Using Deep Learning to Bootstrap Abstractions for Hierarchical Robot Planning

TL;DR

This paper introduces a deep learning-based method to automatically generate environment-specific abstractions for hierarchical robot planning, significantly improving planning efficiency and reliability across diverse settings.

Contribution

It presents a novel approach that bootstraps hierarchical planning with learned abstractions, eliminating the need for manual environment-dependent design.

Findings

Learned abstractions enable efficient multi-source hierarchical planning.

The approach outperforms state-of-the-art baselines by nearly ten times in planning time.

The method is effective across twenty different robot environments.

Abstract

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.