Imagination-Augmented Deep Learning for Goal Recognition

TL;DR

This paper introduces a novel approach combining symbolic planning and deep learning to improve goal recognition accuracy in real-world and synthetic domains by augmenting neural networks with imagination capabilities.

Contribution

It proposes using symbolic planner-derived plan-cost insights to enhance deep neural networks for goal recognition, bridging symbolic and neural methods.

Findings

Improved goal recognition accuracy over traditional methods

Effective integration of symbolic planning with deep learning

Enhanced performance in both real and synthetic domains

Abstract

Being able to infer the goal of people we observe, interact with, or read stories about is one of the hallmarks of human intelligence. A prominent idea in current goal-recognition research is to infer the likelihood of an agent's goal from the estimations of the costs of plans to the different goals the agent might have. Different approaches implement this idea by relying only on handcrafted symbolic representations. Their application to real-world settings is, however, quite limited, mainly because extracting rules for the factors that influence goal-oriented behaviors remains a complicated task. In this paper, we introduce a novel idea of using a symbolic planner to compute plan-cost insights, which augment a deep neural network with an imagination capability, leading to improved goal recognition accuracy in real and synthetic domains compared to a symbolic recognizer or a deep-learning goal recognizer alone.