Neuro-Symbolic Skill Discovery for Conditional Multi-Level Planning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917300808974336 |
|---|---|
| author | Aktas, Hakan Yildirim, Yigit Gamsiz, Ahmet Firat Akkoc, Deniz Bilge Oztop, Erhan Ugur, Emre |
| author_facet | Aktas, Hakan Yildirim, Yigit Gamsiz, Ahmet Firat Akkoc, Deniz Bilge Oztop, Erhan Ugur, Emre |
| contents | This paper proposes a novel learning architecture for acquiring generalizable high-level symbolic skills from a few unlabeled low-level skill trajectory demonstrations. The architecture involves neural networks for symbol discovery and low-level controller acquisition and a multi-level planning pipeline that utilizes the discovered symbols and the learned low-level controllers. The discovered action symbols are automatically interpreted using visual language models that are also responsible for generating high-level plans. While extracting high-level symbols, our model preserves the low-level information so that low-level action planning can be carried out by using gradient-based planning. To assess the efficacy of our method, we tested the high and low-level planning performance of our architecture by using simulated and real-world experiments across various tasks. The experiments have shown that our method is able to manipulate objects in unseen locations and plan and execute long-horizon tasks by using novel action sequences, even in highly cluttered environments when cued by only a few demonstrations that cover small regions of the environment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10045 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neuro-Symbolic Skill Discovery for Conditional Multi-Level Planning Aktas, Hakan Yildirim, Yigit Gamsiz, Ahmet Firat Akkoc, Deniz Bilge Oztop, Erhan Ugur, Emre Robotics Artificial Intelligence Machine Learning This paper proposes a novel learning architecture for acquiring generalizable high-level symbolic skills from a few unlabeled low-level skill trajectory demonstrations. The architecture involves neural networks for symbol discovery and low-level controller acquisition and a multi-level planning pipeline that utilizes the discovered symbols and the learned low-level controllers. The discovered action symbols are automatically interpreted using visual language models that are also responsible for generating high-level plans. While extracting high-level symbols, our model preserves the low-level information so that low-level action planning can be carried out by using gradient-based planning. To assess the efficacy of our method, we tested the high and low-level planning performance of our architecture by using simulated and real-world experiments across various tasks. The experiments have shown that our method is able to manipulate objects in unseen locations and plan and execute long-horizon tasks by using novel action sequences, even in highly cluttered environments when cued by only a few demonstrations that cover small regions of the environment. |
| title | Neuro-Symbolic Skill Discovery for Conditional Multi-Level Planning |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2410.10045 |