Jacta: A Versatile Planner for Learning Dexterous and Whole-body Manipulation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917818013843456 |
|---|---|
| author | Brüdigam, Jan Abbas, Ali-Adeeb Sorokin, Maks Fang, Kuan Hung, Brandon Guru, Maya Sosnowski, Stefan Wang, Jiuguang Hirche, Sandra Cleac'h, Simon Le |
| author_facet | Brüdigam, Jan Abbas, Ali-Adeeb Sorokin, Maks Fang, Kuan Hung, Brandon Guru, Maya Sosnowski, Stefan Wang, Jiuguang Hirche, Sandra Cleac'h, Simon Le |
| contents | Robotic manipulation is challenging due to discontinuous dynamics, as well as high-dimensional state and action spaces. Data-driven approaches that succeed in manipulation tasks require large amounts of data and expert demonstrations, typically from humans. Existing planners are restricted to specific systems and often depend on specialized algorithms for using demonstrations. Therefore, we introduce a flexible motion planner tailored to dexterous and whole-body manipulation tasks. Our planner creates readily usable demonstrations for reinforcement learning algorithms, eliminating the need for additional training pipeline complexities. With this approach, we can efficiently learn policies for complex manipulation tasks, where traditional reinforcement learning alone only makes little progress. Furthermore, we demonstrate that learned policies are transferable to real robotic systems for solving complex dexterous manipulation tasks.
Project website: https://jacta-manipulation.github.io/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01258 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Jacta: A Versatile Planner for Learning Dexterous and Whole-body Manipulation Brüdigam, Jan Abbas, Ali-Adeeb Sorokin, Maks Fang, Kuan Hung, Brandon Guru, Maya Sosnowski, Stefan Wang, Jiuguang Hirche, Sandra Cleac'h, Simon Le Robotics Robotic manipulation is challenging due to discontinuous dynamics, as well as high-dimensional state and action spaces. Data-driven approaches that succeed in manipulation tasks require large amounts of data and expert demonstrations, typically from humans. Existing planners are restricted to specific systems and often depend on specialized algorithms for using demonstrations. Therefore, we introduce a flexible motion planner tailored to dexterous and whole-body manipulation tasks. Our planner creates readily usable demonstrations for reinforcement learning algorithms, eliminating the need for additional training pipeline complexities. With this approach, we can efficiently learn policies for complex manipulation tasks, where traditional reinforcement learning alone only makes little progress. Furthermore, we demonstrate that learned policies are transferable to real robotic systems for solving complex dexterous manipulation tasks. Project website: https://jacta-manipulation.github.io/ |
| title | Jacta: A Versatile Planner for Learning Dexterous and Whole-body Manipulation |
| topic | Robotics |
| url | https://arxiv.org/abs/2408.01258 |