A Value Function Space Approach for Hierarchical Planning with Signal Temporal Logic Tasks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908502681714688 |
|---|---|
| author | Liu, Peiran He, Yiting Qin, Yihao Zhou, Hang Ji, Yiding |
| author_facet | Liu, Peiran He, Yiting Qin, Yihao Zhou, Hang Ji, Yiding |
| contents | Signal Temporal Logic (STL) has emerged as an expressive language for reasoning intricate planning objectives. However, existing STL-based methods often assume full observation and known dynamics, which imposes constraints on real-world applications. To address this challenge, we propose a hierarchical planning framework that starts by constructing the Value Function Space (VFS) for state and action abstraction, which embeds functional information about affordances of the low-level skills. Subsequently, we utilize a neural network to approximate the dynamics in the VFS and employ sampling based optimization to synthesize high-level skill sequences that maximize the robustness measure of the given STL tasks in the VFS. Then those skills are executed in the low-level environment. Empirical evaluations in the Safety Gym and ManiSkill environments demonstrate that our method accomplish the STL tasks without further training in the low-level environments, substantially reducing the training burdens. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01923 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Value Function Space Approach for Hierarchical Planning with Signal Temporal Logic Tasks Liu, Peiran He, Yiting Qin, Yihao Zhou, Hang Ji, Yiding Robotics Signal Temporal Logic (STL) has emerged as an expressive language for reasoning intricate planning objectives. However, existing STL-based methods often assume full observation and known dynamics, which imposes constraints on real-world applications. To address this challenge, we propose a hierarchical planning framework that starts by constructing the Value Function Space (VFS) for state and action abstraction, which embeds functional information about affordances of the low-level skills. Subsequently, we utilize a neural network to approximate the dynamics in the VFS and employ sampling based optimization to synthesize high-level skill sequences that maximize the robustness measure of the given STL tasks in the VFS. Then those skills are executed in the low-level environment. Empirical evaluations in the Safety Gym and ManiSkill environments demonstrate that our method accomplish the STL tasks without further training in the low-level environments, substantially reducing the training burdens. |
| title | A Value Function Space Approach for Hierarchical Planning with Signal Temporal Logic Tasks |
| topic | Robotics |
| url | https://arxiv.org/abs/2408.01923 |