From Simple to Complex Skills: The Case of In-Hand Object Reorientation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929668375969792 |
|---|---|
| author | Qi, Haozhi Yi, Brent Lambeta, Mike Ma, Yi Calandra, Roberto Malik, Jitendra |
| author_facet | Qi, Haozhi Yi, Brent Lambeta, Mike Ma, Yi Calandra, Roberto Malik, Jitendra |
| contents | Learning policies in simulation and transferring them to the real world has become a promising approach in dexterous manipulation. However, bridging the sim-to-real gap for each new task requires substantial human effort, such as careful reward engineering, hyperparameter tuning, and system identification. In this work, we present a system that leverages low-level skills to address these challenges for more complex tasks. Specifically, we introduce a hierarchical policy for in-hand object reorientation based on previously acquired rotation skills. This hierarchical policy learns to select which low-level skill to execute based on feedback from both the environment and the low-level skill policies themselves. Compared to learning from scratch, the hierarchical policy is more robust to out-of-distribution changes and transfers easily from simulation to real-world environments. Additionally, we propose a generalizable object pose estimator that uses proprioceptive information, low-level skill predictions, and control errors as inputs to estimate the object pose over time. We demonstrate that our system can reorient objects, including symmetrical and textureless ones, to a desired pose. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_05439 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | From Simple to Complex Skills: The Case of In-Hand Object Reorientation Qi, Haozhi Yi, Brent Lambeta, Mike Ma, Yi Calandra, Roberto Malik, Jitendra Robotics Artificial Intelligence Machine Learning Learning policies in simulation and transferring them to the real world has become a promising approach in dexterous manipulation. However, bridging the sim-to-real gap for each new task requires substantial human effort, such as careful reward engineering, hyperparameter tuning, and system identification. In this work, we present a system that leverages low-level skills to address these challenges for more complex tasks. Specifically, we introduce a hierarchical policy for in-hand object reorientation based on previously acquired rotation skills. This hierarchical policy learns to select which low-level skill to execute based on feedback from both the environment and the low-level skill policies themselves. Compared to learning from scratch, the hierarchical policy is more robust to out-of-distribution changes and transfers easily from simulation to real-world environments. Additionally, we propose a generalizable object pose estimator that uses proprioceptive information, low-level skill predictions, and control errors as inputs to estimate the object pose over time. We demonstrate that our system can reorient objects, including symmetrical and textureless ones, to a desired pose. |
| title | From Simple to Complex Skills: The Case of In-Hand Object Reorientation |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2501.05439 |