Querying Perception Streams with Spatial Regular Expressions
This addresses the need for general and reproducible pattern matching in perception streams for applications such as robotics and data analysis, though it appears incremental as it builds on existing querying concepts with spatial extensions.
The paper tackles the problem of efficiently querying large volumes of spatial and temporal perception data from fields like robotics and manufacturing, introducing SpREs as a novel querying language and STREM as a pattern matching framework, achieving over 20,000 matches within 296 ms in performance benchmarks.
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.