Learning Long-Horizon Action Dependencies in Sampling-Based Bilevel Planning

Abstract

Autonomous robots will need the ability to make task and motion plans that involve long sequences of actions, e.g. to prepare a meal. One challenge is that the feasibility of actions late in the plan may depend on much earlier actions. This issue is exacerbated if these dependencies exist at a purely geometric level, making them difficult to express for a task planner. Backtracking is a common technique to resolve such geometric dependencies, but its time complexity limits its applicability to short-horizon dependencies. We propose an approach to account for these dependencies by learning a search heuristic for task and motion planning. We evaluate our approach on five quasi-static simulated domains and show a substantial improvement in success rate over the baselines.

Cite

Text

Cieślar et al. "Learning Long-Horizon Action Dependencies in Sampling-Based Bilevel Planning." Proceedings of The 8th Conference on Robot Learning, 2024.

Markdown

[Cieślar et al. "Learning Long-Horizon Action Dependencies in Sampling-Based Bilevel Planning." Proceedings of The 8th Conference on Robot Learning, 2024.](https://mlanthology.org/corl/2024/cieslar2024corl-learning/)

BibTeX

@inproceedings{cieslar2024corl-learning,
  title     = {{Learning Long-Horizon Action Dependencies in Sampling-Based Bilevel Planning}},
  author    = {Cieślar, Bartłomiej and Kaelbling, Leslie Pack and Lozano-Pérez, Tomás and Mendez-Mendez, Jorge},
  booktitle = {Proceedings of The 8th Conference on Robot Learning},
  year      = {2024},
  pages     = {4235-4252},
  volume    = {270},
  url       = {https://mlanthology.org/corl/2024/cieslar2024corl-learning/}
}