Latent Adaptive Planner for Dynamic Manipulation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914167736238080 |
|---|---|
| author | Noh, Donghun Kong, Deqian Zhao, Minglu Lizarraga, Andrew Xie, Jianwen Wu, Ying Nian Hong, Dennis |
| author_facet | Noh, Donghun Kong, Deqian Zhao, Minglu Lizarraga, Andrew Xie, Jianwen Wu, Ying Nian Hong, Dennis |
| contents | We present the Latent Adaptive Planner (LAP), a trajectory-level latent-variable policy for dynamic nonprehensile manipulation (e.g., box catching) that formulates planning as inference in a low-dimensional latent space and is learned effectively from human demonstration videos. During execution, LAP achieves real-time adaptation by maintaining a posterior over the latent plan and performing variational replanning as new observations arrive. To bridge the embodiment gap between humans and robots, we introduce a model-based proportional mapping that regenerates accurate kinematic-dynamic joint states and object positions from human demonstrations. Through challenging box catching experiments with varying object properties, LAP demonstrates superior success rates, trajectory smoothness, and energy efficiency by learning human-like compliant motions and adaptive behaviors. Overall, LAP enables dynamic manipulation with real-time adaptation and successfully transfer across heterogeneous robot platforms using the same human demonstration videos. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03077 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Latent Adaptive Planner for Dynamic Manipulation Noh, Donghun Kong, Deqian Zhao, Minglu Lizarraga, Andrew Xie, Jianwen Wu, Ying Nian Hong, Dennis Robotics Artificial Intelligence Machine Learning We present the Latent Adaptive Planner (LAP), a trajectory-level latent-variable policy for dynamic nonprehensile manipulation (e.g., box catching) that formulates planning as inference in a low-dimensional latent space and is learned effectively from human demonstration videos. During execution, LAP achieves real-time adaptation by maintaining a posterior over the latent plan and performing variational replanning as new observations arrive. To bridge the embodiment gap between humans and robots, we introduce a model-based proportional mapping that regenerates accurate kinematic-dynamic joint states and object positions from human demonstrations. Through challenging box catching experiments with varying object properties, LAP demonstrates superior success rates, trajectory smoothness, and energy efficiency by learning human-like compliant motions and adaptive behaviors. Overall, LAP enables dynamic manipulation with real-time adaptation and successfully transfer across heterogeneous robot platforms using the same human demonstration videos. |
| title | Latent Adaptive Planner for Dynamic Manipulation |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2505.03077 |