# Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

arXiv: https://arxiv.org/abs/2202.00907 · HTML: https://mlsanity.com/paper/2202.00907/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 42 references that are in the map.
- First posted on arXiv 2 Feb 2022.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets](https://mlsanity.com/paper/1606.03657/) (2016)
- [Patch-based Convolutional Neural Network for Whole Slide Tissue Image Classification](https://mlsanity.com/paper/1504.07947/) (2015)
- [PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning](https://mlsanity.com/paper/1802.08705/) (2018)
- [Learning Sampling Distributions for Robot Motion Planning](https://mlsanity.com/paper/1709.05448/) (2017)
- [Learning Plannable Representations with Causal InfoGAN](https://mlsanity.com/paper/1807.09341/) (2018)
- [Learning Domain-Independent Planning Heuristics with Hypergraph Networks](https://mlsanity.com/paper/1911.13101/) (2019)
- [Learning Generalized Relational Heuristic Networks for Model-Agnostic Planning](https://mlsanity.com/paper/2007.06702/) (2020)
- [LEGO: Leveraging Experience in Roadmap Generation for Sampling-Based Planning](https://mlsanity.com/paper/1907.09574/) (2019)
- [Learned Critical Probabilistic Roadmaps for Robotic Motion Planning](https://mlsanity.com/paper/1910.03701/) (2019)
- [Learning Implicit Sampling Distributions for Motion Planning](https://mlsanity.com/paper/1806.01968/) (2018)
- [Anytime Integrated Task and Motion Policies for Stochastic Environments](https://mlsanity.com/paper/1904.13006/) (2019)
- [Learning Sampling Distributions Using Local 3D Workspace Decompositions for Motion Planning in High Dimensions](https://mlsanity.com/paper/2010.15335/) (2020)
- [Learn and Link: Learning Critical Regions for Efficient Planning](https://mlsanity.com/paper/1903.03258/) (2019)
- [From Patch to Image Segmentation using Fully Convolutional Networks -- Application to Retinal Images](https://mlsanity.com/paper/1904.03892/) (2019)
- [Exploration of Indoor Environments Predicting the Layout of Partially Observed Rooms](https://mlsanity.com/paper/2004.06967/) (2020)

## Built on by (most cited first, 2 of 2)

- [Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities](https://mlsanity.com/paper/2603.24318/) (2026)
- [Multi-Task Option Learning and Discovery for Stochastic Path Planning](https://mlsanity.com/paper/2210.00068/) (2022)

## Abstract (arXiv)

This paper addresses the problem of learning abstractions that boost robot planning performance while providing strong guarantees of reliability. 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. We present a new approach for bootstrapping the entire hierarchical planning process. This allows us to compute abstract states and actions for new environments automatically using the critical regions predicted by a deep neural network with an auto-generated robot-specific architecture. We show that the learned abstractions can be used with a novel multi-source bi-directional hierarchical robot planning algorithm that is sound and probabilistically complete. An extensive empirical evaluation on twenty different settings using holonomic and non-holonomic robots shows that (a) our learned abstractions provide the information necessary for efficient multi-source hierarchical planning; and that (b) this approach of learning, abstractions, and planning outperforms state-of-the-art baselines by nearly a factor of ten in terms of planning time on test environments not seen during training.