Discovering State and Action Abstractions for Generalized Task and Motion Planning
Name
2109.11082.pdf
Description
Submitted version
Size
18.49 MB
Format
Adobe PDF
Checksum (MD5)
90e01373485739dfe55f6ba56652ef87
Author(s)
Curtis, Aidan
Silver, Tom
Tenenbaum, Joshua B
Lozano-Pérez, Tomás
Kaelbling, Leslie
Date Issued
2022
Journal
Proceedings of the AAAI Conference on Artificial Intelligence
Publisher
Association for the Advancement of Artificial Intelligence (AAAI)
Citation
Curtis, Aidan, Silver, Tom, Tenenbaum, Joshua B, Lozano-Pérez, Tomás and Kaelbling, Leslie. 2022. "Discovering State and Action Abstractions for Generalized Task and Motion Planning." Proceedings of the AAAI Conference on Artificial Intelligence, 36 (5).
Version
Original manuscript
Abstract
Generalized planning accelerates classical planning by finding an algorithm-like policy that solves multiple instances of a task. A generalized plan can be learned from a few training examples and applied to an entire domain of problems. Generalized planning approaches perform well in discrete AI planning problems that involve large numbers of objects and extended action sequences to achieve the goal. In this paper, we propose an algorithm for learning features, abstractions, and generalized plans for continuous robotic task and motion planning (TAMP) and examine the unique difficulties that arise when forced to consider geometric and physical constraints as a part of the generalized plan. Additionally, we show that these simple generalized plans learned from only a handful of examples can be used to improve the search efficiency of TAMP solvers.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1609/AAAI.V36I5.20475
