Probabilistic State-Dependent Grammars for Plan Recognition

TL;DR

This paper introduces Probabilistic State-Dependent Grammars (PSDGs), a new model for plan recognition that incorporates agent states into probabilistic grammars, enabling efficient inference in complex domains.

Contribution

The paper presents PSDGs, extending probabilistic context-free grammars with state-dependent probabilities, and develops inference algorithms for practical plan recognition in dynamic environments.

Findings

Efficient inference algorithms for PSDGs enable practical plan recognition.

Applications demonstrated in traffic monitoring and air combat scenarios.

Extends the domain applicability of probabilistic plan recognition methods.

Abstract

Techniques for plan recognition under uncertainty require a stochastic model of the plan-generation process. We introduce Probabilistic State-Dependent Grammars (PSDGs) to represent an agent's plan-generation process. The PSDG language model extends probabilistic context-free grammars (PCFGs) by allowing production probabilities to depend on an explicit model of the planning agent's internal and external state. Given a PSDG description of the plan-generation process, we can then use inference algorithms that exploit the particular independence properties of the PSDG language to efficiently answer plan-recognition queries. The combination of the PSDG language model and inference algorithms extends the range of plan-recognition domains for which practical probabilistic inference is possible, as illustrated by applications in traffic monitoring and air combat.