Online Goal Recognition using Path Signature and Dynamic Time Warping

2026-05-08

AI Summary

This work addresses two key challenges in online continuous-domain object identification: redundant trajectory representations and the difficulty of cross-trajectory semantic comparison. It introduces path signatures—a concept from rough path theory—into this domain for the first time, enabling compact yet highly expressive encoding of trajectories. By integrating dynamic time warping, the method facilitates effective alignment and comparison between observed trajectories and target hypotheses. The proposed approach significantly enhances trajectory representation capacity and online identification accuracy, consistently outperforming state-of-the-art methods in both prediction precision and real-time planning efficiency, while also demonstrating competitive offline performance.

Abstract

Online goal recognition in continuous domains poses two central challenges: efficiently encoding large trajectories and effectively comparing them. Recent work addresses these challenges by using custom state-space representations and metrics to compare observations against hypotheses. However, these approaches often overlook well-established encoding techniques used in other domains that offer substantial advantages. This paper introduces a novel method for online goal recognition that leverages path signatures, a compact, expressive representation of rough path theory that efficiently captures key semantic features of trajectories, enabling more meaningful comparisons between them. Experiments show that our method consistently outperforms the state of the art in predictive accuracy and online planning efficiency, while remaining competitive offline.

Problem

• online goal recognition
• trajectory encoding
• trajectory comparison
• continuous domains

Innovation

• path signature
• online goal recognition
• trajectory encoding
• dynamic time warping
• rough path theory