IJCAI 2023poster0 citations
Reliable Neuro-Symbolic Abstractions for Planning and Learning
Abstract
Although state-of-the-art hierarchical robot planning algorithms allow robots to efficiently compute long-horizon motion plans for achieving user desired tasks, these methods typically rely upon environment-dependent state and action abstractions that need to be hand-designed by experts. On the other hand, non-hierarchical robot planning approaches fail to compute solutions for complex tasks that require reasoning over a long horizon. My research addresses these problems by proposing an approach for learning abstractions and developing hierarchical planners that efficiently use learned abstractions to boost robot planning performance and provide strong guarantees of reliability.
Planning and Scheduling: PS: Robot planningPlanning and Scheduling: PS: Hierarchical planningPlanning and Scheduling: PS: Learning in planning and schedulingPlanning and Scheduling: PS: Planning under uncertaintyRobotics: ROB: Learning in roboticsRobotics: ROB: Motion and path planning
BibTeX
@inproceedings{ijcai2023p821,
title = {Reliable Neuro-Symbolic Abstractions for Planning and Learning},
author = {Shah, Naman},
booktitle = {Proceedings of the Thirty-Second International Joint Conference on
Artificial Intelligence, {IJCAI-23}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Edith Elkind},
pages = {7093--7094},
year = {2023},
month = {8},
note = {Doctoral Consortium},
doi = {10.24963/ijcai.2023/821},
url = {https://doi.org/10.24963/ijcai.2023/821},
}