A Transfer Learning Method for Goal Recognition Exploiting Cross-Domain Spatial Features

TL;DR

This paper introduces a transfer learning approach that leverages cross-domain spatial features to improve goal recognition in physical environments, especially with limited data and unseen scenarios.

Contribution

It presents a novel method combining few-shot and transfer learning with cross-domain features for intent inference in navigation tasks.

Findings

Enhanced performance with fewer training samples

Better generalization to unseen configurations

Outperforms baseline deep learning methods

Abstract

The ability to infer the intentions of others, predict their goals, and deduce their plans are critical features for intelligent agents. For a long time, several approaches investigated the use of symbolic representations and inferences with limited success, principally because it is difficult to capture the cognitive knowledge behind human decisions explicitly. The trend, nowadays, is increasingly focusing on learning to infer intentions directly from data, using deep learning in particular. We are now observing interesting applications of intent classification in natural language processing, visual activity recognition, and emerging approaches in other domains. This paper discusses a novel approach combining few-shot and transfer learning with cross-domain features, to learn to infer the intent of an agent navigating in physical environments, executing arbitrary long sequences of actions to achieve their goals. Experiments in synthetic environments demonstrate improved performance in terms of learning from few samples and generalizing to unseen configurations, compared to a deep-learning baseline approach.