Querying Perception Streams with Spatial Regular Expressions

TL;DR

This paper introduces SpREs, a novel pattern matching language for perception streams in dynamic environments, and demonstrates its effectiveness through a new tool, STREM, capable of real-time and offline data analysis.

Contribution

The paper presents SpREs as a new querying language for perception data and the STREM tool for pattern matching, enabling efficient offline and online analysis of perception streams.

Findings

STREM can find over 20,000 matches in 296 ms.

SpREs are effective for pattern matching in perception streams.

STREM supports real-time runtime monitoring applications.

Abstract

Perception in fields like robotics, manufacturing, and data analysis generates large volumes of temporal and spatial data to effectively capture their environments. However, sorting through this data for specific scenarios is a meticulous and error-prone process, often dependent on the application, and lacks generality and reproducibility. In this work, we introduce SpREs as a novel querying language for pattern matching over perception streams containing spatial and temporal data derived from multi-modal dynamic environments. To highlight the capabilities of SpREs, we developed the STREM tool as both an offline and online pattern matching framework for perception data. We demonstrate the offline capabilities of STREM through a case study on a publicly available AV dataset (Woven Planet Perception) and its online capabilities through a case study integrating STREM in ROS with the CARLA simulator. We also conduct performance benchmark experiments on various SpRE queries. Using our matching framework, we are able to find over 20,000 matches within 296 ms making STREM applicable in runtime monitoring applications.