Pattern Matching for Perception Streams

Jacob Anderson, Georgios Fainekos, Bardh Hoxha, Hideki Okamoto, Danil V. Prokhorov

Abstract: We introduce Spatial Regular Expressions (SpREs) as a novel querying language for pattern matching over perception streams containing spatial and temporal data. To highlight the capabilities of SpREs, we developed the Strem tool as a matching framework that works in both the offline and online domain. We demonstrate the tool through an offline example with an AV dataset, an online example through an integration with the ROS and CARLA simulators, and an initial set of performance benchmarks on various SpRE queries. From our designed matching framework, we are able to find over 20,000 matches within 296 ms making it highly usable in runtime monitoring applications.