Action sequencing using visual permutations

TL;DR

This paper introduces a permutation-based neural approach for action sequencing from visual input, demonstrating improved performance and scalability over traditional methods in complex tasks.

Contribution

It proposes a novel permutation perspective for neural action sequencing, enabling better reasoning about action orderings and scaling to larger action sets.

Findings

Neural models with latent permutations outperform standard architectures.

Permutation-based methods accelerate traditional planning techniques.

The approach scales to larger action sets than previous models.

Abstract

Humans can easily reason about the sequence of high level actions needed to complete tasks, but it is particularly difficult to instil this ability in robots trained from relatively few examples. This work considers the task of neural action sequencing conditioned on a single reference visual state. This task is extremely challenging as it is not only subject to the significant combinatorial complexity that arises from large action sets, but also requires a model that can perform some form of symbol grounding, mapping high dimensional input data to actions, while reasoning about action relationships. This paper takes a permutation perspective and argues that action sequencing benefits from the ability to reason about both permutations and ordering concepts. Empirical analysis shows that neural models trained with latent permutations outperform standard neural architectures in constrained action sequencing tasks. Results also show that action sequencing using visual permutations is an effective mechanism to initialise and speed up traditional planning techniques and successfully scales to far greater action set sizes than models considered previously.