LSTM-Based Goal Recognition in Latent Space
This addresses the challenge of real-world goal recognition applications where existing methods have overly strong requirements, though it appears incremental as it builds on recurrent neural network advances.
The paper tackles the problem of goal recognition from raw data without requiring extensive domain knowledge or nearly complete behavior samples, by using an LSTM-based classification approach on encoded plan traces. It demonstrates superiority over state-of-the-art methods in image-based domains under certain conditions.
Approaches to goal recognition have progressively relaxed the requirements about the amount of domain knowledge and available observations, yielding accurate and efficient algorithms capable of recognizing goals. However, to recognize goals in raw data, recent approaches require either human engineered domain knowledge, or samples of behavior that account for almost all actions being observed to infer possible goals. This is clearly too strong a requirement for real-world applications of goal recognition, and we develop an approach that leverages advances in recurrent neural networks to perform goal recognition as a classification task, using encoded plan traces for training. We empirically evaluate our approach against the state-of-the-art in goal recognition with image-based domains, and discuss under which conditions our approach is superior to previous ones.