Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning and Control-Informed Steering
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912615044743168 |
|---|---|
| author | D'Elia, Evelyn Viceconte, Paolo Maria Rapetti, Lorenzo Ferigo, Diego Romualdi, Giulio L'Erario, Giuseppe Camoriano, Raffaello Pucci, Daniele |
| author_facet | D'Elia, Evelyn Viceconte, Paolo Maria Rapetti, Lorenzo Ferigo, Diego Romualdi, Giulio L'Erario, Giuseppe Camoriano, Raffaello Pucci, Daniele |
| contents | Recent trends in humanoid robot control have successfully employed imitation learning to enable the learned generation of smooth, human-like trajectories from human data. While these approaches make more realistic motions possible, they are limited by the amount of available motion data, and do not incorporate prior knowledge about the physical laws governing the system and its interactions with the environment. Thus they may violate such laws, leading to divergent trajectories and sliding contacts which limit real-world stability. We address such limitations via a two-pronged learning strategy which leverages the known physics of the system and fundamental control principles. First, we encode physics priors during supervised imitation learning to promote trajectory feasibility. Second, we minimize drift at inference time by applying a proportional-integral controller directly to the generated output state. We validate our method on various locomotion behaviors for the ergoCub humanoid robot, where a physics-informed loss encourages zero contact foot velocity. Our experiments demonstrate that the proposed approach is compatible with multiple controllers on a real robot and significantly improves the accuracy and physical constraint conformity of generated trajectories. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_24697 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning and Control-Informed Steering D'Elia, Evelyn Viceconte, Paolo Maria Rapetti, Lorenzo Ferigo, Diego Romualdi, Giulio L'Erario, Giuseppe Camoriano, Raffaello Pucci, Daniele Robotics Machine Learning Systems and Control Recent trends in humanoid robot control have successfully employed imitation learning to enable the learned generation of smooth, human-like trajectories from human data. While these approaches make more realistic motions possible, they are limited by the amount of available motion data, and do not incorporate prior knowledge about the physical laws governing the system and its interactions with the environment. Thus they may violate such laws, leading to divergent trajectories and sliding contacts which limit real-world stability. We address such limitations via a two-pronged learning strategy which leverages the known physics of the system and fundamental control principles. First, we encode physics priors during supervised imitation learning to promote trajectory feasibility. Second, we minimize drift at inference time by applying a proportional-integral controller directly to the generated output state. We validate our method on various locomotion behaviors for the ergoCub humanoid robot, where a physics-informed loss encourages zero contact foot velocity. Our experiments demonstrate that the proposed approach is compatible with multiple controllers on a real robot and significantly improves the accuracy and physical constraint conformity of generated trajectories. |
| title | Stabilizing Humanoid Robot Trajectory Generation via Physics-Informed Learning and Control-Informed Steering |
| topic | Robotics Machine Learning Systems and Control |
| url | https://arxiv.org/abs/2509.24697 |