Learning First-Order Symbolic Planning Representations That Are Grounded

TL;DR

This paper introduces a new method for learning grounded first-order planning models from parsed 2D images, combining the interpretability of symbolic models with the grounding benefits of deep learning.

Contribution

It proposes a novel formulation that learns crisp, grounded first-order action models from parsed images, integrating symbolic and visual data for planning.

Findings

Effective learning of planning models from parsed images

Successful planning in Blocks, Sokoban, IPC Grid, Hanoi domains

Combines benefits of symbolic and deep learning approaches

Abstract

Two main approaches have been developed for learning first-order planning (action) models from unstructured data: combinatorial approaches that yield crisp action schemas from the structure of the state space, and deep learning approaches that produce action schemas from states represented by images. A benefit of the former approach is that the learned action schemas are similar to those that can be written by hand; a benefit of the latter is that the learned representations (predicates) are grounded on the images, and as a result, new instances can be given in terms of images. In this work, we develop a new formulation for learning crisp first-order planning models that are grounded on parsed images, a step to combine the benefits of the two approaches. Parsed images are assumed to be given in a simple O2D language (objects in 2D) that involves a small number of unary and binary predicates like "left", "above", "shape", etc. After learning, new planning instances can be given in terms of pairs of parsed images, one for the initial situation and the other for the goal. Learning and planning experiments are reported for several domains including Blocks, Sokoban, IPC Grid, and Hanoi.