917469191405568 |
|---|---|
| author | Müller, David Serifi, Agon Christen, Sammy Grandia, Ruben Knoop, Espen Bächer, Moritz |
| author_facet | Müller, David Serifi, Agon Christen, Sammy Grandia, Ruben Knoop, Espen Bächer, Moritz |
| contents | Retargeting human kinematic reference motion onto a robot's morphology remains a formidable challenge. Existing methods often produce physical inconsistencies, such as foot sliding, self-collisions, or dynamically infeasible motions, which hinder downstream imitation learning. We propose a bilevel optimization framework that jointly adapts reference motions to a robot's morphology while training a tracking policy using reinforcement learning. To make the optimization tractable, we derive an approximate gradient for the upper-level loss. Our framework requires only a sparse set of semantic rigid-body correspondences and eliminates the need for manual tuning by identifying optimal values for a parameterization expressive enough to preserve characteristic motion across different embodiments. Moreover, by integrating retargeting directly with physics simulation, we produce physically plausible motions that facilitate robust imitation learning. We validate our method in simulation and on hardware, demonstrating challenging motions for morphologies that differ significantly from a human, including retargeting onto a quadruped. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_06593 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting Müller, David Serifi, Agon Christen, Sammy Grandia, Ruben Knoop, Espen Bächer, Moritz Robotics Graphics Machine Learning Retargeting human kinematic reference motion onto a robot's morphology remains a formidable challenge. Existing methods often produce physical inconsistencies, such as foot sliding, self-collisions, or dynamically infeasible motions, which hinder downstream imitation learning. We propose a bilevel optimization framework that jointly adapts reference motions to a robot's morphology while training a tracking policy using reinforcement learning. To make the optimization tractable, we derive an approximate gradient for the upper-level loss. Our framework requires only a sparse set of semantic rigid-body correspondences and eliminates the need for manual tuning by identifying optimal values for a parameterization expressive enough to preserve characteristic motion across different embodiments. Moreover, by integrating retargeting directly with physics simulation, we produce physically plausible motions that facilitate robust imitation learning. We validate our method in simulation and on hardware, demonstrating challenging motions for morphologies that differ significantly from a human, including retargeting onto a quadruped. |
| title | ReActor: Reinforcement Learning for Physics-Aware Motion Retargeting |
| topic | Robotics Graphics Machine Learning |
| url | https://arxiv.org/abs/2605.06593 |